1
|
Huang YR, Fan HQ, Kuang YY, Wang P, Lu S. The Relationship Between the Molecular Phenotypes of Brain Gliomas and the Imaging Features and Sensitivity of Radiotherapy and Chemotherapy. Clin Oncol (R Coll Radiol) 2024; 36:541-551. [PMID: 38821723 DOI: 10.1016/j.clon.2024.05.005] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/20/2023] [Revised: 02/28/2024] [Accepted: 05/10/2024] [Indexed: 06/02/2024]
Abstract
Gliomas are the most common primary malignant tumors of the brain, accounting for about 80% of all central nervous system malignancies. With the development of molecular biology, the molecular phenotypes of gliomas have been shown to be closely related to the process of diagnosis and treatment. The molecular phenotype of glioma also plays an important role in guiding treatment plans and evaluating treatment effects and prognosis. However, due to the heterogeneity of the tumors and the trauma associated with the surgical removal of tumor tissue, the application of molecular phenotyping in glioma is limited. With the development of imaging technology, functional magnetic resonance imaging (MRI) can provide structural and function information about tumors in a noninvasive and radiation-free manner. MRI is very important for the diagnosis of intracranial lesions. In recent years, with the development of the technology for tumor molecular diagnosis and imaging, the use of molecular phenotype information and imaging procedures to evaluate the treatment outcome of tumors has become a hot topic. By reviewing the related literature on glioma treatment and molecular typing that has been published in the past 20 years, and referring to the latest 2020 NCCN treatment guidelines, summarizing the imaging characteristic and sensitivity of radiotherapy and chemotherapy of different molecular phenotypes of glioma. In this article, we briefly review the imaging characteristics of different molecular phenotypes in gliomas and their relationship with radiosensitivity and chemosensitivity of gliomas.
Collapse
Affiliation(s)
- Y-R Huang
- Department of Radiation Oncology, Harbin Medical University Cancer Hospital, Harbin, Heilongjiang, China
| | - H-Q Fan
- Department of Radiation Oncology, Harbin Medical University Cancer Hospital, Harbin, Heilongjiang, China
| | - Y-Y Kuang
- Department of Radiation Oncology, Harbin Medical University Cancer Hospital, Harbin, Heilongjiang, China
| | - P Wang
- Department of Radiation Oncology, Harbin Medical University Cancer Hospital, Harbin, Heilongjiang, China
| | - S Lu
- Department of Radiation Oncology, Harbin Medical University Cancer Hospital, Harbin, Heilongjiang, China.
| |
Collapse
|
2
|
Usuzaki T, Inamori R, Shizukuishi T, Morishita Y, Takagi H, Ishikuro M, Obara T, Takase K. Predicting isocitrate dehydrogenase status among adult patients with diffuse glioma using patient characteristics, radiomic features, and magnetic resonance imaging: Multi-modal analysis by variable vision transformer. Magn Reson Imaging 2024; 111:266-276. [PMID: 38815636 DOI: 10.1016/j.mri.2024.05.012] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/21/2024] [Revised: 05/14/2024] [Accepted: 05/22/2024] [Indexed: 06/01/2024]
Abstract
OBJECTIVES To evaluate the performance of the multimodal model, termed variable Vision Transformer (vViT), in the task of predicting isocitrate dehydrogenase (IDH) status among adult patients with diffuse glioma. MATERIALS AND METHODS vViT was designed to predict IDH status using patient characteristics (sex and age), radiomic features, and contrast-enhanced T1-weighted images (CE-T1WI). Radiomic features were extracted from each enhancing tumor (ET), necrotic tumor core (NCR), and peritumoral edematous/infiltrated tissue (ED). CE-T1WI were split into four images and input to vViT. In the training, internal test, and external test, 271 patients with 1070 images (535 IDH wildtype, 535 IDH mutant), 35 patients with 194 images (97 IDH wildtype, 97 IDH mutant), and 291 patients with 872 images (436 IDH wildtype, 436 IDH mutant) were analyzed, respectively. Metrics including accuracy and AUC-ROC were calculated for the internal and external test datasets. Permutation importance analysis combined with the Mann-Whitney U test was performed to compare inputs. RESULTS For the internal test dataset, vViT correctly predicted IDH status for all patients. For the external test dataset, an accuracy of 0.935 (95% confidence interval; 0.913-0.945) and AUC-ROC of 0.887 (0.798-0.956) were obtained. For both internal and external test datasets, CE-T1WI ET radiomic features and patient characteristics had higher importance than other inputs (p < 0.05). CONCLUSIONS The vViT has the potential to be a competent model in predicting IDH status among adult patients with diffuse glioma. Our results indicate that age, sex, and CE-T1WI ET radiomic features have key information in estimating IDH status.
Collapse
Affiliation(s)
- Takuma Usuzaki
- Department of Diagnostic Radiology, Tohoku University Hospital, 1-1 Seiryo-machi, Aoba-ku, Sendai, Miyagi 980-8574, Japan; Miyagi Cancer Center, Miyagi, Japan
| | - Ryusei Inamori
- Radiological Imaging and Informatics, Tohoku University Graduate School of Medicine, Sendai, Japan
| | - Takashi Shizukuishi
- Department of Diagnostic Radiology, Tohoku University Hospital, 1-1 Seiryo-machi, Aoba-ku, Sendai, Miyagi 980-8574, Japan
| | - Yohei Morishita
- Department of Diagnostic Radiology, Tohoku University Hospital, 1-1 Seiryo-machi, Aoba-ku, Sendai, Miyagi 980-8574, Japan
| | - Hidenobu Takagi
- Department of Diagnostic Radiology, Tohoku University Hospital, 1-1 Seiryo-machi, Aoba-ku, Sendai, Miyagi 980-8574, Japan; Department of Advanced MRI Collaborative Research, Graduate School of Medicine, Sendai, Japan
| | - Mami Ishikuro
- Tohoku University Graduate School of Medicine, Division of Molecular Epidemiology, Sendai, Japan
| | - Taku Obara
- Tohoku University Graduate School of Medicine, Division of Molecular Epidemiology, Sendai, Japan; Tohoku University Graduate School of Medicine, Division of Molecular Epidemiology, Department of Preventive Medicine and Epidemiology, Tohoku Medical Megabank Organization, Sendai, Japan; Department of Pharmaceutical Sciences, Tohoku University Hospital, Sendai, Japan
| | - Kei Takase
- Department of Diagnostic Radiology, Tohoku University Hospital, 1-1 Seiryo-machi, Aoba-ku, Sendai, Miyagi 980-8574, Japan
| |
Collapse
|
3
|
Cui Y, Feng J. One solid step to general neuroradiology AI. Eur Radiol 2024:10.1007/s00330-024-11020-y. [PMID: 39179801 DOI: 10.1007/s00330-024-11020-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/07/2024] [Revised: 07/01/2024] [Accepted: 07/19/2024] [Indexed: 08/26/2024]
Affiliation(s)
- Yuanyuan Cui
- Department of Radiology, Second Affiliated Hospital of Naval Medical University, Shanghai, China.
| | - Jie Feng
- Department of Radiology, Corps Hospital of Shanxi province of Chinese People's Armed Police Force, Taiyuan, China.
| |
Collapse
|
4
|
Kudus K, Wagner MW, Namdar K, Bennett J, Nobre L, Tabori U, Hawkins C, Ertl-Wagner BB, Khalvati F. Beyond hand-crafted features for pretherapeutic molecular status identification of pediatric low-grade gliomas. Sci Rep 2024; 14:19102. [PMID: 39154039 PMCID: PMC11330469 DOI: 10.1038/s41598-024-69870-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/08/2024] [Accepted: 08/09/2024] [Indexed: 08/19/2024] Open
Abstract
The use of targeted agents in the treatment of pediatric low-grade gliomas (pLGGs) relies on the determination of molecular status. It has been shown that genetic alterations in pLGG can be identified non-invasively using MRI-based radiomic features or convolutional neural networks (CNNs). We aimed to build and assess a combined radiomics and CNN non-invasive pLGG molecular status identification model. This retrospective study used the tumor regions, manually segmented from T2-FLAIR MR images, of 336 patients treated for pLGG between 1999 and 2018. We designed a CNN and Random Forest radiomics model, along with a model relying on a combination of CNN and radiomic features, to predict the genetic status of pLGG. Additionally, we investigated whether CNNs could predict radiomic feature values from MR images. The combined model (mean AUC: 0.824) outperformed the radiomics model (0.802) and CNN (0.764). The differences in model performance were statistically significant (p-values < 0.05). The CNN was able to learn predictive radiomic features such as surface-to-volume ratio (average correlation: 0.864), and difference matrix dependence non-uniformity normalized (0.924) well but was unable to learn others such as run-length matrix variance (- 0.017) and non-uniformity normalized (- 0.042). Our results show that a model relying on both CNN and radiomic-based features performs better than either approach separately in differentiating the genetic status of pLGGs, and that CNNs are unable to express all handcrafted features.
Collapse
Affiliation(s)
- Kareem Kudus
- Neurosciences & Mental Health Research Program, The Hospital for Sick Children, Toronto, Canada
- Institute of Medical Science, University of Toronto, Toronto, Canada
| | - Matthias W Wagner
- Department of Diagnostic & Interventional Radiology, The Hospital for Sick Children, Toronto, Canada
- Department of Diagnostic and Interventional Neuroradiology, University Hospital Augsburg, Augsburg, Germany
| | - Khashayar Namdar
- Neurosciences & Mental Health Research Program, The Hospital for Sick Children, Toronto, Canada
- Institute of Medical Science, University of Toronto, Toronto, Canada
| | - Julie Bennett
- Division of Hematology and Oncology, The Hospital for Sick Children, Toronto, Canada
- Division of Medical Oncology and Hematology, Princess Margaret Cancer Centre, Toronto, Canada
- Department of Pediatrics, University of Toronto, Toronto, Canada
| | - Liana Nobre
- Department of Paediatrics, University of Alberta, Edmonton, Canada
- Division of Immunology, Hematology/Oncology and Palliative Care, Stollery Children's Hospital, Edmonton, Canada
| | - Uri Tabori
- Division of Hematology and Oncology, The Hospital for Sick Children, Toronto, Canada
| | - Cynthia Hawkins
- Paediatric Laboratory Medicine, Division of Pathology, The Hospital for Sick Children, Toronto, Canada
| | - Birgit Betina Ertl-Wagner
- Neurosciences & Mental Health Research Program, The Hospital for Sick Children, Toronto, Canada
- Institute of Medical Science, University of Toronto, Toronto, Canada
- Department of Diagnostic & Interventional Radiology, The Hospital for Sick Children, Toronto, Canada
- Department of Medical Imaging, University of Toronto, Toronto, Canada
| | - Farzad Khalvati
- Neurosciences & Mental Health Research Program, The Hospital for Sick Children, Toronto, Canada.
- Institute of Medical Science, University of Toronto, Toronto, Canada.
- Department of Diagnostic & Interventional Radiology, The Hospital for Sick Children, Toronto, Canada.
- Department of Medical Imaging, University of Toronto, Toronto, Canada.
- Department of Computer Science, University of Toronto, Toronto, Canada.
- Department of Mechanical and Industrial Engineering, University of Toronto, Toronto, Canada.
| |
Collapse
|
5
|
Wu X, Zhang S, Zhang Z, He Z, Xu Z, Wang W, Jin Z, You J, Guo Y, Zhang L, Huang W, Wang F, Liu X, Yan D, Cheng J, Yan J, Zhang S, Zhang B. Biologically interpretable multi-task deep learning pipeline predicts molecular alterations, grade, and prognosis in glioma patients. NPJ Precis Oncol 2024; 8:181. [PMID: 39152182 PMCID: PMC11329669 DOI: 10.1038/s41698-024-00670-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/15/2024] [Accepted: 08/01/2024] [Indexed: 08/19/2024] Open
Abstract
Deep learning models have been developed for various predictions in glioma; yet, they were constrained by manual segmentation, task-specific design, or a lack of biological interpretation. Herein, we aimed to develop an end-to-end multi-task deep learning (MDL) pipeline that can simultaneously predict molecular alterations and histological grade (auxiliary tasks), as well as prognosis (primary task) in gliomas. Further, we aimed to provide the biological mechanisms underlying the model's predictions. We collected multiscale data including baseline MRI images from 2776 glioma patients across two private (FAHZU and HPPH, n = 1931) and three public datasets (TCGA, n = 213; UCSF, n = 410; and EGD, n = 222). We trained and internally validated the MDL model using our private datasets, and externally validated it using the three public datasets. We used the model-predicted deep prognosis score (DPS) to stratify patients into low-DPS and high-DPS subtypes. Additionally, a radio-multiomics analysis was conducted to elucidate the biological basis of the DPS. In the external validation cohorts, the MDL model achieved average areas under the curve of 0.892-0.903, 0.710-0.894, and 0.850-0.879 for predicting IDH mutation status, 1p/19q co-deletion status, and tumor grade, respectively. Moreover, the MDL model yielded a C-index of 0.723 in the TCGA and 0.671 in the UCSF for the prediction of overall survival. The DPS exhibits significant correlations with activated oncogenic pathways, immune infiltration patterns, specific protein expression, DNA methylation, tumor mutation burden, and tumor-stroma ratio. Accordingly, our work presents an accurate and biologically meaningful tool for predicting molecular subtypes, tumor grade, and survival outcomes in gliomas, which provides personalized clinical decision-making in a global and non-invasive manner.
Collapse
Affiliation(s)
- Xuewei Wu
- Department of Radiology, The First Affiliated Hospital of Jinan University, Guangzhou, Guangdong, China
| | - Shuaitong Zhang
- School of Medical Technology, Beijing Institute of Technology, Beijing, China
| | - Zhenyu Zhang
- Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China
| | - Zicong He
- Department of Radiology, The First Affiliated Hospital of Jinan University, Guangzhou, Guangdong, China
| | - Zexin Xu
- School of Medical Technology, Beijing Institute of Technology, Beijing, China
| | - Weiwei Wang
- Department of Pathology, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China
| | - Zhe Jin
- Department of Radiology, The First Affiliated Hospital of Jinan University, Guangzhou, Guangdong, China
| | - Jingjing You
- Department of Radiology, The First Affiliated Hospital of Jinan University, Guangzhou, Guangdong, China
| | - Yang Guo
- Department of Neurosurgery, The Henan Provincial People's Hospital, Zhengzhou, Henan, China
| | - Lu Zhang
- Department of Radiology, The First Affiliated Hospital of Jinan University, Guangzhou, Guangdong, China
| | - Wenhui Huang
- Department of Radiology, The First Affiliated Hospital of Jinan University, Guangzhou, Guangdong, China
| | - Fei Wang
- Department of Radiology, The First Affiliated Hospital of Jinan University, Guangzhou, Guangdong, China
| | - Xianzhi Liu
- Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China
| | - Dongming Yan
- Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China
| | - Jingliang Cheng
- Department of MRI, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China
| | - Jing Yan
- Department of MRI, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China.
| | - Shuixing Zhang
- Department of Radiology, The First Affiliated Hospital of Jinan University, Guangzhou, Guangdong, China.
| | - Bin Zhang
- Department of Radiology, The First Affiliated Hospital of Jinan University, Guangzhou, Guangdong, China.
| |
Collapse
|
6
|
Habibi MA, Dinpazhouh A, Aliasgary A, Mirjani MS, Mousavinasab M, Ahmadi MR, Minaee P, Eazi S, Shafizadeh M, Gurses ME, Lu VM, Berke CN, Ivan ME, Komotar RJ, Shah AH. Predicting telomerase reverse transcriptase promoter mutation in glioma: A systematic review and diagnostic meta-analysis on machine learning algorithms. Neuroradiol J 2024:19714009241269526. [PMID: 39103206 DOI: 10.1177/19714009241269526] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 08/07/2024] Open
Abstract
BACKGROUND Glioma is one of the most common primary brain tumors. The presence of the telomerase reverse transcriptase promoter (pTERT) mutation is associated with a better prognosis. This study aims to investigate the TERT mutation in patients with glioma using machine learning (ML) algorithms on radiographic imaging. METHOD This study was prepared according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. The electronic databases of PubMed, Embase, Scopus, and Web of Science were searched from inception to August 1, 2023. The statistical analysis was performed using the MIDAS package of STATA v.17. RESULTS A total of 22 studies involving 5371 patients were included for data extraction, with data synthesis based on 11 reports. The analysis revealed a pooled sensitivity of 0.86 (95% CI: 0.78-0.92) and a specificity of 0.80 (95% CI 0.72-0.86). The positive and negative likelihood ratios were 4.23 (95% CI: 2.99-5.99) and 0.18 (95% CI: 0.11-0.29), respectively. The pooled diagnostic score was 3.18 (95% CI: 2.45-3.91), with a diagnostic odds ratio 24.08 (95% CI: 11.63-49.87). The Summary Receiver Operating Characteristic (SROC) curve had an area under the curve (AUC) of 0.89 (95% CI: 0.86-0.91). CONCLUSION The study suggests that ML can predict TERT mutation status in glioma patients. ML models showed high sensitivity (0.86) and moderate specificity (0.80), aiding disease prognosis and treatment planning. However, further development and improvement of ML models are necessary for better performance metrics and increased reliability in clinical practice.
Collapse
Affiliation(s)
- Mohammad Amin Habibi
- Department of Neurosurgery, Shariati Hospital, Tehran University of Medical Science, Tehran, Iran
| | - Ali Dinpazhouh
- Student Research Committee, Faculty of Medicine, Qom University of Medical Science, Qom, Iran
| | - Aliakbar Aliasgary
- Student Research Committee, Faculty of Medicine, Qom University of Medical Science, Qom, Iran
| | - Mohammad Sina Mirjani
- Student Research Committee, Faculty of Medicine, Qom University of Medical Science, Qom, Iran
| | - Mehdi Mousavinasab
- Student Research Committee, Shahid Beheshti University of Medical Science, Tehran, Iran
| | - Mohammad Reza Ahmadi
- Student Research Committee, Shahid Beheshti University of Medical Science, Tehran, Iran
| | - Poriya Minaee
- Student Research Committee, Faculty of Medicine, Qom University of Medical Science, Qom, Iran
| | - SeyedMohammad Eazi
- Student Research Committee, Faculty of Medicine, Qom University of Medical Science, Qom, Iran
| | - Milad Shafizadeh
- Department of Neurosurgery, Shariati Hospital, Tehran University of Medical Science, Tehran, Iran
| | - Muhammet Enes Gurses
- Department of Neurosurgery, Miller School of Medicine, University of Miami, Miami, FL, USA
| | - Victor M Lu
- Department of Neurosurgery, Miller School of Medicine, University of Miami, Miami, FL, USA
| | - Chandler N Berke
- Department of Neurosurgery, Miller School of Medicine, University of Miami, Miami, FL, USA
| | - Michael E Ivan
- Department of Neurosurgery, Miller School of Medicine, University of Miami, Miami, FL, USA
| | - Ricardo J Komotar
- Department of Neurosurgery, Miller School of Medicine, University of Miami, Miami, FL, USA
| | - Ashish H Shah
- Department of Neurosurgery, Miller School of Medicine, University of Miami, Miami, FL, USA
| |
Collapse
|
7
|
Fan L, Wu H, Wu Y, Wu S, Zhao J, Zhu X. Preoperative prediction of rectal Cancer staging combining MRI deep transfer learning, radiomics features, and clinical factors: accurate differentiation from stage T2 to T3. BMC Gastroenterol 2024; 24:247. [PMID: 39103772 DOI: 10.1186/s12876-024-03316-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/31/2024] [Accepted: 07/04/2024] [Indexed: 08/07/2024] Open
Abstract
BACKGROUND This study evaluates the efficacy of integrating MRI deep transfer learning, radiomic signatures, and clinical variables to accurately preoperatively differentiate between stage T2 and T3 rectal cancer. METHODS We included 361 patients with pathologically confirmed stage T2 or T3 rectal cancer, divided into a training set (252 patients) and a test set (109 patients) at a 7:3 ratio. The study utilized features derived from deep transfer learning and radiomics, with Spearman rank correlation and the Least Absolute Shrinkage and Selection Operator (LASSO) regression techniques to reduce feature redundancy. Predictive models were developed using Logistic Regression (LR), Random Forest (RF), Decision Tree (DT), and Support Vector Machine (SVM), selecting the best-performing model for a comprehensive predictive framework incorporating clinical data. RESULTS After removing redundant features, 24 key features were identified. In the training set, the area under the curve (AUC)values for LR, RF, DT, and SVM were 0.867, 0.834, 0.900, and 0.944, respectively; in the test set, they were 0.847, 0.803, 0.842, and 0.910, respectively. The combined model, using SVM and clinical variables, achieved AUCs of 0.946 in the trainingset and 0.920 in the test set. CONCLUSION The study confirms the utility of a combined model of MRI deep transfer learning, radiomic features, and clinical factors for preoperative classification of stage T2 vs. T3 rectal cancer, offering significant technological support for precise diagnosis and potential clinical application.
Collapse
Affiliation(s)
- Lifang Fan
- School of Medical Imageology, Wannan Medical College, Wuhu, 241002, Anhui, China
- Anhui Province Key Laboratory of Cancer Translational Medicine, Bengbu Medical University, 2600 Donghai Avenue, Bengbu, Anhui, 233030, China
| | - Huazhang Wu
- Anhui Province Key Laboratory of Cancer Translational Medicine, Bengbu Medical University, 2600 Donghai Avenue, Bengbu, Anhui, 233030, China
| | - Yimin Wu
- Department of Ultrasound, The Second People's Hospital, WuHu Hospital, East China Normal University, Wuhu, Anhui, 241001, China
| | - Shujian Wu
- Department of Radiology, Yijishan Hospital of Wannan Medical College, Wuhu, Anhui, China
| | - Jinsong Zhao
- School of Medical Imageology, Wannan Medical College, Wuhu, 241002, Anhui, China.
| | - Xiangming Zhu
- Department of Ultrasound, Yijishan Hospital of Wannan Medical College, No.2 Zheshan West Road, Jinghu District, Wuhu, Anhui Province, 241001, China.
| |
Collapse
|
8
|
Yang X, Niu W, Wu K, Li X, Hou H, Tan Y, Wang X, Yang G, Wang L, Zhang H. Diffusion kurtosis imaging-based habitat analysis identifies high-risk molecular subtypes and heterogeneity matching in diffuse gliomas. Ann Clin Transl Neurol 2024; 11:2073-2087. [PMID: 38887966 PMCID: PMC11330218 DOI: 10.1002/acn3.52128] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/06/2024] [Revised: 05/14/2024] [Accepted: 06/02/2024] [Indexed: 06/20/2024] Open
Abstract
OBJECTIVE High-risk types of diffuse gliomas in adults include isocitrate dehydrogenase (IDH) wild-type glioblastomas and grade 4 astrocytomas. Achieving noninvasive prediction of high-risk molecular subtypes of gliomas is important for personalized and precise diagnosis and treatment. METHODS We retrospectively collected data from 116 patients diagnosed with adult diffuse gliomas. Multiple high-risk molecular markers were tested, and various habitat models and whole-tumor models were constructed based on preoperative routine and diffusion kurtosis imaging (DKI) sequences to predict high-risk molecular subtypes of gliomas. Feature selection and model construction utilized Least absolute shrinkage and selection operator (LASSO) and support vector machine (SVM). Finally, the Wilcoxon rank-sum test was employed to explore the correlation between habitat quantitative features (intra-tumor heterogeneity score,ITH score) and heterogeneity, as well as high-risk molecular subtypes. RESULTS The results showed that the habitat analysis model based on DKI performed remarkably well (with AUC values reaching 0.977 and 0.902 in the training and test sets, respectively). The model's performance was further enhanced when combined with clinical variables. (The AUC values were 0.994 and 0.920, respectively.) Additionally, we found a close correlation between ITH score and heterogeneity, with statistically significant differences observed between high-risk and non-high-risk molecular subtypes. INTERPRETATION The habitat model based on DKI is an ideal means for preoperatively predicting high-risk molecular subtypes of gliomas, holding significant value for noninvasively alerting malignant gliomas and those with malignant transformation potential.
Collapse
Affiliation(s)
- Xiangli Yang
- Department of RadiologyFirst Hospital of Shanxi Medical UniversityTaiyuan030001China
- Third Hospital of Shanxi Medical University, Shanxi Bethune Hospital, Shanxi Academy of Medical Sciences, Tongji Shanxi HospitalTaiyuan030032China
- College of Medical Imaging, Shanxi Medical UniversityTaiyuan030001China
| | - Wenju Niu
- College of Medical Imaging, Shanxi Medical UniversityTaiyuan030001China
| | - Kai Wu
- Department of Information ManagementFirst Hospital of Shanxi Medical UniversityTaiyuan030001China
| | - Xiang Li
- College of Medical Imaging, Shanxi Medical UniversityTaiyuan030001China
| | - Heng Hou
- Department of RadiologyFirst Hospital of Shanxi Medical UniversityTaiyuan030001China
| | - Yan Tan
- Department of RadiologyFirst Hospital of Shanxi Medical UniversityTaiyuan030001China
| | - Xiaochun Wang
- Department of RadiologyFirst Hospital of Shanxi Medical UniversityTaiyuan030001China
| | - Guoqiang Yang
- Department of RadiologyFirst Hospital of Shanxi Medical UniversityTaiyuan030001China
- College of Medical Imaging, Shanxi Medical UniversityTaiyuan030001China
- Shanxi Key Laboratory of Intelligent Imaging and NanomedicineFirst Hospital of Shanxi Medical UniversityTaiyuan030001China
| | - Lei Wang
- Beijing Tiantan HospitalCapital Medical UniversityBeijing100050China
| | - Hui Zhang
- Department of RadiologyFirst Hospital of Shanxi Medical UniversityTaiyuan030001China
- College of Medical Imaging, Shanxi Medical UniversityTaiyuan030001China
- Shanxi Key Laboratory of Intelligent Imaging and NanomedicineFirst Hospital of Shanxi Medical UniversityTaiyuan030001China
- Intelligent Imaging Big Data and Functional Nano‐imaging Engineering Research Center of Shanxi ProvinceFirst Hospital of Shanxi Medical UniversityTaiyuan030001China
| |
Collapse
|
9
|
Sanchez I, Rahman R. Radiogenomics as an Integrated Approach to Glioblastoma Precision Medicine. Curr Oncol Rep 2024:10.1007/s11912-024-01580-z. [PMID: 39009914 DOI: 10.1007/s11912-024-01580-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 07/05/2024] [Indexed: 07/17/2024]
Abstract
PURPOSE OF REVIEW Isocitrate dehydrogenase wild-type glioblastoma is the most aggressive primary brain tumour in adults. Its infiltrative nature and heterogeneity confer a dismal prognosis, despite multimodal treatment. Precision medicine is increasingly advocated to improve survival rates in glioblastoma management; however, conventional neuroimaging techniques are insufficient in providing the detail required for accurate diagnosis of this complex condition. RECENT FINDINGS Advanced magnetic resonance imaging allows more comprehensive understanding of the tumour microenvironment. Combining diffusion and perfusion magnetic resonance imaging to create a multiparametric scan enhances diagnostic power and can overcome the unreliability of tumour characterisation by standard imaging. Recent progress in deep learning algorithms establishes their remarkable ability in image-recognition tasks. Integrating these with multiparametric scans could transform the diagnosis and monitoring of patients by ensuring that the entire tumour is captured. As a corollary, radiomics has emerged as a powerful approach to offer insights into diagnosis, prognosis, treatment, and tumour response through extraction of information from radiological scans, and transformation of these tumour characteristics into quantitative data. Radiogenomics, which links imaging features with genomic profiles, has exhibited its ability in characterising glioblastoma, and determining therapeutic response, with the potential to revolutionise management of glioblastoma. The integration of deep learning algorithms into radiogenomic models has established an automated, highly reproducible means to predict glioblastoma molecular signatures, further aiding prognosis and targeted therapy. However, challenges including lack of large cohorts, absence of standardised guidelines and the 'black-box' nature of deep learning algorithms, must first be overcome before this workflow can be applied in clinical practice.
Collapse
Affiliation(s)
- Isabella Sanchez
- Biodiscovery Institute, School of Medicine, University of Nottingham, Nottingham, NG7 2RD, UK
| | - Ruman Rahman
- Biodiscovery Institute, School of Medicine, University of Nottingham, Nottingham, NG7 2RD, UK.
| |
Collapse
|
10
|
Sun C, Jiang C, Wang X, Ma S, Zhang D, Jia W. MR-Based Radiomics Predicts CDK6 Expression and Prognostic Value in High-grade Glioma. Acad Radiol 2024:S1076-6332(24)00364-7. [PMID: 38964985 DOI: 10.1016/j.acra.2024.06.006] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/28/2024] [Revised: 05/28/2024] [Accepted: 06/03/2024] [Indexed: 07/06/2024]
Abstract
RATIONALE AND OBJECTIVES This study aims to assess the prognostic value of Cyclin-dependent kinases 6 (CDK6) expression levels and establish a machine learning-based radiomics model for predicting the expression levels of CDK6 in high-grade gliomas (HGG). MATERIALS AND METHODS Clinical parameters and genomic data were extracted from 310 HGG patients in the Cancer Genome Atlas (TCGA) database and 27 patients in the Repository of Molecular Brain Neoplasia Data (REMBRANDT) database. Univariate and multivariate Cox regression, as well as Kaplan-Meier analysis, were performed for prognosis analysis. The correlation between immune cell Infiltration with CDK6 was assessed using spearman correlation analysis. Radiomic features were extracted from contrast-enhanced magnetic resonance imaging (CE-MRI) in the Cancer Imaging Archive (TCIA) database (n = 82) and REMBRANDT database (n = 27). Logistic regression (LR) and support vector machine (SVM) were employed to establish the radiomics model for predicting CDK6 expression. Receiver operating characteristic curve (ROC), calibration curve, and decision curve analysis (DCA) were utilized to assess the predictive performance of the radiomics model. Generate radiomic scores (RS) based on the LR model. An RS-based nomogram was constructed to predict the prognosis of HGG. RESULTS CDK6 was significantly overexpressed in HGG tissues and was related to lower overall survival. A significant elevation in infiltrating M0 macrophages was observed in the CDK6 high group (P < 0.001). The LR radiomics model for the prediction of CDK6 expression levels (AUC=0.810 in the training cohort, AUC = 0.784 after cross-validation, AUC=0.750 in the testing cohort) was established utilizing three radiomic features. The predictive efficiencies of the RS-based nomogram, as measured by AUC, were 0.769 for 1-year, 0.815 for 3-year, and 0.780 for 5-year, respectively. CONCLUSION The expression level of CDK6 can impact the prognosis of patients with HGG. The expression level of HGG can be noninvasively prognosticated utilizing a radiomics model.
Collapse
Affiliation(s)
- Chen Sun
- Department of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, No. 119 West Road, South Fourth Ring Road, Beijing, China
| | - Chenggang Jiang
- Department of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, No. 119 West Road, South Fourth Ring Road, Beijing, China
| | - Xi Wang
- Department of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, No. 119 West Road, South Fourth Ring Road, Beijing, China
| | - Shunchang Ma
- Department of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, No. 119 West Road, South Fourth Ring Road, Beijing, China
| | - Dainan Zhang
- Department of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, No. 119 West Road, South Fourth Ring Road, Beijing, China
| | - Wang Jia
- Department of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, No. 119 West Road, South Fourth Ring Road, Beijing, China.
| |
Collapse
|
11
|
Rudà R, Horbinski C, van den Bent M, Preusser M, Soffietti R. IDH inhibition in gliomas: from preclinical models to clinical trials. Nat Rev Neurol 2024; 20:395-407. [PMID: 38760442 DOI: 10.1038/s41582-024-00967-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 04/26/2024] [Indexed: 05/19/2024]
Abstract
Gliomas are the most common malignant primary brain tumours in adults and cannot usually be cured with standard cancer treatments. Gliomas show intratumoural and intertumoural heterogeneity at the histological and molecular levels, and they frequently contain mutations in the isocitrate dehydrogenase 1 (IDH1) or IDH2 gene. IDH-mutant adult-type diffuse gliomas are subdivided into grade 2, 3 or 4 IDH-mutant astrocytomas and grade 2 or 3 IDH-mutant, 1p19q-codeleted oligodendrogliomas. The product of the mutated IDH genes, D-2-hydroxyglutarate (D-2-HG), induces global DNA hypermethylation and interferes with immunity, leading to stimulation of tumour growth. Selective inhibitors of mutant IDH, such as ivosidenib and vorasidenib, have been shown to reduce D-2-HG levels and induce cellular differentiation in preclinical models and to induce MRI-detectable responses in early clinical trials. The phase III INDIGO trial has demonstrated superiority of vorasidenib, a brain-penetrant pan-mutant IDH inhibitor, over placebo in people with non-enhancing grade 2 IDH-mutant gliomas following surgery. In this Review, we describe the pathway of development of IDH inhibitors in IDH-mutant low-grade gliomas from preclinical models to clinical trials. We discuss the practice-changing implications of the INDIGO trial and consider new avenues of investigation in the field of IDH-mutant gliomas.
Collapse
Affiliation(s)
- Roberta Rudà
- Division of Neuro-Oncology, Department of Neuroscience 'Rita Levi Montalcini', University of Turin, Turin, Italy.
| | - Craig Horbinski
- Department of Pathology, Feinberg School of Medicine, Northwestern University, Chicago, IL, USA
- Department of Neurological Surgery, Feinberg School of Medicine, Northwestern University, Chicago, IL, USA
| | - Martin van den Bent
- Brain Tumour Center at Erasmus MC Cancer Institute, Rotterdam, The Netherlands
| | - Matthias Preusser
- Division of Oncology, Department of Medicine I, Medical University of Vienna, Vienna, Austria
| | - Riccardo Soffietti
- Division of Neuro-Oncology, Department of Neuroscience 'Rita Levi Montalcini', University of Turin, Turin, Italy
| |
Collapse
|
12
|
Zeng Y, Liu N, Yang X, Huang C, Liu M. Enhanced Multimodal Brain Tumor Classification in MR Images using 2D ResNet as backbone with Explicit Tumor Size Information. J Cancer 2024; 15:4275-4286. [PMID: 38947386 PMCID: PMC11212098 DOI: 10.7150/jca.95987] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/06/2024] [Accepted: 05/02/2024] [Indexed: 07/02/2024] Open
Abstract
It's a major public health problem of global concern that malignant gliomas tend to grow rapidly and infiltrate surrounding tissues. Accurate grading of the tumor can determine the degree of malignancy to formulate the best treatment plan, which can eliminate the tumor or limit widespread metastasis of the tumor, saving the patient's life and improving their prognosis. To more accurately predict the grading of gliomas, we proposed a novel method of combining the advantages of 2D and 3D Convolutional Neural Networks for tumor grading by multimodality on Magnetic Resonance Imaging. The core of the innovation lies in our combination of tumor 3D information extracted from multimodal data with those obtained from a 2D ResNet50 architecture. It solves both the lack of temporal-spatial information provided by 3D imaging in 2D convolutional neural networks and avoids more noise from too much information in 3D convolutional neural networks, which causes serious overfitting problems. Incorporating explicit tumor 3D information, such as tumor volume and surface area, enhances the grading model's performance and addresses the limitations of both approaches. By fusing information from multiple modalities, the model achieves a more precise and accurate characterization of tumors. The model I s trained and evaluated using two publicly available brain glioma datasets, achieving an AUC of 0.9684 on the validation set. The model's interpretability is enhanced through heatmaps, which highlight the tumor region. The proposed method holds promise for clinical application in tumor grading and contributes to the field of medical diagnostics for prediction.
Collapse
Affiliation(s)
- Yunhao Zeng
- School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China
- Yangtze Delta Region Institute (Quzhou), University of Electronic Science and Technology of China, Quzhou 324000, China
| | - Nianbo Liu
- Yangtze Delta Region Institute (Quzhou), University of Electronic Science and Technology of China, Quzhou 324000, China
- Quzhou People's Hospital, Quzhou Affiliated Hospital of Wenzhou Medical University, Quzhou 324000, China
| | - Xinduoji Yang
- School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China
- Yangtze Delta Region Institute (Quzhou), University of Electronic Science and Technology of China, Quzhou 324000, China
| | - Chenke Huang
- School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China
| | - Ming Liu
- Yangtze Delta Region Institute (Quzhou), University of Electronic Science and Technology of China, Quzhou 324000, China
- Quzhou People's Hospital, Quzhou Affiliated Hospital of Wenzhou Medical University, Quzhou 324000, China
| |
Collapse
|
13
|
Moon HH, Jeong J, Park JE, Kim N, Choi C, Kim Y, Song SW, Hong CK, Kim JH, Kim HS. Generative AI in glioma: Ensuring diversity in training image phenotypes to improve diagnostic performance for IDH mutation prediction. Neuro Oncol 2024; 26:1124-1135. [PMID: 38253989 PMCID: PMC11145451 DOI: 10.1093/neuonc/noae012] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/09/2023] [Indexed: 01/24/2024] Open
Abstract
BACKGROUND This study evaluated whether generative artificial intelligence (AI)-based augmentation (GAA) can provide diverse and realistic imaging phenotypes and improve deep learning-based classification of isocitrate dehydrogenase (IDH) type in glioma compared with neuroradiologists. METHODS For model development, 565 patients (346 IDH-wildtype, 219 IDH-mutant) with paired contrast-enhanced T1 and FLAIR MRI scans were collected from tertiary hospitals and The Cancer Imaging Archive. Performance was tested on internal (119, 78 IDH-wildtype, 41 IDH-mutant [IDH1 and 2]) and external test sets (108, 72 IDH-wildtype, 36 IDH-mutant). GAA was developed using a score-based diffusion model and ResNet50 classifier. The optimal GAA was selected in comparison with the null model. Two neuroradiologists (R1, R2) assessed realism, diversity of imaging phenotypes, and predicted IDH mutation. The performance of a classifier trained with optimal GAA was compared with that of neuroradiologists using the area under the receiver operating characteristics curve (AUC). The effect of tumor size and contrast enhancement on GAA performance was tested. RESULTS Generated images demonstrated realism (Turing's test: 47.5-50.5%) and diversity indicating IDH type. Optimal GAA was achieved with augmentation with 110 000 generated slices (AUC: 0.938). The classifier trained with optimal GAA demonstrated significantly higher AUC values than neuroradiologists in both the internal (R1, P = .003; R2, P < .001) and external test sets (R1, P < .01; R2, P < .001). GAA with large-sized tumors or predominant enhancement showed comparable performance to optimal GAA (internal test: AUC 0.956 and 0.922; external test: 0.810 and 0.749). CONCLUSIONS The application of generative AI with realistic and diverse images provided better diagnostic performance than neuroradiologists for predicting IDH type in glioma.
Collapse
Affiliation(s)
- Hye Hyeon Moon
- Department of Radiology and Research Institute of Radiology, University of Ulsan College of Medicine, Asan Medical Center, Seoul, Korea
| | - Jiheon Jeong
- Department of Convergence Medicine, University of Ulsan College of Medicine, Asan Medical Center, Seoul, Korea
- Department of Biomedical Engineering, Asan Medical Institute of Convergence Science of Technology, Asan Medical Center, College of Medicine, University of Ulsan, Seoul, Korea
| | - Ji Eun Park
- Department of Radiology and Research Institute of Radiology, University of Ulsan College of Medicine, Asan Medical Center, Seoul, Korea
| | - Namkug Kim
- Department of Radiology and Research Institute of Radiology, University of Ulsan College of Medicine, Asan Medical Center, Seoul, Korea
- Department of Convergence Medicine, University of Ulsan College of Medicine, Asan Medical Center, Seoul, Korea
| | - Changyong Choi
- Department of Convergence Medicine, University of Ulsan College of Medicine, Asan Medical Center, Seoul, Korea
- Department of Biomedical Engineering, Asan Medical Institute of Convergence Science of Technology, Asan Medical Center, College of Medicine, University of Ulsan, Seoul, Korea
| | - Young‑Hoon Kim
- Department of Neurosurgery, University of Ulsan College of Medicine, Asan Medical Center, Seoul, Korea
| | - Sang Woo Song
- Department of Neurosurgery, University of Ulsan College of Medicine, Asan Medical Center, Seoul, Korea
| | - Chang-Ki Hong
- Department of Neurosurgery, University of Ulsan College of Medicine, Asan Medical Center, Seoul, Korea
| | - Jeong Hoon Kim
- Department of Neurosurgery, University of Ulsan College of Medicine, Asan Medical Center, Seoul, Korea
| | - Ho Sung Kim
- Department of Radiology and Research Institute of Radiology, University of Ulsan College of Medicine, Asan Medical Center, Seoul, Korea
| |
Collapse
|
14
|
Wang S, Liu X, Jiang C, Kang W, Pan Y, Tang X, Luo Y, Gong J. CT-Based Super-Resolution Deep Learning Models with Attention Mechanisms for Predicting Spread Through Air Spaces of Solid or Part-Solid Lung Adenocarcinoma. Acad Radiol 2024; 31:2601-2609. [PMID: 38184418 DOI: 10.1016/j.acra.2023.12.034] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/07/2023] [Revised: 12/20/2023] [Accepted: 12/20/2023] [Indexed: 01/08/2024]
Abstract
RATIONALE AND OBJECTIVES Spread through air space (STAS) is a novel invasive pattern of lung adenocarcinoma (LUAD), and preoperative knowledge of STAS status is helpful in choosing an appropriate surgical approach. MATERIALS AND METHODS This retrospective study collected and analyzed 602 patients diagnosed with LUAD from two medical centers: center 1 was randomly partitioned into training (n = 358) and validation cohorts (n = 154) at a 7:3 ratio; and center 2 was the external test cohort (n = 90). Super resolution was performed on all images to acquire high-resolution images, which were used to train the SE-ResNet50 model, before creating an equivalent parameter ResNet50 model. Disparities were compared between the two models using receiver operating characteristic curves, area under the curve, accuracy, precision, sensitivity, and specificity. RESULTS In this study, 512 and 90 patients with LUAD were enrolled from centers 1 and 2, respectively. The curve values of the SE-ResNet50 and ResNet50 models were compared for training, validation, and test cohorts, resulting in values of 0.933 vs 0.909, 0.783 vs 0.728, and 0.806 vs 0.695, respectively. In the external test cohort, the accuracy of the SE-ResNet50 model demonstrated a 10% improvement over the ResNet50 model (82.2% vs 72.2%). CONCLUSION The SE-ResNet50 model based on computed tomography super-resolution has great potential for predicting STAS status in patients with solid or partially solid LUAD, with superior predictive performance compared to traditional deep learning models.
Collapse
Affiliation(s)
- Shuxing Wang
- The Second Clinical Medical College, Jinan University, Shenzhen, Guangdong, China (S.W., X.L., Y.P., J.G.)
| | - Xiaowen Liu
- The Second Clinical Medical College, Jinan University, Shenzhen, Guangdong, China (S.W., X.L., Y.P., J.G.)
| | - Changsi Jiang
- Department of Radiology, Shenzhen People's Hospital (The Second Clinical Medical College of Jinan University, The First Affiliated Hospital of Southern University of Science and Technology), Floor 1 Bldg 4, Dongbeilu 1017, Shenzhen 518020, Guangdong, China (C.J., X.T., Y.L., J.G.)
| | - Wenyan Kang
- Department of Radiology, Cancer Hospital Chinese Academy of Medical Sciences, Shenzhen Center, Shenzhen, China (W.K.)
| | - Yudie Pan
- The Second Clinical Medical College, Jinan University, Shenzhen, Guangdong, China (S.W., X.L., Y.P., J.G.)
| | - Xue Tang
- Department of Radiology, Shenzhen People's Hospital (The Second Clinical Medical College of Jinan University, The First Affiliated Hospital of Southern University of Science and Technology), Floor 1 Bldg 4, Dongbeilu 1017, Shenzhen 518020, Guangdong, China (C.J., X.T., Y.L., J.G.)
| | - Yan Luo
- Department of Radiology, Shenzhen People's Hospital (The Second Clinical Medical College of Jinan University, The First Affiliated Hospital of Southern University of Science and Technology), Floor 1 Bldg 4, Dongbeilu 1017, Shenzhen 518020, Guangdong, China (C.J., X.T., Y.L., J.G.)
| | - Jingshan Gong
- The Second Clinical Medical College, Jinan University, Shenzhen, Guangdong, China (S.W., X.L., Y.P., J.G.); Department of Radiology, Shenzhen People's Hospital (The Second Clinical Medical College of Jinan University, The First Affiliated Hospital of Southern University of Science and Technology), Floor 1 Bldg 4, Dongbeilu 1017, Shenzhen 518020, Guangdong, China (C.J., X.T., Y.L., J.G.).
| |
Collapse
|
15
|
Kersch CN, Kim M, Stoller J, Barajas RF, Park JE. Imaging Genomics of Glioma Revisited: Analytic Methods to Understand Spatial and Temporal Heterogeneity. AJNR Am J Neuroradiol 2024; 45:537-548. [PMID: 38548303 PMCID: PMC11288537 DOI: 10.3174/ajnr.a8148] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/28/2023] [Accepted: 11/09/2023] [Indexed: 04/12/2024]
Abstract
An improved understanding of the cellular and molecular biologic processes responsible for brain tumor development, growth, and resistance to therapy is fundamental to improving clinical outcomes. Imaging genomics is the study of the relationships between microscopic, genetic, and molecular biologic features and macroscopic imaging features. Imaging genomics is beginning to shift clinical paradigms for diagnosing and treating brain tumors. This article provides an overview of imaging genomics in gliomas, in which imaging data including hallmarks such as IDH-mutation, MGMT methylation, and EGFR-mutation status can provide critical insights into the pretreatment and posttreatment stages. This article will accomplish the following: 1) review the methods used in imaging genomics, including visual analysis, quantitative analysis, and radiomics analysis; 2) recommend suitable analytic methods for imaging genomics according to biologic characteristics; 3) discuss the clinical applicability of imaging genomics; and 4) introduce subregional tumor habitat analysis with the goal of guiding future radiogenetics research endeavors toward translation into critically needed clinical applications.
Collapse
Affiliation(s)
- Cymon N Kersch
- From the Department of Radiation Medicine (C.N.K.), Oregon Health and Science University, Portland, Oregon
| | - Minjae Kim
- Department of Radiology and Research Institute of Radiology (M.K., J.E.P.), Asan Medical Center, University of Ulsan College of Medicine, Seoul, Korea
| | - Jared Stoller
- Department of Diagnostic Radiology (J.S., R.F.B.), Oregon Health and Science University, Portland, Oregon
| | - Ramon F Barajas
- Department of Diagnostic Radiology (J.S., R.F.B.), Oregon Health and Science University, Portland, Oregon
- Knight Cancer Institute (R.F.B.), Oregon Health and Science University, Portland, Oregon
- Advanced Imaging Research Center (R.F.B.), Oregon Health and Science University, Portland, Oregon
| | - Ji Eun Park
- Department of Radiology and Research Institute of Radiology (M.K., J.E.P.), Asan Medical Center, University of Ulsan College of Medicine, Seoul, Korea
| |
Collapse
|
16
|
Yuan J, Siakallis L, Li HB, Brandner S, Zhang J, Li C, Mancini L, Bisdas S. Structural- and DTI- MRI enable automated prediction of IDH Mutation Status in CNS WHO Grade 2-4 glioma patients: a deep Radiomics Approach. BMC Med Imaging 2024; 24:104. [PMID: 38702613 PMCID: PMC11067215 DOI: 10.1186/s12880-024-01274-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/01/2023] [Accepted: 04/15/2024] [Indexed: 05/06/2024] Open
Abstract
BACKGROUND The role of isocitrate dehydrogenase (IDH) mutation status for glioma stratification and prognosis is established. While structural magnetic resonance image (MRI) is a promising biomarker, it may not be sufficient for non-invasive characterisation of IDH mutation status. We investigated the diagnostic value of combined diffusion tensor imaging (DTI) and structural MRI enhanced by a deep radiomics approach based on convolutional neural networks (CNNs) and support vector machine (SVM), to determine the IDH mutation status in Central Nervous System World Health Organization (CNS WHO) grade 2-4 gliomas. METHODS This retrospective study analyzed the DTI-derived fractional anisotropy (FA) and mean diffusivity (MD) images and structural images including fluid attenuated inversion recovery (FLAIR), non-enhanced T1-, and T2-weighted images of 206 treatment-naïve gliomas, including 146 IDH mutant and 60 IDH-wildtype ones. The lesions were manually segmented by experienced neuroradiologists and the masks were applied to the FA and MD maps. Deep radiomics features were extracted from each subject by applying a pre-trained CNN and statistical description. An SVM classifier was applied to predict IDH status using imaging features in combination with demographic data. RESULTS We comparatively assessed the CNN-SVM classifier performance in predicting IDH mutation status using standalone and combined structural and DTI-based imaging features. Combined imaging features surpassed stand-alone modalities for the prediction of IDH mutation status [area under the curve (AUC) = 0.846; sensitivity = 0.925; and specificity = 0.567]. Importantly, optimal model performance was noted following the addition of demographic data (patients' age) to structural and DTI imaging features [area under the curve (AUC) = 0.847; sensitivity = 0.911; and specificity = 0.617]. CONCLUSIONS Imaging features derived from DTI-based FA and MD maps combined with structural MRI, have superior diagnostic value to that provided by standalone structural or DTI sequences. In combination with demographic information, this CNN-SVM model offers a further enhanced non-invasive prediction of IDH mutation status in gliomas.
Collapse
Affiliation(s)
- Jialin Yuan
- Department of Radiology, Shenzhen People's Hospital, Second Clinical Medical College of Jinan University, First Affiliated Hospital of Southern University of Science and Technology, Shenzhen, China
- Queen Square Institute of Neurology, University College London, London, UK
| | - Loizos Siakallis
- Queen Square Institute of Neurology, University College London, London, UK
| | - Hongwei Bran Li
- Department of Informatics, Technical University of Munich, Munich, Germany
- Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Harvard Medical School, Charlestown, USA
| | - Sebastian Brandner
- Division of Neuropathology, Queen Square Institute of Neurology, University College London, London, UK
| | - Jianguo Zhang
- Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China
| | - Chenming Li
- Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China
| | - Laura Mancini
- Queen Square Institute of Neurology, University College London, London, UK
- Lysholm Department of Neuroradiology, University College London Hospitals NHS Foundation Trust, London, UK
| | - Sotirios Bisdas
- Queen Square Institute of Neurology, University College London, London, UK.
- Lysholm Department of Neuroradiology, University College London Hospitals NHS Foundation Trust, London, UK.
| |
Collapse
|
17
|
Gao J, Liu Z, Pan H, Cao X, Kan Y, Wen Z, Chen S, Wen M, Zhang L. Preoperative Discrimination of CDKN2A/B Homozygous Deletion Status in Isocitrate Dehydrogenase-Mutant Astrocytoma: A Deep Learning-Based Radiomics Model Using MRI. J Magn Reson Imaging 2024; 59:1655-1664. [PMID: 37555723 DOI: 10.1002/jmri.28945] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/28/2023] [Revised: 07/26/2023] [Accepted: 07/26/2023] [Indexed: 08/10/2023] Open
Abstract
BACKGROUND Cyclin-dependent kinase inhibitor 2A/B (CDKN2A/B) homozygous deletion has been verified as an independent and critical biomarker of negative prognosis and short survival in isocitrate dehydrogenase (IDH)-mutant astrocytoma. Therefore, noninvasive and accurate discrimination of CDKN2A/B homozygous deletion status is essential for the clinical management of IDH-mutant astrocytoma patients. PURPOSE To develop a noninvasive, robust preoperative model based on MR image features for discriminating CDKN2A/B homozygous deletion status of IDH-mutant astrocytoma. STUDY TYPE Retrospective. POPULATION Two hundred fifty-one patients: 107 patients with CDKN2A/B homozygous deletion and 144 patients without CDKN2A/B homozygous deletion. FIELD STRENGTH/SEQUENCE 3.0 T/1.5 T: Contrast-enhanced T1-weighted spin-echo inversion recovery sequence (CE-T1WI) and T2-weighted fluid-attenuation spin-echo inversion recovery sequence (T2FLAIR). ASSESSMENT A total of 1106 radiomics and 1000 deep learning features extracted from CE-T1WI and T2FLAIR were used to develop models to discriminate the CDKN2A/B homozygous deletion status. Radiomics models, deep learning-based radiomics (DLR) models and the final integrated model combining radiomics features with deep learning features were developed and compared their preoperative discrimination performance. STATISTICAL TESTING Pearson chi-square test and Mann Whitney U test were used for assessing the statistical differences in patients' clinical characteristics. The Delong test compared the statistical differences of receiver operating characteristic (ROC) curves and area under the curve (AUC) of different models. The significance threshold is P < 0.05. RESULTS The final combined model (training AUC = 0.966; validation AUC = 0.935; test group: AUC = 0.943) outperformed the optimal models based on only radiomics or DLR features (training: AUC = 0.916 and 0.952; validation: AUC = 0.886 and 0.912; test group: AUC = 0.862 and 0.902). DATA CONCLUSION Whether based on a single sequence or a combination of two sequences, radiomics and DLR models have achieved promising performance in assessing CDKN2A/B homozygous deletion status. However, the final model combining both deep learning and radiomics features from CE-T1WI and T2FLAIR outperformed the optimal radiomics or DLR model. EVIDENCE LEVEL 4 TECHNICAL EFFICACY: Stage 2.
Collapse
Affiliation(s)
- Jueni Gao
- Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China
| | - Zhi Liu
- Department of Nuclear Medicine, Chongqing Hospital of Traditional Chinese Medicine, Chongqing, China
| | - Hongyu Pan
- College of Computer and Information Science, Southwest University, Chongqing, China
| | - Xu Cao
- School of Medical and Life Sciences, Chengdu University of Traditional Chinese Medicine, Chengdu, China
| | - Yubo Kan
- School of Medical and Life Sciences, Chengdu University of Traditional Chinese Medicine, Chengdu, China
| | - Zhipeng Wen
- Department of Radiology, Sichuan Cancer Hospital, Chengdu, China
| | - Shanxiong Chen
- College of Computer and Information Science, Southwest University, Chongqing, China
| | - Ming Wen
- Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China
| | - Liqiang Zhang
- Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China
| |
Collapse
|
18
|
Wu G, Shi Z, Li Z, Xie X, Tang Q, Zhu J, Yang Z, Wang Y, Wu J, Yu J. Study of radiochemotherapy decision-making for young high-risk low-grade glioma patients using a macroscopic and microscopic combined radiomics model. Eur Radiol 2024; 34:2861-2872. [PMID: 37889272 DOI: 10.1007/s00330-023-10378-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/28/2023] [Revised: 09/06/2023] [Accepted: 09/16/2023] [Indexed: 10/28/2023]
Abstract
OBJECTIVES As a few types of glioma, young high-risk low-grade gliomas (HRLGGs) have higher requirements for postoperative quality of life. Although adjuvant chemotherapy with delayed radiotherapy is the first treatment strategy for HRLGGs, not all HRLGGs benefit from it. Accurate assessment of chemosensitivity in HRLGGs is vital for making treatment choices. This study developed a multimodal fusion radiomics (MFR) model to support radiochemotherapy decision-making for HRLGGs. METHODS A MFR model combining macroscopic MRI and microscopic pathological images was proposed. Multiscale features including macroscopic tumor structure and microscopic histological layer and nuclear information were grabbed by unique paradigm, respectively. Then, these features were adaptively incorporated into the MFR model through attention mechanism to predict the chemosensitivity of temozolomide (TMZ) by means of objective response rate and progression free survival (PFS). RESULTS Macroscopic tumor texture complexity and microscopic nuclear size showed significant statistical differences (p < 0.001) between sensitivity and insensitivity groups. The MFR model achieved stable prediction results, with an area under the curve of 0.950 (95% CI: 0.942-0.958), sensitivity of 0.833 (95% CI: 0.780-0.848), specificity of 0.929 (95% CI: 0.914-0.936), positive predictive value of 0.833 (95% CI: 0.811-0.860), and negative predictive value of 0.929 (95% CI: 0.914-0.934). The predictive efficacy of MFR was significantly higher than that of the reported molecular markers (p < 0.001). MFR was also demonstrated to be a predictor of PFS. CONCLUSIONS A MFR model including radiomics and pathological features predicts accurately the response postoperative TMZ treatment. CLINICAL RELEVANCE STATEMENT Our MFR model could identify young high-risk low-grade glioma patients who can have the most benefit from postoperative upfront temozolomide (TMZ) treatment. KEY POINTS • Multimodal radiomics is proposed to support the radiochemotherapy of glioma. • Some macro and micro image markers related to tumor chemotherapy sensitivity are revealed. • The proposed model surpasses reported molecular markers, with a promising area under the curve (AUC) of 0.95.
Collapse
Affiliation(s)
- Guoqing Wu
- School of Information Science and Technology, Fudan University, Shanghai, China
- Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention of Shanghai, Shanghai, China
| | - Zhifeng Shi
- Department of Neurosurgery, Huashan Hospital, Shanghai Medical College, Fudan University, Shanghai, China
- National Center for Neurological Disorders, Shanghai, China
- Shanghai Key Laboratory of Brain Function Restoration and Neural Regeneration, Shanghai, China
- Neurosurgical Institute of Fudan University, Shanghai, China
| | - Zeyang Li
- Department of Neurosurgery, Huashan Hospital, Shanghai Medical College, Fudan University, Shanghai, China
- National Center for Neurological Disorders, Shanghai, China
- Shanghai Key Laboratory of Brain Function Restoration and Neural Regeneration, Shanghai, China
- Neurosurgical Institute of Fudan University, Shanghai, China
| | - Xuan Xie
- School of Information Science and Technology, Fudan University, Shanghai, China
- Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention of Shanghai, Shanghai, China
| | - Qisheng Tang
- Department of Neurosurgery, Huashan Hospital, Shanghai Medical College, Fudan University, Shanghai, China
- National Center for Neurological Disorders, Shanghai, China
- Shanghai Key Laboratory of Brain Function Restoration and Neural Regeneration, Shanghai, China
- Neurosurgical Institute of Fudan University, Shanghai, China
| | - Jingjing Zhu
- Department of Pathology, Huashan Hospital, Shanghai Medical College, Fudan University, Shanghai, China
| | - Zhong Yang
- Department of Radiology, Huashan Hospital, Shanghai Medical College, Fudan University, Shanghai, China
| | - Yuanyuan Wang
- School of Information Science and Technology, Fudan University, Shanghai, China
- Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention of Shanghai, Shanghai, China
| | - Jinsong Wu
- Department of Neurosurgery, Huashan Hospital, Shanghai Medical College, Fudan University, Shanghai, China.
- National Center for Neurological Disorders, Shanghai, China.
- Shanghai Key Laboratory of Brain Function Restoration and Neural Regeneration, Shanghai, China.
- Neurosurgical Institute of Fudan University, Shanghai, China.
| | - Jinhua Yu
- School of Information Science and Technology, Fudan University, Shanghai, China.
- Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention of Shanghai, Shanghai, China.
- The AI Lab of Huashan Hospital, Fudan University, Shanghai, China.
| |
Collapse
|
19
|
Zhao Z, Nie C, Zhao L, Xiao D, Zheng J, Zhang H, Yan P, Jiang X, Zhao H. Multi-parametric MRI-based machine learning model for prediction of WHO grading in patients with meningiomas. Eur Radiol 2024; 34:2468-2479. [PMID: 37812296 PMCID: PMC10957672 DOI: 10.1007/s00330-023-10252-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/27/2022] [Revised: 07/05/2023] [Accepted: 07/15/2023] [Indexed: 10/10/2023]
Abstract
OBJECTIVE The purpose of this study was to develop and validate a nomogram combined multiparametric MRI and clinical indicators for identifying the WHO grade of meningioma. MATERIALS AND METHODS Five hundred and sixty-eight patients were included in this study, who were diagnosed pathologically as having meningiomas. Firstly, radiomics features were extracted from CE-T1, T2, and 1-cm-thick tumor-to-brain interface (BTI) images. Then, difference analysis and the least absolute shrinkage and selection operator were orderly used to select the most representative features. Next, the support vector machine algorithm was conducted to predict the WHO grade of meningioma. Furthermore, a nomogram incorporated radiomics features and valuable clinical indicators was constructed by logistic regression. The performance of the nomogram was assessed by calibration and clinical effectiveness, as well as internal validation. RESULTS Peritumoral edema volume and gender are independent risk factors for predicting meningioma grade. The multiparametric MRI features incorporating CE-T1, T2, and BTI features showed the higher performance for prediction of meningioma grade with a pooled AUC = 0.885 (95% CI, 0.821-0.946) and 0.860 (95% CI, 0.788-0.923) in the training and test groups, respectively. Then, a nomogram with a pooled AUC = 0.912 (95% CI, 0.876-0.961), combined radiomics score, peritumoral edema volume, and gender improved diagnostic performance compared to radiomics model or clinical model and showed good calibration as the true results. Moreover, decision curve analysis demonstrated satisfactory clinical effectiveness of the proposed nomogram. CONCLUSIONS A novel nomogram is simple yet effective in differentiating WHO grades of meningioma and thus can be used in patients with meningiomas. CLINICAL RELEVANCE STATEMENT We proposed a nomogram that included clinical indicators and multi-parameter radiomics features, which can accurately, objectively, and non-invasively differentiate WHO grading of meningioma and thus can be used in clinical work. KEY POINTS • The study combined radiomics features and clinical indicators for objectively predicting the meningioma grade. • The model with CE-T1 + T2 + brain-to-tumor interface features demonstrated the best predictive performance by investigating seven different radiomics models. • The nomogram potentially has clinical applications in distinguishing high-grade and low-grade meningiomas.
Collapse
Affiliation(s)
- Zhen Zhao
- Department of Neurosurgery, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Chuansheng Nie
- Department of Neurosurgery, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Lei Zhao
- International Education College of Henan University, Kaifeng, China
| | - Dongdong Xiao
- Department of Neurosurgery, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Jianglin Zheng
- Department of Neurosurgery, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Hao Zhang
- Department of Geriatric Medicine, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Pengfei Yan
- Department of Neurosurgery, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Xiaobing Jiang
- Department of Neurosurgery, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China.
| | - Hongyang Zhao
- Department of Neurosurgery, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China.
| |
Collapse
|
20
|
Kasap DNG, Mora NGN, Blömer DA, Akkurt BH, Heindel WL, Mannil M, Musigmann M. Comparison of MRI Sequences to Predict IDH Mutation Status in Gliomas Using Radiomics-Based Machine Learning. Biomedicines 2024; 12:725. [PMID: 38672080 PMCID: PMC11048271 DOI: 10.3390/biomedicines12040725] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/22/2024] [Revised: 02/24/2024] [Accepted: 03/21/2024] [Indexed: 04/28/2024] Open
Abstract
OBJECTIVES Regarding the 2021 World Health Organization (WHO) classification of central nervous system (CNS) tumors, the isocitrate dehydrogenase (IDH) mutation status is one of the most important factors for CNS tumor classification. The aim of our study is to analyze which of the commonly used magnetic resonance imaging (MRI) sequences is best suited to obtain this information non-invasively using radiomics-based machine learning models. We developed machine learning models based on different MRI sequences and determined which of the MRI sequences analyzed yields the highest discriminatory power in predicting the IDH mutation status. MATERIAL AND METHODS In our retrospective IRB-approved study, we used the MRI images of 106 patients with histologically confirmed gliomas. The MRI images were acquired using the T1 sequence with and without administration of a contrast agent, the T2 sequence, and the Fluid-Attenuated Inversion Recovery (FLAIR) sequence. To objectively compare performance in predicting the IDH mutation status as a function of the MRI sequence used, we included only patients in our study cohort for whom MRI images of all four sequences were available. Seventy-one of the patients had an IDH mutation, and the remaining 35 patients did not have an IDH mutation (IDH wild-type). For each of the four MRI sequences used, 107 radiomic features were extracted from the corresponding MRI images by hand-delineated regions of interest. Data partitioning into training data and independent test data was repeated 100 times to avoid random effects associated with the data partitioning. Feature preselection and subsequent model development were performed using Random Forest, Lasso regression, LDA, and Naïve Bayes. The performance of all models was determined with independent test data. RESULTS Among the different approaches we examined, the T1-weighted contrast-enhanced sequence was found to be the most suitable for predicting IDH mutations status using radiomics-based machine learning models. Using contrast-enhanced T1-weighted MRI images, our seven-feature model developed with Lasso regression achieved a mean area under the curve (AUC) of 0.846, a mean accuracy of 0.792, a mean sensitivity of 0.847, and a mean specificity of 0.681. The administration of contrast agents resulted in a significant increase in the achieved discriminatory power. CONCLUSIONS Our analyses show that for the prediction of the IDH mutation status using radiomics-based machine learning models, among the MRI images acquired with the commonly used MRI sequences, the contrast-enhanced T1-weighted images are the most suitable.
Collapse
|
21
|
Zhang X, Zhang G, Qiu X, Yin J, Tan W, Yin X, Yang H, Wang H, Zhang Y. Non-invasive decision support for clinical treatment of non-small cell lung cancer using a multiscale radiomics approach. Radiother Oncol 2024; 191:110082. [PMID: 38195018 DOI: 10.1016/j.radonc.2024.110082] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/22/2023] [Revised: 12/01/2023] [Accepted: 01/02/2024] [Indexed: 01/11/2024]
Abstract
BACKGROUND Selecting therapeutic strategies for cancer patients is typically based on key target-molecule biomarkers that play an important role in cancer onset, progression, and prognosis. Thus, there is a pressing need for novel biomarkers that can be utilized longitudinally to guide treatment selection. METHODS Using data from 508 non-small cell lung cancer (NSCLC) patients across three institutions, we developed and validated a comprehensive predictive biomarker that distinguishes six genotypes and infiltrative immune phenotypes. These features were analyzed to establish the association between radiological phenotypes and tumor genotypes/immune phenotypes and to create a radiological interpretation of molecular features. In addition, we assessed the sensitivity of the models by evaluating their performance at five different voxel intervals, resulting in improved generalizability of the proposed approach. FINDINGS The radiomics model we developed, which integrates clinical factors and multi-regional features, outperformed the conventional model that only uses clinical and intratumoral features. Our combined model showed significant performance for EGFR, KRAS, ALK, TP53, PIK3CA, and ROS1 mutation status with AUCs of 0.866, 0.874, 0.902, 0.850, 0.860, and 0.900, respectively. Additionally, the predictive performance for PD-1/PD-L1 was 0.852. Although the performance of all models decreased to different degrees at five different voxel space resolutions, the performance advantage of the combined model did not change. CONCLUSIONS We validated multiscale radiomic signatures across tumor genotypes and immunophenotypes in a multi-institutional cohort. This imaging-based biomarker offers a non-invasive approach to select patients with NSCLC who are sensitive to targeted therapies or immunotherapy, which is promising for developing personalized treatment strategies during therapy.
Collapse
Affiliation(s)
- Xingping Zhang
- School of Medical Information Engineering, Gannan Medical University, 341000, Ganzhou, China; Cyberspace Institute of Advanced Technology, Guangzhou University, 510006 Guangzhou, China; Institute for Sustainable Industries and Liveable Cities, Victoria University, 3011, Melbourne, Australia; Department of New Networks, Peng Cheng Laboratory, 518000, Shenzhen, China
| | - Guijuan Zhang
- Department of Respiratory and Critical Care, First Affiliated Hospital of Gannan Medical University, 341000, Ganzhou, China
| | - Xingting Qiu
- Department of Radiology, First Affiliated Hospital of Gannan Medical University, 341000, Ganzhou, China
| | - Jiao Yin
- Institute for Sustainable Industries and Liveable Cities, Victoria University, 3011, Melbourne, Australia
| | - Wenjun Tan
- Key Laboratory of Intelligent Computing in Medical Image, Ministry of Education, Northeastern University, 110189, Shenyang, China
| | - Xiaoxia Yin
- Cyberspace Institute of Advanced Technology, Guangzhou University, 510006 Guangzhou, China
| | - Hong Yang
- Cyberspace Institute of Advanced Technology, Guangzhou University, 510006 Guangzhou, China
| | - Hua Wang
- Institute for Sustainable Industries and Liveable Cities, Victoria University, 3011, Melbourne, Australia.
| | - Yanchun Zhang
- Institute for Sustainable Industries and Liveable Cities, Victoria University, 3011, Melbourne, Australia; School of Computer Science and Technology, Zhejiang Normal University, 321000, Jinhua, China; Department of New Networks, Peng Cheng Laboratory, 518000, Shenzhen, China.
| |
Collapse
|
22
|
Guo Y, Xie X, Tang W, Chen S, Wang M, Fan Y, Lin C, Hu W, Yang J, Xiang J, Jiang K, Wei X, Huang B, Jiang X. Noninvasive identification of HER2-low-positive status by MRI-based deep learning radiomics predicts the disease-free survival of patients with breast cancer. Eur Radiol 2024; 34:899-913. [PMID: 37597033 DOI: 10.1007/s00330-023-09990-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/21/2022] [Revised: 04/09/2023] [Accepted: 06/02/2023] [Indexed: 08/21/2023]
Abstract
OBJECTIVE This study aimed to establish a MRI-based deep learning radiomics (DLR) signature to predict the human epidermal growth factor receptor 2 (HER2)-low-positive status and further verified the difference in prognosis by the DLR model. METHODS A total of 481 patients with breast cancer who underwent preoperative MRI were retrospectively recruited from two institutions. Traditional radiomics features and deep semantic segmentation feature-based radiomics (DSFR) features were extracted from segmented tumors to construct models separately. Then, the DLR model was constructed to assess the HER2 status by averaging the output probabilities of the two models. Finally, a Kaplan‒Meier survival analysis was conducted to explore the disease-free survival (DFS) in patients with HER2-low-positive status. The multivariate Cox proportional hazard model was constructed to further determine the factors associated with DFS. RESULTS First, the DLR model distinguished between HER2-negative and HER2-overexpressing patients with AUCs of 0.868 and 0.763 in the training and validation cohorts, respectively. Furthermore, the DLR model distinguished between HER2-low-positive and HER2-zero patients with AUCs of 0.855 and 0.750, respectively. Cox regression analysis showed that the prediction score obtained using the DLR model (HR, 0.175; p = 0.024) and lesion size (HR, 1.043; p = 0.009) were significant, independent predictors of DFS. CONCLUSIONS We successfully constructed a DLR model based on MRI to noninvasively evaluate the HER2 status and further revealed prospects for predicting the DFS of patients with HER2-low-positive status. CLINICAL RELEVANCE STATEMENT The MRI-based DLR model could noninvasively identify HER2-low-positive status, which is considered a novel prognostic predictor and therapeutic target. KEY POINTS • The DLR model effectively distinguished the HER2 status of breast cancer patients, especially the HER2-low-positive status. • The DLR model was better than the traditional radiomics model or DSFR model in distinguishing HER2 expression. • The prediction score obtained using the model and lesion size were significant independent predictors of DFS.
Collapse
Affiliation(s)
- Yuan Guo
- Department of Radiology, Guangzhou First People's Hospital, South China University of Technology, Guangzhou, Guangdong, 510180, China
| | - Xiaotong Xie
- School of Life Science, South China Normal University, Guangzhou, 510631, China
- Medical AI Lab, School of Biomedical Engineering, Medical School, Shenzhen University, Shenzhen, Guangdong, 518055, China
| | - Wenjie Tang
- Department of Radiology, Guangzhou First People's Hospital, South China University of Technology, Guangzhou, Guangdong, 510180, China
| | - Siyi Chen
- Department of Radiology, Guangzhou First People's Hospital, South China University of Technology, Guangzhou, Guangdong, 510180, China
| | - Mingyu Wang
- Medical AI Lab, School of Biomedical Engineering, Medical School, Shenzhen University, Shenzhen, Guangdong, 518055, China
| | - Yaheng Fan
- Medical AI Lab, School of Biomedical Engineering, Medical School, Shenzhen University, Shenzhen, Guangdong, 518055, China
| | - Chuxuan Lin
- Medical AI Lab, School of Biomedical Engineering, Medical School, Shenzhen University, Shenzhen, Guangdong, 518055, China
| | - Wenke Hu
- Department of Radiology, Guangzhou First People's Hospital, South China University of Technology, Guangzhou, Guangdong, 510180, China
| | - Jing Yang
- Department of Pathology, Guangzhou First People's Hospital, South China University of Technology, Guangzhou, 510180, China
| | - Jialin Xiang
- Department of Radiology, Guangdong Women and Children Hospital, Guangzhou, Guangdong, 510010, China
| | - Kuiming Jiang
- Department of Radiology, Guangdong Women and Children Hospital, Guangzhou, Guangdong, 510010, China.
| | - Xinhua Wei
- Department of Radiology, Guangzhou First People's Hospital, South China University of Technology, Guangzhou, Guangdong, 510180, China.
| | - Bingsheng Huang
- Medical AI Lab, School of Biomedical Engineering, Medical School, Shenzhen University, Shenzhen, Guangdong, 518055, China.
| | - Xinqing Jiang
- Department of Radiology, Guangzhou First People's Hospital, South China University of Technology, Guangzhou, Guangdong, 510180, China.
| |
Collapse
|
23
|
Santinha J, Katsaros V, Stranjalis G, Liouta E, Boskos C, Matos C, Viegas C, Papanikolaou N. Development of End-to-End AI-Based MRI Image Analysis System for Predicting IDH Mutation Status of Patients with Gliomas: Multicentric Validation. JOURNAL OF IMAGING INFORMATICS IN MEDICINE 2024; 37:31-44. [PMID: 38343254 DOI: 10.1007/s10278-023-00918-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/05/2023] [Revised: 08/08/2023] [Accepted: 08/23/2023] [Indexed: 03/02/2024]
Abstract
Radiogenomics has shown potential to predict genomic phenotypes from medical images. The development of models using standard-of-care pre-operative MRI images, as opposed to advanced MRI images, enables a broader reach of such models. In this work, a radiogenomics model for IDH mutation status prediction from standard-of-care MRIs in patients with glioma was developed and validated using multicentric data. A cohort of 142 (wild-type: 32.4%) patients with glioma retrieved from the TCIA/TCGA was used to train a logistic regression model to predict the IDH mutation status. The model was evaluated using retrospective data collected in two distinct hospitals, comprising 36 (wild-type: 63.9%) and 53 (wild-type: 75.5%) patients. Model development utilized ROC analysis. Model discrimination and calibration were used for validation. The model yielded an AUC of 0.741 vs. 0.716 vs. 0.938, a sensitivity of 0.784 vs. 0.739 vs. 0.875, and a specificity of 0.657 vs. 0.692 vs. 1.000 on the training, test cohort 1, and test cohort 2, respectively. The assessment of model fairness suggested an unbiased model for age and sex, and calibration tests showed a p < 0.05. These results indicate that the developed model allows the prediction of the IDH mutation status in gliomas using standard-of-care MRI images and does not appear to hold sex and age biases.
Collapse
Affiliation(s)
- João Santinha
- Computational Clinical Imaging Group, Champalimaud Research , Champalimaud Foundation, Av. Brasília, 1400-038, Lisbon, Portugal.
- Instituto Superior Técnico, Universidade de Lisboa, Av. Rovisco Pais 1, 1049-001, Lisbon, Portugal.
| | - Vasileios Katsaros
- Department of Radiology, General Anti-Cancer and Oncological Hospital of Athens, St. Savvas, Athens, Greece
| | - George Stranjalis
- Department of Neurosurgery, National and Kapodistrian University of Athens, Evangelismos Hospital, Athens, Greece
- Hellenic Center for Neurosurgical Research "Prof. Petros Kokkalis", Athens, Greece
- Athens Microneurosurgery Laboratory, Athens, Greece
| | - Evangelia Liouta
- Department of Neurosurgery, National and Kapodistrian University of Athens, Evangelismos Hospital, Athens, Greece
- Hellenic Center for Neurosurgical Research "Prof. Petros Kokkalis", Athens, Greece
| | - Christos Boskos
- Athens Microneurosurgery Laboratory, Athens, Greece
- IATROPOLIS CyberKnife Center, Hellenic Neuro-Oncology Society, Chalandri, Greece
| | - Celso Matos
- Radiology Department, Champalimaud Clinical Centre, Champalimaud Foundation, Av. Brasília, 1400-038, Lisbon, Portugal
| | - Catarina Viegas
- Department of Neurosurgery, Hospital Garcia de Orta, Almada, Portugal
| | - Nickolas Papanikolaou
- Computational Clinical Imaging Group, Champalimaud Research , Champalimaud Foundation, Av. Brasília, 1400-038, Lisbon, Portugal
| |
Collapse
|
24
|
Sabeghi P, Zarand P, Zargham S, Golestany B, Shariat A, Chang M, Yang E, Rajagopalan P, Phung DC, Gholamrezanezhad A. Advances in Neuro-Oncological Imaging: An Update on Diagnostic Approach to Brain Tumors. Cancers (Basel) 2024; 16:576. [PMID: 38339327 PMCID: PMC10854543 DOI: 10.3390/cancers16030576] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/27/2023] [Revised: 01/22/2024] [Accepted: 01/24/2024] [Indexed: 02/12/2024] Open
Abstract
This study delineates the pivotal role of imaging within the field of neurology, emphasizing its significance in the diagnosis, prognostication, and evaluation of treatment responses for central nervous system (CNS) tumors. A comprehensive understanding of both the capabilities and limitations inherent in emerging imaging technologies is imperative for delivering a heightened level of personalized care to individuals with neuro-oncological conditions. Ongoing research in neuro-oncological imaging endeavors to rectify some limitations of radiological modalities, aiming to augment accuracy and efficacy in the management of brain tumors. This review is dedicated to the comparison and critical examination of the latest advancements in diverse imaging modalities employed in neuro-oncology. The objective is to investigate their respective impacts on diagnosis, cancer staging, prognosis, and post-treatment monitoring. By providing a comprehensive analysis of these modalities, this review aims to contribute to the collective knowledge in the field, fostering an informed approach to neuro-oncological care. In conclusion, the outlook for neuro-oncological imaging appears promising, and sustained exploration in this domain is anticipated to yield further breakthroughs, ultimately enhancing outcomes for individuals grappling with CNS tumors.
Collapse
Affiliation(s)
- Paniz Sabeghi
- Department of Radiology, Keck School of Medicine, University of Southern California, 1500 San Pablo St., Los Angeles, CA 90033, USA; (P.S.); (E.Y.); (P.R.); (D.C.P.)
| | - Paniz Zarand
- School of Medicine, Shahid Beheshti University of Medical Sciences, Tehran 1985717411, Iran;
| | - Sina Zargham
- Department of Basic Science, California Northstate University College of Medicine, 9700 West Taron Drive, Elk Grove, CA 95757, USA;
| | - Batis Golestany
- Division of Biomedical Sciences, Riverside School of Medicine, University of California, 900 University Ave., Riverside, CA 92521, USA;
| | - Arya Shariat
- Kaiser Permanente Los Angeles Medical Center, 4867 W Sunset Blvd, Los Angeles, CA 90027, USA;
| | - Myles Chang
- Keck School of Medicine, University of Southern California, 1975 Zonal Avenue, Los Angeles, CA 90089, USA;
| | - Evan Yang
- Department of Radiology, Keck School of Medicine, University of Southern California, 1500 San Pablo St., Los Angeles, CA 90033, USA; (P.S.); (E.Y.); (P.R.); (D.C.P.)
| | - Priya Rajagopalan
- Department of Radiology, Keck School of Medicine, University of Southern California, 1500 San Pablo St., Los Angeles, CA 90033, USA; (P.S.); (E.Y.); (P.R.); (D.C.P.)
| | - Daniel Chang Phung
- Department of Radiology, Keck School of Medicine, University of Southern California, 1500 San Pablo St., Los Angeles, CA 90033, USA; (P.S.); (E.Y.); (P.R.); (D.C.P.)
| | - Ali Gholamrezanezhad
- Department of Radiology, Keck School of Medicine, University of Southern California, 1500 San Pablo St., Los Angeles, CA 90033, USA; (P.S.); (E.Y.); (P.R.); (D.C.P.)
| |
Collapse
|
25
|
Xue Y, Yang S, Sun W, Tan H, Lin K, Peng L, Wang Z, Zhang J. Approaching expert-level accuracy for differentiating ACL tear types on MRI with deep learning. Sci Rep 2024; 14:938. [PMID: 38195977 PMCID: PMC10776725 DOI: 10.1038/s41598-024-51666-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/12/2023] [Accepted: 01/08/2024] [Indexed: 01/11/2024] Open
Abstract
Treatment for anterior cruciate ligament (ACL) tears depends on the condition of the ligament. We aimed to identify different tear statuses from preoperative MRI using deep learning-based radiomics with sex and age. We reviewed 862 patients with preoperative MRI scans reflecting ACL status from Hunan Provincial People's Hospital. Based on sagittal proton density-weighted images, a fully automated approach was developed that consisted of a deep learning model for segmenting ACL tissue (ACL-DNet) and a deep learning-based recognizer for ligament status classification (ACL-SNet). The efficacy of the proposed approach was evaluated by using the sensitivity, specificity and area under the receiver operating characteristic curve (AUC) and compared with that of a group of three orthopedists in the holdout test set. The ACL-DNet model yielded a Dice coefficient of 98% ± 6% on the MRI datasets. Our proposed classification model yielded a sensitivity of 97% and a specificity of 97%. In comparison, the sensitivity of alternative models ranged from 84 to 90%, while the specificity was between 86 and 92%. The AUC of the ACL-SNet model was 99%, demonstrating high overall diagnostic accuracy. The diagnostic performance of the clinical experts as reflected in the AUC was 96%, 92% and 88%, respectively. The fully automated model shows potential as a highly reliable and reproducible tool that allows orthopedists to noninvasively identify the ACL status and may aid in optimizing different techniques, such as ACL remnant preservation, for ACL reconstruction.
Collapse
Affiliation(s)
- Yang Xue
- School of Computer Science, Hunan First Normal University, Changsha, 410205, China
- Hunan Provincial Key Laboratory of Information Technology for Basic Education, Changsha, 410205, China
| | - Shu Yang
- Department of Orthopaedic, Hunan Provincial People's Hospital (The First Affiliated Hospital of Hunan Normal University), Changsha, 410002, China
| | - Wenjie Sun
- Department of Radiology, Hunan Provincial People's Hospital (The First Affiliated Hospital of Hunan Normal University), Changsha, 410002, China
| | - Hui Tan
- Department of Radiology, Hunan Provincial People's Hospital (The First Affiliated Hospital of Hunan Normal University), Changsha, 410002, China
| | - Kaibin Lin
- School of Computer Science, Hunan First Normal University, Changsha, 410205, China
- Hunan Provincial Key Laboratory of Information Technology for Basic Education, Changsha, 410205, China
| | - Li Peng
- School of Computer Science, Hunan First Normal University, Changsha, 410205, China
- Hunan Provincial Key Laboratory of Information Technology for Basic Education, Changsha, 410205, China
| | - Zheng Wang
- School of Computer Science, Hunan First Normal University, Changsha, 410205, China.
- Hunan Provincial Key Laboratory of Information Technology for Basic Education, Changsha, 410205, China.
| | - Jianglin Zhang
- Department of Dermatology, Shenzhen People's Hospital (The Second Clinical Medical College, Jinan University; The First Affiliated Hospital, Southern University of Science and Technology), Shenzhen, 518020, Guangdong, China.
- Candidate Branch of National Clinical Research Center for Skin Diseases, Shenzhen, 518020, Guangdong, China.
- Department of Geriatrics, Shenzhen People's Hospital, (The Second Clinical Medical College, Jinan University; The First Affiliated Hospital, Southern University of Science and Technology), Shenzhen, 518020, Guangdong, China.
| |
Collapse
|
26
|
Cheng D, Zhuo Z, Du J, Weng J, Zhang C, Duan Y, Sun T, Wu M, Guo M, Hua T, Jin Y, Peng B, Li Z, Zhu M, Imami M, Bettegowda C, Sair H, Bai HX, Barkhof F, Liu X, Liu Y. A Fully Automated Deep-Learning Model for Predicting the Molecular Subtypes of Posterior Fossa Ependymomas Using T2-Weighted Images. Clin Cancer Res 2024; 30:150-158. [PMID: 37916978 DOI: 10.1158/1078-0432.ccr-23-1461] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/18/2023] [Revised: 09/11/2023] [Accepted: 10/31/2023] [Indexed: 11/03/2023]
Abstract
PURPOSE We aimed to develop and validate a deep learning (DL) model to automatically segment posterior fossa ependymoma (PF-EPN) and predict its molecular subtypes [Group A (PFA) and Group B (PFB)] from preoperative MR images. EXPERIMENTAL DESIGN We retrospectively identified 227 PF-EPNs (development and internal test sets) with available preoperative T2-weighted (T2w) MR images and molecular status to develop and test a 3D nnU-Net (referred to as T2-nnU-Net) for tumor segmentation and molecular subtype prediction. The network was externally tested using an external independent set [n = 40; subset-1 (n = 31) and subset-2 (n =9)] and prospectively enrolled cases [prospective validation set (n = 27)]. The Dice similarity coefficient was used to evaluate the segmentation performance. Receiver operating characteristic analysis for molecular subtype prediction was performed. RESULTS For tumor segmentation, the T2-nnU-Net achieved a Dice score of 0.94 ± 0.02 in the internal test set. For molecular subtype prediction, the T2-nnU-Net achieved an AUC of 0.93 and accuracy of 0.89 in the internal test set, an AUC of 0.99 and accuracy of 0.93 in the external test set. In the prospective validation set, the model achieved an AUC of 0.93 and an accuracy of 0.89. The predictive performance of T2-nnU-Net was superior or comparable to that of demographic and multiple radiologic features (AUCs ranging from 0.87 to 0.95). CONCLUSIONS A fully automated DL model was developed and validated to accurately segment PF-EPNs and predict molecular subtypes using only T2w MR images, which could help in clinical decision-making.
Collapse
Affiliation(s)
- Dan Cheng
- Department of Radiology, Beijing Tiantan Hospital, Capital Medical University, Beijing, P.R. China
| | - Zhizheng Zhuo
- Department of Radiology, Beijing Tiantan Hospital, Capital Medical University, Beijing, P.R. China
| | - Jiang Du
- Department of Neuropathology, Beijing Neurosurgical Institute, Capital Medical University, Beijing, China
| | - Jinyuan Weng
- Department of Medical Imaging Product, Neusoft, Group Ltd., Shenyang, P.R. China
| | - Chengzhou Zhang
- Department of Radiology, Yantai Yuhuangding Hospital, Yantai, Shandong, P.R. China
| | - Yunyun Duan
- Department of Radiology, Beijing Tiantan Hospital, Capital Medical University, Beijing, P.R. China
| | - Ting Sun
- Department of Radiology, Beijing Tiantan Hospital, Capital Medical University, Beijing, P.R. China
| | - Minghao Wu
- Department of Radiology, Beijing Tiantan Hospital, Capital Medical University, Beijing, P.R. China
| | - Min Guo
- Department of Radiology, Beijing Tiantan Hospital, Capital Medical University, Beijing, P.R. China
| | - Tiantian Hua
- Department of Radiology, Beijing Tiantan Hospital, Capital Medical University, Beijing, P.R. China
| | - Ying Jin
- Department of Radiology, Beijing Tiantan Hospital, Capital Medical University, Beijing, P.R. China
| | - Boyang Peng
- Department of Radiology, Beijing Tiantan Hospital, Capital Medical University, Beijing, P.R. China
| | | | - Mingwang Zhu
- Department of Radiology, Sanbo Brain Hospital, Capital Medical University, Beijing, P.R. China
| | - Maliha Imami
- Department of Radiology and Radiological Science, Johns Hopkins University School of Medicine, Baltimore, Maryland
| | - Chetan Bettegowda
- Department of Neurosurgery, Johns Hopkins University School of Medicine, Baltimore, Maryland
| | - Haris Sair
- Department of Radiology and Radiological Science, Johns Hopkins University School of Medicine, Baltimore, Maryland
| | - Harrison X Bai
- Department of Radiology and Radiological Science, Johns Hopkins University School of Medicine, Baltimore, Maryland
| | - Frederik Barkhof
- Queen Square Institute of Neurology and Centre for Medical Image Computing, University College London, London, United Kingdom
- Department of Radiology & Nuclear Medicine, Amsterdam UMC, Vrije Universiteit, the Netherlands
| | - Xing Liu
- Department of Neuropathology, Beijing Neurosurgical Institute, Capital Medical University, Beijing, China
| | - Yaou Liu
- Department of Radiology, Beijing Tiantan Hospital, Capital Medical University, Beijing, P.R. China
| |
Collapse
|
27
|
Liu Z, Xu X, Zhang W, Zhang L, Wen M, Gao J, Yang J, Kan Y, Yang X, Wen Z, Chen S, Cao X. A fusion model integrating magnetic resonance imaging radiomics and deep learning features for predicting alpha-thalassemia X-linked intellectual disability mutation status in isocitrate dehydrogenase-mutant high-grade astrocytoma: a multicenter study. Quant Imaging Med Surg 2024; 14:251-263. [PMID: 38223098 PMCID: PMC10784047 DOI: 10.21037/qims-23-807] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/05/2023] [Accepted: 10/24/2023] [Indexed: 01/16/2024]
Abstract
Background The mutational status of alpha-thalassemia X-linked intellectual disability (ATRX) is an important indicator for the treatment and prognosis of high-grade gliomas, but reliable ATRX testing currently requires invasive procedures. The objective of this study was to develop a clinical trait-imaging fusion model that combines preoperative magnetic resonance imaging (MRI) radiomics and deep learning (DL) features with clinical variables to predict ATRX status in isocitrate dehydrogenase (IDH)-mutant high-grade astrocytoma. Methods A total of 234 patients with IDH-mutant high-grade astrocytoma (120 ATRX mutant type, 114 ATRX wild type) from 3 centers were retrospectively analyzed. Radiomics and DL features from different regions (edema, tumor, and the overall lesion) were extracted to construct multiple imaging models by combining different features in different regions for predicting ATRX status. An optimal imaging model was then selected, and its features and linear coefficients were used to calculate an imaging score. Finally, a fusion model was developed by combining the imaging score and clinical variables. The performance and application value of the fusion model were evaluated through the comparison of receiver operating characteristic curves, the construction of a nomogram, calibration curves, decision curves, and clinical application curves. Results The overall hybrid model constructed with radiomics and DL features from the overall lesion was identified as the optimal imaging model. The fusion model showed the best prediction performance with an area under curve of 0.969 in the training set, 0.956 in the validation set, and 0.949 in the test set as compared to the optimal imaging model (0.966, 0.916, and 0.936, respectively) and clinical model (0.677, 0.641, 0.772, respectively). Conclusions The clinical trait-imaging fusion model based on preoperative MRI could effectively predict the ATRX mutation status of individuals with IDH-mutant high-grade astrocytoma and has the potential to help patients through the development of a more effective treatment strategy before treatment.
Collapse
Affiliation(s)
- Zhi Liu
- Department of Radiology, Chongqing Hospital of Traditional Chinese Medicine, Chongqing, China
| | - Xinyi Xu
- Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China
| | - Wang Zhang
- College of Computer & Information Science, Southwest University, Chongqing, China
| | - Liqiang Zhang
- Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China
| | - Ming Wen
- Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China
| | - Jueni Gao
- Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China
| | - Jun Yang
- Department of Endocrinology, University-Town Hospital of Chongqing Medical University, Chongqing, China
| | - Yubo Kan
- School of Medical and Life Sciences Chengdu University of Traditional Chinese Medicine, Chengdu, China
| | - Xing Yang
- Department of Radiology, Chongqing United Medical Imaging Center, Chongqing, China
| | - Zhipeng Wen
- Department of Radiology, Sichuan Cancer Hospital & Institute, Sichuan Cancer Center, School of Medicine, University of Electronic Science and Technology of China, Chengdu, China
| | - Shanxiong Chen
- College of Computer & Information Science, Southwest University, Chongqing, China
| | - Xu Cao
- School of Medical and Life Sciences Chengdu University of Traditional Chinese Medicine, Chengdu, China
| |
Collapse
|
28
|
Kertels O, Delbridge C, Sahm F, Ehret F, Acker G, Capper D, Peeken JC, Diehl C, Griessmair M, Metz MC, Negwer C, Krieg SM, Onken J, Yakushev I, Vajkoczy P, Meyer B, Zips D, Combs SE, Zimmer C, Kaul D, Bernhardt D, Wiestler B. Imaging meningioma biology: Machine learning predicts integrated risk score in WHO grade 2/3 meningioma. Neurooncol Adv 2024; 6:vdae080. [PMID: 38957161 PMCID: PMC11217900 DOI: 10.1093/noajnl/vdae080] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 07/04/2024] Open
Abstract
Background Meningiomas are the most common primary brain tumors. While most are benign (WHO grade 1) and have a favorable prognosis, up to one-fourth are classified as higher-grade, falling into WHO grade 2 or 3 categories. Recently, an integrated risk score (IRS) pertaining to tumor biology was developed and its prognostic relevance was validated in a large, multicenter study. We hypothesized imaging data to be reflective of the IRS. Thus, we assessed the potential of a machine learning classifier for its noninvasive prediction using preoperative magnetic resonance imaging (MRI). Methods In total, 160 WHO grade 2 and 3 meningioma patients from 2 university centers were included in this study. All patients underwent surgery with histopathological workup including methylation analysis. Preoperative MRI scans were automatically segmented, and radiomic parameters were extracted. Using a random forest classifier, 3 machine learning classifiers (1 multiclass classifier for IRS and 2 binary classifiers for low-risk and high-risk prediction, respectively) were developed in a training set (120 patients) and independently tested in a hold-out test set (40 patients). Results Multiclass IRS classification had a test set area under the curve (AUC) of 0.7, mostly driven by the difficulties in clearly separating medium-risk from high-risk patients. Consequently, a classifier predicting low-risk IRS versus medium-/high-risk showed a very high test accuracy of 90% (AUC 0.88). In particular, "sphericity" was associated with low-risk IRS classification. Conclusion The IRS, in particular molecular low-risk, can be predicted from imaging data with high accuracy, making this important prognostic classification accessible by imaging.
Collapse
Affiliation(s)
- Olivia Kertels
- Department of Diagnostic and Interventional Neuroradiology, School of Medicine, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany
| | - Claire Delbridge
- Department of Neuropathology, School of Medicine, Institute of Pathology, Technical University of Munich, Munich, Germany
| | - Felix Sahm
- Department of Neuropathology, Institute of Pathology, University Hospital Heidelberg, Heidelberg, Germany
- Clinical Cooperation Unit Neuropathology, German Cancer Consortium (DKTK), German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Felix Ehret
- German Cancer Consortium (DKTK), Partner Site Berlin, German Cancer Research Center (DKFZ), Heidelberg, Germany
- Department of Radiation Oncology, Charité – Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany
| | - Güliz Acker
- Department of Radiation Oncology, Charité – Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany
- Department of Neurosurgery, Charité – Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany
| | - David Capper
- German Cancer Consortium (DKTK), Partner Site Berlin, German Cancer Research Center (DKFZ), Heidelberg, Germany
- Department of Neuropathology, Charité – Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany
| | - Jan C Peeken
- Department of Radiation Oncology, Klinikum rechts der Isar, Technische Universität München, Institut für Innovative Radiotherapy (iRT), Munich, Germany
| | - Christian Diehl
- Department of Radiation Oncology, Klinikum rechts der Isar, Technische Universität München, Institut für Innovative Radiotherapy (iRT), Munich, Germany
| | - Michael Griessmair
- Department of Diagnostic and Interventional Neuroradiology, School of Medicine, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany
| | - Marie-Christin Metz
- Department of Diagnostic and Interventional Neuroradiology, School of Medicine, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany
| | - Chiara Negwer
- Department of Neurosurgery, Technical University of Munich, School of Medicine, Klinikum rechts der Isar, Munich, Germany
| | - Sandro M Krieg
- Department of Neurosurgery, University Hospital Heidelberg, Heidelberg, Germany
| | - Julia Onken
- Department of Neurosurgery, Charité – Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany
| | - Igor Yakushev
- Department of Nuclear Medicine, Klinikum Rechts der Isar, Technical University of Munich, München, Germany
| | - Peter Vajkoczy
- Department of Neurosurgery, Charité – Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany
| | - Bernhard Meyer
- Department of Neurosurgery, Technical University of Munich, School of Medicine, Klinikum rechts der Isar, Munich, Germany
| | - Daniel Zips
- Department of Radiation Oncology, Charité – Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany
| | - Stephanie E Combs
- Department of Radiation Oncology, Klinikum rechts der Isar, Technische Universität München, Institut für Innovative Radiotherapy (iRT), Munich, Germany
| | - Claus Zimmer
- Department of Diagnostic and Interventional Neuroradiology, School of Medicine, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany
| | - David Kaul
- Faculty of Medicine, HMU Health and Medical University, Potsdam, Germany
- Department of Radiation Oncology, Charité – Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany
| | - Denise Bernhardt
- Department of Radiation Oncology, Klinikum rechts der Isar, Technische Universität München, Institut für Innovative Radiotherapy (iRT), Munich, Germany
| | - Benedikt Wiestler
- Department of Diagnostic and Interventional Neuroradiology, School of Medicine, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany
- TranslaTUM, Center for Translational Cancer Research, Technical University of Munich, Munich, Germany
| |
Collapse
|
29
|
Lu T, Ma J, Zou J, Jiang C, Li Y, Han J. CT-based intratumoral and peritumoral deep transfer learning features prediction of lymph node metastasis in non-small cell lung cancer. JOURNAL OF X-RAY SCIENCE AND TECHNOLOGY 2024; 32:597-609. [PMID: 38578874 DOI: 10.3233/xst-230326] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 04/07/2024]
Abstract
BACKGROUND The main metastatic route for lung cancer is lymph node metastasis, and studies have shown that non-small cell lung cancer (NSCLC) has a high risk of lymph node infiltration. OBJECTIVE This study aimed to compare the performance of handcrafted radiomics (HR) features and deep transfer learning (DTL) features in Computed Tomography (CT) of intratumoral and peritumoral regions in predicting the metastatic status of NSCLC lymph nodes in different machine learning classifier models. METHODS We retrospectively collected data of 199 patients with pathologically confirmed NSCLC. All patients were divided into training (n = 159) and validation (n = 40) cohorts, respectively. The best HR and DTL features in the intratumoral and peritumoral regions were extracted and selected, respectively. Support Vector Machine (SVM), k-Nearest Neighbors (KNN), Light Gradient Boosting Machine (Light GBM), Multilayer Perceptron (MLP), and Logistic Regression (LR) models were constructed, and the performance of the models was evaluated. RESULTS Among the five models in the training and validation cohorts, the LR classifier model performed best in terms of HR and DTL features. The AUCs of the training cohort were 0.841 (95% CI: 0.776-0.907) and 0.955 (95% CI: 0.926-0.983), and the AUCs of the validation cohort were 0.812 (95% CI: 0.677-0.948) and 0.893 (95% CI: 0.795-0.991), respectively. The DTL signature was superior to the handcrafted radiomics signature. CONCLUSIONS Compared with the radiomics signature, the DTL signature constructed based on intratumoral and peritumoral areas in CT can better predict NSCLC lymph node metastasis.
Collapse
Affiliation(s)
- Tianyu Lu
- Department of Radiology, The First Hospital of Jiaxing or The Affiliated Hospital of Jiaxing University, Jiaxing, China
| | - Jianbing Ma
- Department of Radiology, The First Hospital of Jiaxing or The Affiliated Hospital of Jiaxing University, Jiaxing, China
| | - Jiajun Zou
- Department of Radiology, The First Hospital of Jiaxing or The Affiliated Hospital of Jiaxing University, Jiaxing, China
| | - Chenxu Jiang
- Department of Radiology, The First Hospital of Jiaxing or The Affiliated Hospital of Jiaxing University, Jiaxing, China
| | - Yangyang Li
- Department of Radiology, The First Hospital of Jiaxing or The Affiliated Hospital of Jiaxing University, Jiaxing, China
| | - Jun Han
- Department of Radiology, The First Hospital of Jiaxing or The Affiliated Hospital of Jiaxing University, Jiaxing, China
| |
Collapse
|
30
|
Foltyn-Dumitru M, Schell M, Sahm F, Kessler T, Wick W, Bendszus M, Rastogi A, Brugnara G, Vollmuth P. Advancing noninvasive glioma classification with diffusion radiomics: Exploring the impact of signal intensity normalization. Neurooncol Adv 2024; 6:vdae043. [PMID: 38596719 PMCID: PMC11003539 DOI: 10.1093/noajnl/vdae043] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 04/11/2024] Open
Abstract
Background This study investigates the influence of diffusion-weighted Magnetic Resonance Imaging (DWI-MRI) on radiomic-based prediction of glioma types according to molecular status and assesses the impact of DWI intensity normalization on model generalizability. Methods Radiomic features, compliant with image biomarker standardization initiative standards, were extracted from preoperative MRI of 549 patients with diffuse glioma, known IDH, and 1p19q-status. Anatomical sequences (T1, T1c, T2, FLAIR) underwent N4-Bias Field Correction (N4) and WhiteStripe normalization (N4/WS). Apparent diffusion coefficient (ADC) maps were normalized using N4 or N4/z-score. Nine machine-learning algorithms were trained for multiclass prediction of glioma types (IDH-mutant 1p/19q codeleted, IDH-mutant 1p/19q non-codeleted, IDH-wild type). Four approaches were compared: Anatomical, anatomical + ADC naive, anatomical + ADC N4, and anatomical + ADC N4/z-score. The University of California San Francisco (UCSF)-glioma dataset (n = 409) was used for external validation. Results Naïve-Bayes algorithms yielded overall the best performance on the internal test set. Adding ADC radiomics significantly improved AUC from 0.79 to 0.86 (P = .011) for the IDH-wild-type subgroup, but not for the other 2 glioma subgroups (P > .05). In the external UCSF dataset, the addition of ADC radiomics yielded a significantly higher AUC for the IDH-wild-type subgroup (P ≤ .001): 0.80 (N4/WS anatomical alone), 0.81 (anatomical + ADC naive), 0.81 (anatomical + ADC N4), and 0.88 (anatomical + ADC N4/z-score) as well as for the IDH-mutant 1p/19q non-codeleted subgroup (P < .012 each). Conclusions ADC radiomics can enhance the performance of conventional MRI-based radiomic models, particularly for IDH-wild-type glioma. The benefit of intensity normalization of ADC maps depends on the type and context of the used data.
Collapse
Affiliation(s)
- Martha Foltyn-Dumitru
- Department of Neuroradiology, Heidelberg University Hospital, Heidelberg, Germany
- Division for Computational Neuroimaging, Department of Neuroradiology, Heidelberg University Hospital, Heidelberg, Germany
| | - Marianne Schell
- Department of Neuroradiology, Heidelberg University Hospital, Heidelberg, Germany
- Division for Computational Neuroimaging, Department of Neuroradiology, Heidelberg University Hospital, Heidelberg, Germany
| | - Felix Sahm
- Department of Neuropathology, Heidelberg University Hospital, Heidelberg, Germany
- Clinical Cooperation Unit Neuropathology, German Cancer Consortium (DKTK), German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Tobias Kessler
- Department of Neurology and Neurooncology Program, Heidelberg University Hospital, Heidelberg University, Heidelberg, Germany
- Clinical Cooperation Unit Neurooncology, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Wolfgang Wick
- Department of Neurology and Neurooncology Program, Heidelberg University Hospital, Heidelberg University, Heidelberg, Germany
- Clinical Cooperation Unit Neurooncology, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Martin Bendszus
- Department of Neuroradiology, Heidelberg University Hospital, Heidelberg, Germany
| | - Aditya Rastogi
- Department of Neuroradiology, Heidelberg University Hospital, Heidelberg, Germany
- Division for Computational Neuroimaging, Department of Neuroradiology, Heidelberg University Hospital, Heidelberg, Germany
| | - Gianluca Brugnara
- Department of Neuroradiology, Heidelberg University Hospital, Heidelberg, Germany
- Division for Computational Neuroimaging, Department of Neuroradiology, Heidelberg University Hospital, Heidelberg, Germany
| | - Philipp Vollmuth
- Department of Neuroradiology, Heidelberg University Hospital, Heidelberg, Germany
- Division for Computational Neuroimaging, Department of Neuroradiology, Heidelberg University Hospital, Heidelberg, Germany
- Division for Computational Radiology & Clinical AI, Department of Neuroradiology, Bonn University Hospital, Bonn, Germany
| |
Collapse
|
31
|
Tang R, Li J, Zhao P, Zhang Z, Yin H, Ding H, Xu N, Yang Z, Wang Z. Utility of machine learning for identifying stapes fixation on ultra-high-resolution CT. Jpn J Radiol 2024; 42:69-77. [PMID: 37561264 DOI: 10.1007/s11604-023-01475-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/06/2023] [Accepted: 07/18/2023] [Indexed: 08/11/2023]
Abstract
PURPOSE Imaging diagnosis of stapes fixation (SF) is challenging owing to a lack of definite evidence. We developed a comprehensive machine learning (ML) model to identify SF on ultra-high-resolution CT. MATERIALS AND METHODS We retrospectively enrolled 109 participants (143 ears) and divided them into the training set (115 ears) and test set (28 ears). Stapes mobility (SF or non-SF) was determined by surgical inspection. In the ML analysis, rectangular regions of interest were placed on consecutive axial slices in the training set. Radiomic features were extracted and fed into the training session. The test set was analyzed using 7 ML models (support vector machine, k nearest neighbor, decision tree, random forest, extra trees, eXtreme Gradient Boosting, and Light Gradient Boosting Machine) and by 2 dedicated neuroradiologists. Diagnostic performance (sensitivity, specificity and accuracy, with surgical findings as the reference) was compared between the radiologists and the optimal ML model by using the McNemar test. RESULTS The mean age of the participants was 42.3 ± 17.5 years. The Light Gradient Boosting Machine (LightGBM) model showed the highest sensitivity (0.83), specificity (0.81), accuracy (0.82) and area under the curve (0.88) for detecting SF among the 7 ML models. The neuroradiologists achieved good sensitivities (0.75 and 0.67), moderate-to-good specificities (0.63 and 0.56) and good accuracies (0.68 and 0.61). This model showed no statistical differences with the neuroradiologists (P values 0.289-1.000). CONCLUSIONS Compared to the neuroradiologists, the LightGBM model achieved competitive diagnostic performance in identifying SF, and has the potential to be a supportive tool in clinical practice.
Collapse
Affiliation(s)
- Ruowei Tang
- Department of Radiology, Beijing Friendship Hospital, Capital Medical University, 95 Yong'an Road, Xicheng District, Beijing, 100050, People's Republic of China
| | - Jia Li
- Department of Radiology, Beijing Friendship Hospital, Capital Medical University, 95 Yong'an Road, Xicheng District, Beijing, 100050, People's Republic of China
| | - Pengfei Zhao
- Department of Radiology, Beijing Friendship Hospital, Capital Medical University, 95 Yong'an Road, Xicheng District, Beijing, 100050, People's Republic of China.
| | - Zhengyu Zhang
- Department of Radiology, Beijing Friendship Hospital, Capital Medical University, 95 Yong'an Road, Xicheng District, Beijing, 100050, People's Republic of China
| | - Hongxia Yin
- Department of Radiology, Beijing Friendship Hospital, Capital Medical University, 95 Yong'an Road, Xicheng District, Beijing, 100050, People's Republic of China
| | - Heyu Ding
- Department of Radiology, Beijing Friendship Hospital, Capital Medical University, 95 Yong'an Road, Xicheng District, Beijing, 100050, People's Republic of China
| | - Ning Xu
- Department of Radiology, Beijing Friendship Hospital, Capital Medical University, 95 Yong'an Road, Xicheng District, Beijing, 100050, People's Republic of China
| | - Zhenghan Yang
- Department of Radiology, Beijing Friendship Hospital, Capital Medical University, 95 Yong'an Road, Xicheng District, Beijing, 100050, People's Republic of China
| | - Zhenchang Wang
- Department of Radiology, Beijing Friendship Hospital, Capital Medical University, 95 Yong'an Road, Xicheng District, Beijing, 100050, People's Republic of China.
| |
Collapse
|
32
|
Zhang L, Wang R, Gao J, Tang Y, Xu X, Kan Y, Cao X, Wen Z, Liu Z, Cui S, Li Y. A novel MRI-based deep learning networks combined with attention mechanism for predicting CDKN2A/B homozygous deletion status in IDH-mutant astrocytoma. Eur Radiol 2024; 34:391-399. [PMID: 37553486 DOI: 10.1007/s00330-023-09944-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/22/2022] [Revised: 04/12/2023] [Accepted: 05/16/2023] [Indexed: 08/10/2023]
Abstract
OBJECTIVES To develop a high-accuracy MRI-based deep learning method for predicting cyclin-dependent kinase inhibitor 2A/B (CDKN2A/B) homozygous deletion status in isocitrate dehydrogenase (IDH)-mutant astrocytoma. METHODS Multiparametric brain MRI data and corresponding genomic information of 234 subjects (111 positives for CDKN2A/B homozygous deletion and 123 negatives for CDKN2A/B homozygous deletion) were obtained from The Cancer Imaging Archive (TCIA) and The Cancer Genome Atlas (TCGA) respectively. Two independent multi-sequence networks (ResFN-Net and FN-Net) are built on the basis of ResNet and ConvNeXt network combined with attention mechanism to classify CDKN2A/B homozygous deletion status using MR images including contrast-enhanced T1-weighted imaging (CE-T1WI) and T2-weighted imaging (T2WI). The performance of the network is summarized by three-way cross-validation; ROC analysis is also performed. RESULTS The average cross-validation accuracy (ACC) of ResFN-Net is 0.813. The average cross-validation area under curve (AUC) of ResFN-Net is 0.8804. The average cross-validation ACC and AUC of FN-Net is 0.9236 and 0.9704, respectively. Comparing all sequence combinations of the two networks (ResFN-Net and FN-Net), the sequence combination of CE-T1WI and T2WI performed the best, and the ACC and AUC were 0.8244, 0.8975 and 0.8971, 0.9574, respectively. CONCLUSIONS The FN-Net deep learning networks based on ConvNeXt network achieved promising performance for predicting CDKN2A/B homozygous deletion status of IDH-mutant astrocytoma. CLINICAL RELEVANCE STATEMENT A novel deep learning network (FN-Net) based on preoperative MRI was developed to predict the CDKN2A/B homozygous deletion status. This network has the potential to be a practical tool for the noninvasive characterization of CDKN2A/B in glioma to support personalized classification and treatment planning. KEY POINTS • CDKN2A/B homozygous deletion status is an important marker for glioma grading and prognosis. • An MRI-based deep learning approach was developed to predict CDKN2A/B homozygous deletion status. • The predictive performance based on ConvNeXt network was better than that of ResNet network.
Collapse
Affiliation(s)
- Liqiang Zhang
- Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, 400016, China
| | - Rui Wang
- School of Computer Science and Engineering, Chongqing Normal University, Chongqing, 401331, China
| | - Jueni Gao
- Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, 400016, China
| | - Yi Tang
- Molecular Medicine Diagnostic and Testing Center, Chongqing Medical University, Chongqing, 400016, China
| | - Xinyi Xu
- Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, 400016, China
| | - Yubo Kan
- School of Medical and Life Sciences, Chengdu University of Traditional Chinese Medicine, Chengdu, 610032, China
| | - Xu Cao
- School of Medical and Life Sciences, Chengdu University of Traditional Chinese Medicine, Chengdu, 610032, China
| | - Zhipeng Wen
- Department of Radiology, School of Medicine, Sichuan Cancer Hospital & Institute, Sichuan Cancer Center, University of Electronic Science and Technology of China, Chengdu, 610042, China
| | - Zhi Liu
- Department of Radiology, Chongqing Hospital of Traditional Chinese Medicine, Chongqing, 400021, China.
| | - Shaoguo Cui
- School of Computer Science and Engineering, Chongqing Normal University, Chongqing, 401331, China.
| | - Yongmei Li
- Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, 400016, China.
| |
Collapse
|
33
|
Fan ZC, Zhang L, Yang GQ, Li S, Guo JT, Bai JJ, Wang B, Li Y, Wang L, Wang XC. MRI radiomics for predicting poor disease-free survival in muscle invasive bladder cancer: the results of the retrospective cohort study. Abdom Radiol (NY) 2024; 49:151-162. [PMID: 37804424 DOI: 10.1007/s00261-023-04028-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/02/2023] [Revised: 08/09/2023] [Accepted: 08/14/2023] [Indexed: 10/09/2023]
Abstract
OBJECTIVES To develop an MRI radiomic nomogram capable of identifying muscle invasive bladder cancer (MIBC) patients with high-risk molecular characteristics related to poor 2-year disease-free survival (DFS). METHODS We performed a retrospective analysis of DNA sequencing data, prognostic information, and radiomics features from 91 MIBC patients at stages T2-T4aN0M0 without history of immunotherapy. To identify risk stratification, we employed Cox regression based on TP53 mutation status and tumor mutational burden (TMB) level. Radiomics signatures were selected using the least absolute shrinkage and selection operator (LASSO) to construct a nomogram based on logistic regression for predicting the stratification in the training cohort. The predictive performance of the nomogram was assessed in the testing cohort using receiver operator curve (ROC), Hosmer-Lemeshow (HL) test, clinical impact curve (CIC), and decision curve analysis (DCA). RESULTS Among 91 participants, the mean TMB value was 3.3 mut/Mb, with 60 participants having TP53 mutations. Patients with TP53 mutations and a below-average TMB value were identified as high risk and had a significantly poor 2-year DFS (hazard ratio = 4.36, 95% CI 1.82-10.44, P < 0.001). LASSO identified five radiomics signatures that correlated with the risk stratification. In the testing cohort, the nomogram achieved an area under the ROC curve of 0.909 (95% CI 0.789-0.991) and an accuracy of 0.889 (95% CI 0.708-0.977). CONCLUSION The molecular risk stratification based on TP53 mutation status combined with TMB level is strongly associated with DFS in MIBC. Radiomics signatures can effectively predict this stratification and provide valuable information to clinical decision-making.
Collapse
Affiliation(s)
- Zhi-Chang Fan
- Department of Medical Imaging, Shanxi Medical University, Taiyuan, 030001, Shanxi, People's Republic of China
| | - Lu Zhang
- Department of Medical Imaging, Shanxi Medical University, Taiyuan, 030001, Shanxi, People's Republic of China
| | - Guo-Qiang Yang
- Department of Radiology, First Hospital of Shanxi Medical University, No. 85 Jiefang South Road, Taiyuan, 030001, Shanxi, People's Republic of China
| | - Shuo Li
- Department of Medical Imaging, Shanxi Medical University, Taiyuan, 030001, Shanxi, People's Republic of China
| | - Jun-Ting Guo
- Department of Medical Imaging, Shanxi Medical University, Taiyuan, 030001, Shanxi, People's Republic of China
| | - Jing-Jing Bai
- Department of Medical Imaging, Shanxi Medical University, Taiyuan, 030001, Shanxi, People's Republic of China
| | - Bin Wang
- Department of Radiology, First Hospital of Shanxi Medical University, No. 85 Jiefang South Road, Taiyuan, 030001, Shanxi, People's Republic of China
| | - Yan Li
- Department of Radiology, First Hospital of Shanxi Medical University, No. 85 Jiefang South Road, Taiyuan, 030001, Shanxi, People's Republic of China
| | - Le Wang
- Department of Radiology, First Hospital of Shanxi Medical University, No. 85 Jiefang South Road, Taiyuan, 030001, Shanxi, People's Republic of China
| | - Xiao-Chun Wang
- Department of Radiology, First Hospital of Shanxi Medical University, No. 85 Jiefang South Road, Taiyuan, 030001, Shanxi, People's Republic of China.
| |
Collapse
|
34
|
Buz-Yalug B, Turhan G, Cetin AI, Dindar SS, Danyeli AE, Yakicier C, Pamir MN, Özduman K, Dincer A, Ozturk-Isik E. Identification of IDH and TERTp mutations using dynamic susceptibility contrast MRI with deep learning in 162 gliomas. Eur J Radiol 2024; 170:111257. [PMID: 38134710 DOI: 10.1016/j.ejrad.2023.111257] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/10/2023] [Revised: 11/21/2023] [Accepted: 12/06/2023] [Indexed: 12/24/2023]
Abstract
PURPOSE Isocitrate dehydrogenase (IDH) and telomerase reverse transcriptase gene promoter (TERTp) mutations play crucial roles in glioma biology. Such genetic information is typically obtained invasively from excised tumor tissue; however, these mutations need to be identified preoperatively for better treatment planning. The relative cerebral blood volume (rCBV) information derived from dynamic susceptibility contrast MRI (DSC-MRI) has been demonstrated to correlate with tumor vascularity, functionality, and biology, and might provide some information about the genetic alterations in gliomas before surgery. Therefore, this study aims to predict IDH and TERTp mutational subgroups in gliomas using deep learning applied to rCBV images. METHOD After the generation of rCBV images from DSC-MRI data, classical machine learning algorithms were applied to the features obtained from the segmented tumor volumes to classify IDH and TERTp mutation subgroups. Furthermore, pre-trained convolutional neural networks (CNNs) and CNNs enhanced with attention gates were trained using rCBV images or a combination of rCBV and anatomical images to classify the mutational subgroups. RESULTS The best accuracies obtained with classical machine learning algorithms were 83 %, 68 %, and 76 % for the identification of IDH mutational, TERTp mutational, and TERTp-only subgroups, respectively. On the other hand, the best-performing CNN model achieved 88 % accuracy (86 % sensitivity, 91 % specificity) for the IDH-mutational subgroups, 70 % accuracy (73 % sensitivity and 67 % specificity) for the TERTp-mutational subgroups, and 84 % accuracy (86 % sensitivity, 81 % specificity) for the TERTp-only subgroup using attention gates. CONCLUSIONS DSC-MRI can be utilized to noninvasively classify IDH- and TERTp-based molecular subgroups of gliomas, facilitating preoperative identification of these genetic alterations.
Collapse
Affiliation(s)
- Buse Buz-Yalug
- Institute of Biomedical Engineering, Bogazici University, Istanbul, Turkey
| | - Gulce Turhan
- Institute of Biomedical Engineering, Bogazici University, Istanbul, Turkey
| | - Ayse Irem Cetin
- Institute of Biomedical Engineering, Bogazici University, Istanbul, Turkey
| | - Sukru Samet Dindar
- Electrical and Electronics Engineering Department, Bogazici University, Istanbul, Turkey
| | - Ayca Ersen Danyeli
- Department of Medical Pathology, Acibadem University, Istanbul, Turkey; Center for Neuroradiological Applications and Research, Acibadem University, Istanbul, Turkey
| | - Cengiz Yakicier
- Department of Molecular Biology and Genetics, Acibadem University, Istanbul, Turkey
| | - M Necmettin Pamir
- Center for Neuroradiological Applications and Research, Acibadem University, Istanbul, Turkey; Department of Neurosurgery, Acibadem University, Istanbul, Turkey
| | - Koray Özduman
- Center for Neuroradiological Applications and Research, Acibadem University, Istanbul, Turkey; Department of Neurosurgery, Acibadem University, Istanbul, Turkey
| | - Alp Dincer
- Center for Neuroradiological Applications and Research, Acibadem University, Istanbul, Turkey; Department of Radiology, Acıbadem University, Istanbul, Turkey
| | - Esin Ozturk-Isik
- Institute of Biomedical Engineering, Bogazici University, Istanbul, Turkey; Center for Neuroradiological Applications and Research, Acibadem University, Istanbul, Turkey.
| |
Collapse
|
35
|
Wen X, Wang C, Pan Z, Jin Y, Wang H, Zhou J, Sun C, Ye G, Chen M. Integrated analysis reveals the potential of cluster of differentiation 86 as a key biomarker in high-grade glioma. Aging (Albany NY) 2023; 15:15402-15418. [PMID: 38154107 PMCID: PMC10781505 DOI: 10.18632/aging.205359] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/08/2023] [Accepted: 11/16/2023] [Indexed: 12/30/2023]
Abstract
This study aimed to evaluate the potential of cluster of differentiation 86 (CD86) as a biomarker in high-grade glioma (HGG). The TCGA and TCIA databases were used to obtain the CD86 expression value, clinical data, and MRI images of HGG patients. Prognostic values were assessed by the Kaplan-Meier method, Receiver operating characteristic curve (ROC), Cox regression, logistic regression, and nomogram analyses. CD86-associated pathways were also explored. We found that CD86 was significantly upregulated in HGG compared with the normal group. Survival analysis showed a significant association between CD86 high expression and shorter overall survival time. Its independent prognostic value was also confirmed. These results suggested the possibility of CD86 as a biomarker in HGG. We also innovatively established 2 radiomics models with Support Vector Machine (SVM) and Logistic regression (LR) algorithms to predict the CD86 expression. The 2 models containing 5 optimal features by SVM and LR methods showed similar favorable performance in predicting CD86 expression in the training set, and their performance were also confirmed in validation set. These results indicated the successful construction of a radiomics model for non-invasively predicting biomarker in HGG. Finally, pathway analysis indicated that CD86 might be involved in the natural killer cell-mediated cytotoxicity in HGG progression.
Collapse
Affiliation(s)
- Xuebin Wen
- Department of Anesthesiology, Ningbo Medical Center Lihuili Hospital, Ningbo 315100, Zhejiang, China
| | - Chaochao Wang
- Department of Radiology, Ningbo Medical Center Lihuili Hospital, Ningbo 315100, Zhejiang, China
| | - Zhihao Pan
- Department of Anesthesiology, Ningbo Medical Center Lihuili Hospital, Ningbo 315100, Zhejiang, China
| | - Yao Jin
- Department of Radiology, Ningbo Medical Center Lihuili Hospital, Ningbo 315100, Zhejiang, China
| | - Hongcai Wang
- Department of Neurosurgery, Ningbo Medical Center Lihuili Hospital, Ningbo 315100, Zhejiang, China
| | - Jiang Zhou
- Department of Neurosurgery, Ningbo Medical Center Lihuili Hospital, Ningbo 315100, Zhejiang, China
| | - Chengfeng Sun
- Department of Neurosurgery, Ningbo Medical Center Lihuili Hospital, Ningbo 315100, Zhejiang, China
| | - Gengfan Ye
- Department of Neurosurgery, Ningbo Medical Center Lihuili Hospital, Ningbo 315100, Zhejiang, China
| | - Maosong Chen
- Department of Neurosurgery, Ningbo Medical Center Lihuili Hospital, Ningbo 315100, Zhejiang, China
| |
Collapse
|
36
|
Guillevin R, Naudin M, Fayolle P, Giraud C, Le Guillou X, Thomas C, Herpe G, Miranville A, Fernandez-Maloigne C, Pellerin L, Guillevin C. Diagnostic and Therapeutic Issues in Glioma Using Imaging Data: The Challenge of Numerical Twinning. J Clin Med 2023; 12:7706. [PMID: 38137775 PMCID: PMC10744312 DOI: 10.3390/jcm12247706] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/06/2023] [Revised: 11/28/2023] [Accepted: 12/11/2023] [Indexed: 12/24/2023] Open
Abstract
Glial tumors represent the leading etiology of primary brain tumors. Their particularities lie in (i) their location in a highly functional organ that is difficult to access surgically, including for biopsy, and (ii) their rapid, anisotropic mode of extension, notably via the fiber bundles of the white matter, which further limits the possibilities of resection. The use of mathematical tools enables the development of numerical models representative of the oncotype, genotype, evolution, and therapeutic response of lesions. The significant development of digital technologies linked to high-resolution NMR exploration, coupled with the possibilities offered by AI, means that we can envisage the creation of digital twins of tumors and their host organs, thus reducing the use of physical sampling.
Collapse
Affiliation(s)
- Rémy Guillevin
- Department of Imaging, University Hospital Center of Poitiers, 86000 Poitiers, France
- Labcom I3M, University of Poitiers, 86000 Poitiers, France
- DACTIM-MIS Team, Laboratoire de Mathématiques Appliquées LMA, CNRS UMR 7348, 86021 Poitiers, France
| | - Mathieu Naudin
- Department of Imaging, University Hospital Center of Poitiers, 86000 Poitiers, France
- Labcom I3M, University of Poitiers, 86000 Poitiers, France
- DACTIM-MIS Team, Laboratoire de Mathématiques Appliquées LMA, CNRS UMR 7348, 86021 Poitiers, France
| | - Pierre Fayolle
- Department of Imaging, University Hospital Center of Poitiers, 86000 Poitiers, France
- Labcom I3M, University of Poitiers, 86000 Poitiers, France
- DACTIM-MIS Team, Laboratoire de Mathématiques Appliquées LMA, CNRS UMR 7348, 86021 Poitiers, France
| | - Clément Giraud
- Department of Imaging, University Hospital Center of Poitiers, 86000 Poitiers, France
- Labcom I3M, University of Poitiers, 86000 Poitiers, France
- DACTIM-MIS Team, Laboratoire de Mathématiques Appliquées LMA, CNRS UMR 7348, 86021 Poitiers, France
| | - Xavier Le Guillou
- Labcom I3M, University of Poitiers, 86000 Poitiers, France
- DACTIM-MIS Team, Laboratoire de Mathématiques Appliquées LMA, CNRS UMR 7348, 86021 Poitiers, France
- Department of Genetic, University Hospital Center of Poitiers, 86000 Poitiers, France
| | - Clément Thomas
- Department of Imaging, University Hospital Center of Poitiers, 86000 Poitiers, France
- Labcom I3M, University of Poitiers, 86000 Poitiers, France
- DACTIM-MIS Team, Laboratoire de Mathématiques Appliquées LMA, CNRS UMR 7348, 86021 Poitiers, France
| | - Guillaume Herpe
- Department of Imaging, University Hospital Center of Poitiers, 86000 Poitiers, France
- Labcom I3M, University of Poitiers, 86000 Poitiers, France
- DACTIM-MIS Team, Laboratoire de Mathématiques Appliquées LMA, CNRS UMR 7348, 86021 Poitiers, France
| | - Alain Miranville
- Labcom I3M, University of Poitiers, 86000 Poitiers, France
- DACTIM-MIS Team, Laboratoire de Mathématiques Appliquées LMA, CNRS UMR 7348, 86021 Poitiers, France
| | | | - Luc Pellerin
- IRMETIST Laboratory, INSERM U1313, University of Poitiers and University Hospital Center of Poitiers, 86000 Poitiers, France
| | - Carole Guillevin
- Department of Imaging, University Hospital Center of Poitiers, 86000 Poitiers, France
- Labcom I3M, University of Poitiers, 86000 Poitiers, France
- DACTIM-MIS Team, Laboratoire de Mathématiques Appliquées LMA, CNRS UMR 7348, 86021 Poitiers, France
| |
Collapse
|
37
|
Xie X, Shen C, Zhang X, Wu G, Yang B, Qi Z, Tang Q, Wang Y, Ding H, Shi Z, Yu J. Rapid intraoperative multi-molecular diagnosis of glioma with ultrasound radio frequency signals and deep learning. EBioMedicine 2023; 98:104899. [PMID: 38041959 PMCID: PMC10711390 DOI: 10.1016/j.ebiom.2023.104899] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/06/2023] [Revised: 11/16/2023] [Accepted: 11/17/2023] [Indexed: 12/04/2023] Open
Abstract
BACKGROUND Molecular diagnosis is crucial for biomarker-assisted glioma resection and management. However, some limitations of current molecular diagnostic techniques prevent their widespread use intraoperatively. With the unique advantages of ultrasound, this study developed a rapid intraoperative molecular diagnostic method based on ultrasound radio-frequency signals. METHODS We built a brain tumor ultrasound bank with 169 cases enrolled since July 2020, of which 43483 RF signal patches from 67 cases with a pathological diagnosis of glioma were a retrospective cohort for model training and validation. IDH1 and TERT promoter (TERTp) mutations and 1p/19q co-deletion were detected by next-generation sequencing. We designed a spatial-temporal integration model (STIM) to diagnose the three molecular biomarkers, thus establishing a rapid intraoperative molecular diagnostic system for glioma, and further analysed its consistency with the fifth edition of the WHO Classification of Tumors of the Central Nervous System (WHO CNS5). We tested STIM in 16-case prospective cohorts, which contained a total of 10384 RF signal patches. Two other RF-based classical models were used for comparison. Further, we included 20 cases additional prospective data for robustness test (ClinicalTrials.govNCT05656053). FINDINGS In the retrospective cohort, STIM achieved a mean accuracy and AUC of 0.9190 and 0.9650 (95% CI, 0.94-0.99) respectively for the three molecular biomarkers, with a total time of 3 s and a 96% match to WHO CNS5. In the prospective cohort, the diagnostic accuracy of STIM is 0.85 ± 0.04 (mean ± SD) for IDH1, 0.84 ± 0.05 for TERTp, and 0.88 ± 0.04 for 1p/19q. The AUC is 0.89 ± 0.02 (95% CI, 0.84-0.94) for IDH1, 0.80 ± 0.04 (95% CI, 0.71-0.89) for TERTp, and 0.85 ± 0.06 (95% CI, 0.73-0.98) for 1p/19q. Compared to the second best available method based on RF signal, the diagnostic accuracy of STIM is improved by 16.70% and the AUC is improved by 19.23% on average. INTERPRETATION STIM is a rapid, cost-effective, and easy-to-manipulate AI method to perform real-time intraoperative molecular diagnosis. In the future, it may help neurosurgeons designate personalized surgical plans and predict survival outcomes. FUNDING A full list of funding bodies that contributed to this study can be found in the Acknowledgements section.
Collapse
Affiliation(s)
- Xuan Xie
- School of Information Science and Technology, Fudan University, Shanghai, China; Neurosurgical Institute of Fudan University, Shanghai, China
| | - Chao Shen
- Department of Neurosurgery, Huashan Hospital, Fudan University, Shanghai, China; National Center for Neurological Disorders, Shanghai, China; Shanghai Key Laboratory of Brain Function Restoration and Neural Regeneration, Shanghai, China; Neurosurgical Institute of Fudan University, Shanghai, China
| | - Xiandi Zhang
- Department of Ultrasound, Huashan Hospital, Fudan University, Shanghai, China
| | - Guoqing Wu
- School of Information Science and Technology, Fudan University, Shanghai, China; Neurosurgical Institute of Fudan University, Shanghai, China
| | - Bojie Yang
- Department of Neurosurgery, Huashan Hospital, Fudan University, Shanghai, China; National Center for Neurological Disorders, Shanghai, China; Shanghai Key Laboratory of Brain Function Restoration and Neural Regeneration, Shanghai, China; Neurosurgical Institute of Fudan University, Shanghai, China
| | - Zengxin Qi
- Department of Neurosurgery, Huashan Hospital, Fudan University, Shanghai, China; National Center for Neurological Disorders, Shanghai, China; Shanghai Key Laboratory of Brain Function Restoration and Neural Regeneration, Shanghai, China; Neurosurgical Institute of Fudan University, Shanghai, China
| | - Qisheng Tang
- Department of Neurosurgery, Huashan Hospital, Fudan University, Shanghai, China; National Center for Neurological Disorders, Shanghai, China; Shanghai Key Laboratory of Brain Function Restoration and Neural Regeneration, Shanghai, China; Neurosurgical Institute of Fudan University, Shanghai, China
| | - Yuanyuan Wang
- School of Information Science and Technology, Fudan University, Shanghai, China
| | - Hong Ding
- Department of Ultrasound, Huashan Hospital, Fudan University, Shanghai, China.
| | - Zhifeng Shi
- Department of Neurosurgery, Huashan Hospital, Fudan University, Shanghai, China; National Center for Neurological Disorders, Shanghai, China; Shanghai Key Laboratory of Brain Function Restoration and Neural Regeneration, Shanghai, China; Neurosurgical Institute of Fudan University, Shanghai, China.
| | - Jinhua Yu
- School of Information Science and Technology, Fudan University, Shanghai, China; Neurosurgical Institute of Fudan University, Shanghai, China.
| |
Collapse
|
38
|
Pan I, Huang RY. Artificial intelligence in neuroimaging of brain tumors: reality or still promise? Curr Opin Neurol 2023; 36:549-556. [PMID: 37973024 DOI: 10.1097/wco.0000000000001213] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/19/2023]
Abstract
PURPOSE OF REVIEW To provide an updated overview of artificial intelligence (AI) applications in neuro-oncologic imaging and discuss current barriers to wider clinical adoption. RECENT FINDINGS A wide variety of AI applications in neuro-oncologic imaging have been developed and researched, spanning tasks from pretreatment brain tumor classification and segmentation, preoperative planning, radiogenomics, prognostication and survival prediction, posttreatment surveillance, and differentiating between pseudoprogression and true disease progression. While earlier studies were largely based on data from a single institution, more recent studies have demonstrated that the performance of these algorithms are also effective on external data from other institutions. Nevertheless, most of these algorithms have yet to see widespread clinical adoption, given the lack of prospective studies demonstrating their efficacy and the logistical difficulties involved in clinical implementation. SUMMARY While there has been significant progress in AI and neuro-oncologic imaging, clinical utility remains to be demonstrated. The next wave of progress in this area will be driven by prospective studies measuring outcomes relevant to clinical practice and go beyond retrospective studies which primarily aim to demonstrate high performance.
Collapse
Affiliation(s)
- Ian Pan
- Department of Radiology, Brigham and Women's Hospital, Harvard Medical School
| | | |
Collapse
|
39
|
Kim H, Kim HG, Oh JH, Lee KM. Deep-learning model for diagnostic clue: detecting the dural tail sign for meningiomas on contrast-enhanced T1 weighted images. Quant Imaging Med Surg 2023; 13:8132-8143. [PMID: 38106283 PMCID: PMC10722041 DOI: 10.21037/qims-23-114] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/30/2023] [Accepted: 09/06/2023] [Indexed: 12/19/2023]
Abstract
Background Meningiomas are the most common primary central nervous system tumors, and magnetic resonance imaging (MRI), especially contrast-enhanced T1 weighted image (CE T1WI), is used as a fundamental imaging modality for the detection and analysis of the tumors. In this study, we propose an automated deep-learning model for meningioma detection using the dural tail sign. Methods The dataset included 123 patients with 3,824 dural tail signs on sagittal CE T1WI. The dataset was divided into training and test datasets based on specific time point, and 78 and 45 patients were comprised for the training and test dataset, respectively. To compensate for the small sample size of the training dataset, 39 additional patients with 69 dural tail signs from the open dataset were appended to the training dataset. A You Only Look Once (YOLO) v4 network was trained with sagittal CE T1WI to detect dural tail signs. The normal group dataset, comprised of 51 patients with no abnormal finding on MRI, was employed to evaluate the specificity of the trained model. Results The sensitivity and false positive average were 82.22% and 29.73, respectively, in the test dataset. The specificity and false positive average were 17.65% and 3.16, respectively, in the normal dataset. Most of the false-positive cases in the test dataset were enhancing vessels, misinterpreted as dural thickening. Conclusions The proposed model demonstrates an automated detection system for the dural tail sign to identify meningioma in general screening MRI. Our model can facilitate and alleviate radiologists' reading process by notifying the possibility of incidental dural mass based on dural tail sign detection.
Collapse
Affiliation(s)
- Hyunmin Kim
- Department of Radiology, Kyung Hee University Hospital, Kyung Hee University College of Medicine, Seoul, Republic of Korea
| | - Hyug-Gi Kim
- Department of Radiology, Kyung Hee University Hospital, Kyung Hee University College of Medicine, Seoul, Republic of Korea
| | | | | |
Collapse
|
40
|
Liu X, Zhang Q, Li J, Xu Q, Zhuo Z, Li J, Zhou X, Lu M, Zhou Q, Pan H, Wu N, Zhou Q, Shi F, Lu G, Liu Y, Zhang Z. Coordinatized lesion location analysis empowering ROI-based radiomics diagnosis on brain gliomas. Eur Radiol 2023; 33:8776-8787. [PMID: 37382614 DOI: 10.1007/s00330-023-09871-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/12/2022] [Revised: 05/09/2023] [Accepted: 05/16/2023] [Indexed: 06/30/2023]
Abstract
OBJECTIVES To assess the value of coordinatized lesion location analysis (CLLA), in empowering ROI-based imaging diagnosis of gliomas by improving accuracy and generalization performances. METHODS In this retrospective study, pre-operative contrasted T1-weighted and T2-weighted MR images were obtained from patients with gliomas from three centers: Jinling Hospital, Tiantan Hospital, and the Cancer Genome Atlas Program. Based on CLLA and ROI-based radiomic analyses, a fusion location-radiomics model was constructed to predict tumor grades, isocitrate dehydrogenase (IDH) status, and overall survival (OS). An inter-site cross-validation strategy was used for assessing the performances of the fusion model on accuracy and generalization with the value of area under the curve (AUC) and delta accuracy (ACC) (ACCtesting-ACCtraining). Comparisons of diagnostic performances were performed between the fusion model and the other two models constructed with location and radiomics analysis using DeLong's test and Wilcoxon signed ranks test. RESULTS A total of 679 patients (mean age, 50 years ± 14 [standard deviation]; 388 men) were enrolled. Based on tumor location probabilistic maps, fusion location-radiomics models (averaged AUC values of grade/IDH/OS: 0.756/0.748/0.768) showed the highest accuracy in contrast to radiomics models (0.731/0.686/0.716) and location models (0.706/0.712/0.740). Notably, fusion models ([median Delta ACC: - 0.125, interquartile range: 0.130]) demonstrated improved generalization than that of radiomics model ([- 0.200, 0.195], p = 0.018). CONCLUSIONS CLLA could empower ROI-based radiomics diagnosis of gliomas by improving the accuracy and generalization of the models. CLINICAL RELEVANCE STATEMENT This study proposed a coordinatized lesion location analysis for glioma diagnosis, which could improve the performances of the conventional ROI-based radiomics model in accuracy and generalization. KEY POINTS • Using coordinatized lesion location analysis, we mapped anatomic distribution patterns of gliomas with specific pathological and clinical features and constructed glioma prediction models. • We integrated coordinatized lesion location analysis into ROI-based analysis of radiomics to propose new fusion location-radiomics models. • Fusion location-radiomics models, with the advantages of being less influenced by variabilities, improved accuracy, and generalization performances of ROI-based radiomics models on predicting the diagnosis of gliomas.
Collapse
Affiliation(s)
- Xiaoxue Liu
- Department of Diagnostic Radiology, Affiliated Jinling Hospital, Medical School of Nanjing University, 305#, Eastern Zhongshan Rd, Nanjing, 210002, China
| | - Qirui Zhang
- Department of Diagnostic Radiology, Affiliated Jinling Hospital, Medical School of Nanjing University, 305#, Eastern Zhongshan Rd, Nanjing, 210002, China
| | - Jianrui Li
- Department of Diagnostic Radiology, Affiliated Jinling Hospital, Medical School of Nanjing University, 305#, Eastern Zhongshan Rd, Nanjing, 210002, China
| | - Qiang Xu
- Department of Diagnostic Radiology, Affiliated Jinling Hospital, Medical School of Nanjing University, 305#, Eastern Zhongshan Rd, Nanjing, 210002, China
| | - Zhizheng Zhuo
- Department of Radiology, Beijing Tiantan Hospital, Capital Medical University, Beijing, 100070, China
| | - Junjie Li
- Department of Radiology, Beijing Tiantan Hospital, Capital Medical University, Beijing, 100070, China
| | - Xian Zhou
- Department of Diagnostic Radiology, Affiliated Jinling Hospital, Medical School of Nanjing University, 305#, Eastern Zhongshan Rd, Nanjing, 210002, China
| | - Mengjie Lu
- School of Public Health, Shanghai JiaoTong University School of Medicine, Shanghai, 200240, China
| | - Qingqing Zhou
- Department of Radiology, The Affiliated Jiangning Hospital of Nanjing Medical University, Nanjing, 211100, China
| | - Hao Pan
- Department of Neurosurgery, Affiliated Jinling Hospital, Medical School of Nanjing University, Nanjing, 210002, China
| | - Nan Wu
- Department of Pathology, Affiliated Jinling Hospital, Medical School of Nanjing University, Nanjing, 210002, China
| | - Qing Zhou
- Department of Research and Development, Shanghai United Imaging Intelligence Co., Ltd., Shanghai, 200232, China
| | - Feng Shi
- Department of Research and Development, Shanghai United Imaging Intelligence Co., Ltd., Shanghai, 200232, China
| | - Guangming Lu
- Department of Diagnostic Radiology, Affiliated Jinling Hospital, Medical School of Nanjing University, 305#, Eastern Zhongshan Rd, Nanjing, 210002, China
- State Key Laboratory of Analytical Chemistry for Life Science, Nanjing University, Nanjing, 210093, China
| | - Yaou Liu
- Department of Radiology, Beijing Tiantan Hospital, Capital Medical University, Beijing, 100070, China
| | - Zhiqiang Zhang
- Department of Diagnostic Radiology, Affiliated Jinling Hospital, Medical School of Nanjing University, 305#, Eastern Zhongshan Rd, Nanjing, 210002, China.
- State Key Laboratory of Analytical Chemistry for Life Science, Nanjing University, Nanjing, 210093, China.
| |
Collapse
|
41
|
Ioannidis GS, Pigott LE, Iv M, Surlan-Popovic K, Wintermark M, Bisdas S, Marias K. Investigating the value of radiomics stemming from DSC quantitative biomarkers in IDH mutation prediction in gliomas. Front Neurol 2023; 14:1249452. [PMID: 38046592 PMCID: PMC10690367 DOI: 10.3389/fneur.2023.1249452] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/28/2023] [Accepted: 10/31/2023] [Indexed: 12/05/2023] Open
Abstract
Objective This study aims to assess the value of biomarker based radiomics to predict IDH mutation in gliomas. The patient cohort consists of 160 patients histopathologicaly proven of primary glioma (WHO grades 2-4) from 3 different centers. Methods To quantify the DSC perfusion signal two different mathematical modeling methods were used (Gamma fitting, leakage correction algorithms) considering the assumptions about the compartments contributing in the blood flow between the extra- and intra vascular space. Results The Mean slope of increase (MSI) and the K1 parameter of the bidirectional exchange model exhibited the highest performance with (ACC 74.3% AUROC 74.2%) and (ACC 75% AUROC 70.5%) respectively. Conclusion The proposed framework on DSC-MRI radiogenomics in gliomas has the potential of becoming a reliable diagnostic support tool exploiting the mathematical modeling of the DSC signal to characterize IDH mutation status through a more reproducible and standardized signal analysis scheme for facilitating clinical translation.
Collapse
Affiliation(s)
- Georgios S. Ioannidis
- Computational BioMedicine Laboratory (CBML), Institute of Computer Science, Foundation for Research and Technology—Hellas (FORTH), Heraklion, Greece
| | - Laura Elin Pigott
- Institute of Health and Social Care, London South Bank University, London, United Kingdom
- Faculty of Brain Science, Queen Square Institute of Neurology, University College London, London, United Kingdom
- Lysholm Department of Neuroradiology, The National Hospital for Neurology and Neurosurgery University College London, London, United Kingdom
| | - Michael Iv
- Department of Radiology, Division of Neuroimaging and Neurointervention, Stanford University, Stanford, CA, United States
| | - Katarina Surlan-Popovic
- Department of Radiology, Faculty of Medicine, University of Ljubljana, Ljubljana, Slovenia
- Department of Neuroradiology, University Medical Centre, Ljubljana, Slovenia
| | - Max Wintermark
- Department of Radiology, Division of Neuroimaging and Neurointervention, Stanford University, Stanford, CA, United States
| | - Sotirios Bisdas
- Department of Brain Repair and Rehabilitation, Queen Square Institute of Neurology, UCL, London, United Kingdom
- Department of Neuroradiology, The National Hospital for Neurology and Neurosurgery, University College London NHS Foundation Trust, London, United Kingdom
| | - Kostas Marias
- Computational BioMedicine Laboratory (CBML), Institute of Computer Science, Foundation for Research and Technology—Hellas (FORTH), Heraklion, Greece
- Department of Electrical and Computer Engineering, Hellenic Mediterranean University, Heraklion, Greece
| |
Collapse
|
42
|
Hanna MG, Ardon O. Digital pathology systems enabling quality patient care. Genes Chromosomes Cancer 2023; 62:685-697. [PMID: 37458325 PMCID: PMC11265285 DOI: 10.1002/gcc.23192] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/13/2023] [Revised: 06/27/2023] [Accepted: 07/06/2023] [Indexed: 09/20/2023] Open
Abstract
Pathology laboratories are undergoing digital transformations, adopting innovative technologies to enhance patient care. Digital pathology systems impact clinical, education, and research use cases where pathologists use digital technologies to perform tasks in lieu of using glass slides and a microscope. Pathology professional societies have established clinical validation guidelines, and the US Food and Drug Administration have also authorized digital pathology systems for primary diagnosis, including image analysis and machine learning systems. Whole slide images, or digital slides, can be viewed and navigated similar to glass slides on a microscope. These modern tools not only enable pathologists to practice their routine clinical activities, but can potentially enable digital computational discovery. Assimilation of whole slide images in pathology clinical workflow can further empower machine learning systems to support computer assisted diagnostics. The potential enrichment these systems can provide is unprecedented in the field of pathology. With appropriate integration, these clinical decision support systems will allow pathologists to increase the delivery of quality patient care. This review describes the digital pathology transformation process, applicable clinical use cases, incorporation of image analysis and machine learning systems in the clinical workflow, as well as future technologies that may further disrupt pathology modalities to deliver quality patient care.
Collapse
Affiliation(s)
- Matthew G Hanna
- Department of Pathology and Laboratory Medicine, Memorial Sloan Kettering Cancer Center, New York, New York, USA
| | - Orly Ardon
- Department of Pathology and Laboratory Medicine, Memorial Sloan Kettering Cancer Center, New York, New York, USA
| |
Collapse
|
43
|
Wei Y, Chen X, Zhu L, Zhang L, Schonlieb CB, Price S, Li C. Multi-Modal Learning for Predicting the Genotype of Glioma. IEEE TRANSACTIONS ON MEDICAL IMAGING 2023; 42:3167-3178. [PMID: 37022918 DOI: 10.1109/tmi.2023.3244038] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/18/2023]
Abstract
The isocitrate dehydrogenase (IDH) gene mutation is an essential biomarker for the diagnosis and prognosis of glioma. It is promising to better predict glioma genotype by integrating focal tumor image and geometric features with brain network features derived from MRI. Convolutional neural networks show reasonable performance in predicting IDH mutation, which, however, cannot learn from non-Euclidean data, e.g., geometric and network data. In this study, we propose a multi-modal learning framework using three separate encoders to extract features of focal tumor image, tumor geometrics and global brain networks. To mitigate the limited availability of diffusion MRI, we develop a self-supervised approach to generate brain networks from anatomical multi-sequence MRI. Moreover, to extract tumor-related features from the brain network, we design a hierarchical attention module for the brain network encoder. Further, we design a bi-level multi-modal contrastive loss to align the multi-modal features and tackle the domain gap at the focal tumor and global brain. Finally, we propose a weighted population graph to integrate the multi-modal features for genotype prediction. Experimental results on the testing set show that the proposed model outperforms the baseline deep learning models. The ablation experiments validate the performance of different components of the framework. The visualized interpretation corresponds to clinical knowledge with further validation. In conclusion, the proposed learning framework provides a novel approach for predicting the genotype of glioma.
Collapse
|
44
|
Kim M, Ong KTI, Choi S, Yeo J, Kim S, Han K, Park JE, Kim HS, Choi YS, Ahn SS, Kim J, Lee SK, Sohn B. Natural language processing to predict isocitrate dehydrogenase genotype in diffuse glioma using MR radiology reports. Eur Radiol 2023; 33:8017-8025. [PMID: 37566271 DOI: 10.1007/s00330-023-10061-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/12/2023] [Revised: 05/18/2023] [Accepted: 06/22/2023] [Indexed: 08/12/2023]
Abstract
OBJECTIVES To evaluate the performance of natural language processing (NLP) models to predict isocitrate dehydrogenase (IDH) mutation status in diffuse glioma using routine MR radiology reports. MATERIALS AND METHODS This retrospective, multi-center study included consecutive patients with diffuse glioma with known IDH mutation status from May 2009 to November 2021 whose initial MR radiology report was available prior to pathologic diagnosis. Five NLP models (long short-term memory [LSTM], bidirectional LSTM, bidirectional encoder representations from transformers [BERT], BERT graph convolutional network [GCN], BioBERT) were trained, and area under the receiver operating characteristic curve (AUC) was assessed to validate prediction of IDH mutation status in the internal and external validation sets. The performance of the best performing NLP model was compared with that of the human readers. RESULTS A total of 1427 patients (mean age ± standard deviation, 54 ± 15; 779 men, 54.6%) with 720 patients in the training set, 180 patients in the internal validation set, and 527 patients in the external validation set were included. In the external validation set, BERT GCN showed the highest performance (AUC 0.85, 95% CI 0.81-0.89) in predicting IDH mutation status, which was higher than LSTM (AUC 0.77, 95% CI 0.72-0.81; p = .003) and BioBERT (AUC 0.81, 95% CI 0.76-0.85; p = .03). This was higher than that of a neuroradiologist (AUC 0.80, 95% CI 0.76-0.84; p = .005) and a neurosurgeon (AUC 0.79, 95% CI 0.76-0.84; p = .04). CONCLUSION BERT GCN was externally validated to predict IDH mutation status in patients with diffuse glioma using routine MR radiology reports with superior or at least comparable performance to human reader. CLINICAL RELEVANCE STATEMENT Natural language processing may be used to extract relevant information from routine radiology reports to predict cancer genotype and provide prognostic information that may aid in guiding treatment strategy and enabling personalized medicine. KEY POINTS • A transformer-based natural language processing (NLP) model predicted isocitrate dehydrogenase mutation status in diffuse glioma with an AUC of 0.85 in the external validation set. • The best NLP models were superior or at least comparable to human readers in both internal and external validation sets. • Transformer-based models showed higher performance than conventional NLP model such as long short-term memory.
Collapse
Affiliation(s)
- Minjae Kim
- Department of Radiology and Research Institute of Radiological Science and Center for Clinical Imaging Data Science, Yonsei University College of Medicine, Seoul, Korea
- Department of Radiology and Research Institute of Radiology, University of Ulsan College of Medicine, Asan Medical Center, Seoul, Korea
| | - Kai Tzu-Iunn Ong
- Department of Artificial Intelligence, College of Computing, Yonsei University, Seoul, Korea
| | - Seonah Choi
- Department of Neurosurgery, Brain Tumor Center, Severance Hospital, Yonsei University College of Medicine, Seoul, Korea
| | - Jinyoung Yeo
- Department of Artificial Intelligence, College of Computing, Yonsei University, Seoul, Korea
| | - Sooyon Kim
- Department of Statistics and Data Science, Yonsei University, Seoul, Korea
| | - Kyunghwa Han
- Department of Radiology and Research Institute of Radiological Science and Center for Clinical Imaging Data Science, Yonsei University College of Medicine, Seoul, Korea
| | - Ji Eun Park
- Department of Radiology and Research Institute of Radiology, University of Ulsan College of Medicine, Asan Medical Center, Seoul, Korea
| | - Ho Sung Kim
- Department of Radiology and Research Institute of Radiology, University of Ulsan College of Medicine, Asan Medical Center, Seoul, Korea
| | - Yoon Seong Choi
- Department of Radiology and Research Institute of Radiological Science and Center for Clinical Imaging Data Science, Yonsei University College of Medicine, Seoul, Korea
| | - Sung Soo Ahn
- Department of Radiology and Research Institute of Radiological Science and Center for Clinical Imaging Data Science, Yonsei University College of Medicine, Seoul, Korea
| | - Jinna Kim
- Department of Radiology and Research Institute of Radiological Science and Center for Clinical Imaging Data Science, Yonsei University College of Medicine, Seoul, Korea
| | - Seung-Koo Lee
- Department of Radiology and Research Institute of Radiological Science and Center for Clinical Imaging Data Science, Yonsei University College of Medicine, Seoul, Korea
| | - Beomseok Sohn
- Department of Radiology and Research Institute of Radiological Science and Center for Clinical Imaging Data Science, Yonsei University College of Medicine, Seoul, Korea.
- Department of Radiology and Center for Imaging Sciences, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, Korea.
| |
Collapse
|
45
|
Guo J, Fu X, Li Y, Ming H, Lin Y, Yu S, Wei H, Sun C, Zhang K, Yang X. Ultra high b-value diffusion weighted imaging enables better molecular grading stratification over histological grading in adult-type diffuse glioma. Eur J Radiol 2023; 168:111140. [PMID: 37832200 DOI: 10.1016/j.ejrad.2023.111140] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/31/2023] [Revised: 09/22/2023] [Accepted: 10/05/2023] [Indexed: 10/15/2023]
Abstract
PURPOSE Accurate preoperative radiological staging of adult-type diffuse glioma is crucial for effective prognostic stratification and selection of appropriate therapeutic interventions. The purpose of this study was to compare the effectiveness of apparent diffusion coefficient (ADC) maps generated from ultrahigh b-value diffusion-weighted imaging (DWI) for molecular grading with that for histological grading of adult-type diffuse glioma, and to evaluate the correlation between these ADC maps and molecular and histological biomarkers. METHODS This study retrospectively enrolled forty adult-type diffuse glioma patients, diagnosed using the 2021 WHO classification criteria. Preoperative imaging data, including multiple b-value DWI and conventional magnetic resonance imaging, were collected. Tumors were graded using both histological and molecular criteria. Histogram analysis was conducted to generate 14 parameters for each tumor. Receiver operating characteristic curves and the area under the curve (AUC) were used to evaluate tumor grading and molecular status differentiation. Analysis of histological biomarkers was performed by calculating the Pearson and Spearman correlation coefficients of continuous and hierarchical variables, respectively. RESULTS The intensity-related parameters for molecular grading were found to be superior to those for histological grading for the identification of WHO grade 4 (WHO4) adult-type diffuse glioma. The AUC of both grading systems increased with increasing b-values, with ADC8000-based histogram parameters showing the best results (molecular grading, square root: AUC = 0.897; histological grading, median: AUC = 0.737). The intensity-related parameters could also differentiate molecular WHO4 gliomas from histologically lower-grade gliomas (ADC8000-based square root: AUC = 0.919), and different ADC8000-based kurtosis was observed between molecular and histological WHO4 gliomas (AUC = 0.833). Significant correlations between the Ki-67 index and molecular status prediction for IDH, CDKN2A, and EGFR were also demonstrated. CONCLUSION The histogram parameters derived from high b-value ADC maps were found to be more effective for differentiating molecular grades of WHO4 adult-type diffuse glioma than for differentiating histological grades.
Collapse
Affiliation(s)
- Jiahe Guo
- Department of Neurosurgery, Tianjin Medical University General Hospital, Tianjin, China
| | - Xiuwei Fu
- Department of Radiology, Tianjin Medical University General Hospital, Tianjin, China
| | - Yiming Li
- Department of Neurosurgery, Tianjin Medical University General Hospital, Tianjin, China
| | - Haolang Ming
- Department of Neurosurgery, Tianjin Medical University General Hospital, Tianjin, China
| | - Yu Lin
- Department of Neurosurgery, Tianjin Medical University General Hospital, Tianjin, China
| | - Shengping Yu
- Department of Neurosurgery, Tianjin Medical University General Hospital, Tianjin, China
| | - Huijie Wei
- Department of Neurosurgery, Tianjin Medical University General Hospital, Tianjin, China
| | - Cuiyun Sun
- Department of Neuropathology, Tianjin Medical University General Hospital, Tianjin, China
| | - Kai Zhang
- Department of Neurosurgery, Beijing Tsinghua Changgung Hospital, Tsinghua University, Beijing, China; Institute for Intelligent Healthcare, Tsinghua University, Beijing, China
| | - Xuejun Yang
- Department of Neurosurgery, Beijing Tsinghua Changgung Hospital, Tsinghua University, Beijing, China; Institute for Intelligent Healthcare, Tsinghua University, Beijing, China.
| |
Collapse
|
46
|
Li Y, Zheng K, Li S, Yi Y, Li M, Ren Y, Guo C, Zhong L, Yang W, Li X, Yao L. A transformer-based multi-task deep learning model for simultaneous infiltrated brain area identification and segmentation of gliomas. Cancer Imaging 2023; 23:105. [PMID: 37891702 PMCID: PMC10612240 DOI: 10.1186/s40644-023-00615-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/20/2023] [Accepted: 09/20/2023] [Indexed: 10/29/2023] Open
Abstract
BACKGROUND The anatomical infiltrated brain area and the boundaries of gliomas have a significant impact on clinical decision making and available treatment options. Identifying glioma-infiltrated brain areas and delineating the tumor manually is a laborious and time-intensive process. Previous deep learning-based studies have mainly been focused on automatic tumor segmentation or predicting genetic/histological features. However, few studies have specifically addressed the identification of infiltrated brain areas. To bridge this gap, we aim to develop a model that can simultaneously identify infiltrated brain areas and perform accurate segmentation of gliomas. METHODS We have developed a transformer-based multi-task deep learning model that can perform two tasks simultaneously: identifying infiltrated brain areas segmentation of gliomas. The multi-task model leverages shaped location and boundary information to enhance the performance of both tasks. Our retrospective study involved 354 glioma patients (grades II-IV) with single or multiple brain area infiltrations, which were divided into training (N = 270), validation (N = 30), and independent test (N = 54) sets. We evaluated the predictive performance using the area under the receiver operating characteristic curve (AUC) and Dice scores. RESULTS Our multi-task model achieved impressive results in the independent test set, with an AUC of 94.95% (95% CI, 91.78-97.58), a sensitivity of 87.67%, a specificity of 87.31%, and accuracy of 87.41%. Specifically, for grade II-IV glioma, the model achieved AUCs of 95.25% (95% CI, 91.09-98.23, 84.38% sensitivity, 89.04% specificity, 87.62% accuracy), 98.26% (95% CI, 95.22-100, 93.75% sensitivity, 98.15% specificity, 97.14% accuracy), and 93.83% (95%CI, 86.57-99.12, 92.00% sensitivity, 85.71% specificity, 87.37% accuracy) respectively for the identification of infiltrated brain areas. Moreover, our model achieved a mean Dice score of 87.60% for the whole tumor segmentation. CONCLUSIONS Experimental results show that our multi-task model achieved superior performance and outperformed the state-of-the-art methods. The impressive performance demonstrates the potential of our work as an innovative solution for identifying tumor-infiltrated brain areas and suggests that it can be a practical tool for supporting clinical decision making.
Collapse
Affiliation(s)
- Yin Li
- Department of Information, The Sixth Affiliated Hospital, Sun Yat-Sen University, Guangzhou, China
| | - Kaiyi Zheng
- School of Biomedical Engineering, Southern Medical University, Guangzhou, China
- Guangdong Provincial Key Laboratory of Medical Image Processing, Guangzhou, China
| | - Shuang Li
- Department of General Practice, The Sixth Affiliated Hospital, Sun Yat-Sen University, Guangzhou, China
| | - Yongju Yi
- Department of Information, The Sixth Affiliated Hospital, Sun Yat-Sen University, Guangzhou, China
| | - Min Li
- Department of Radiology, Zhujiang Hospital, Southern Medical University, Guangzhou, China
| | - Yufan Ren
- Department of Radiology, Zhujiang Hospital, Southern Medical University, Guangzhou, China
| | - Congyue Guo
- Department of Radiology, Zhujiang Hospital, Southern Medical University, Guangzhou, China
| | - Liming Zhong
- School of Biomedical Engineering, Southern Medical University, Guangzhou, China
- Guangdong Provincial Key Laboratory of Medical Image Processing, Guangzhou, China
| | - Wei Yang
- School of Biomedical Engineering, Southern Medical University, Guangzhou, China
- Guangdong Provincial Key Laboratory of Medical Image Processing, Guangzhou, China
| | - Xinming Li
- Department of Radiology, Zhujiang Hospital, Southern Medical University, Guangzhou, China.
| | - Lin Yao
- Department of General Practice, The Sixth Affiliated Hospital, Sun Yat-Sen University, Guangzhou, China.
| |
Collapse
|
47
|
Yoon HS, Oh J, Kim YC. Assessing Machine Learning Models for Predicting Age with Intracranial Vessel Tortuosity and Thickness Information. Brain Sci 2023; 13:1512. [PMID: 38002472 PMCID: PMC10669197 DOI: 10.3390/brainsci13111512] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/08/2023] [Revised: 10/19/2023] [Accepted: 10/23/2023] [Indexed: 11/26/2023] Open
Abstract
This study aimed to develop and validate machine learning (ML) models that predict age using intracranial vessels' tortuosity and diameter features derived from magnetic resonance angiography (MRA) data. A total of 171 subjects' three-dimensional (3D) time-of-flight MRA image data were considered for analysis. After annotations of two endpoints in each arterial segment, tortuosity features such as the sum of the angle metrics, triangular index, relative length, and product of the angle distance, as well as the vessels' diameter features, were extracted and used to train and validate the ML models for age prediction. Features extracted from the right and left internal carotid arteries (ICA) and basilar arteries were considered as the inputs to train and validate six ML regression models with a four-fold cross validation. The random forest regression model resulted in the lowest root mean square error of 14.9 years and the highest average coefficient of determination of 0.186. The linear regression model showed the lowest average mean absolute percentage error (MAPE) and the highest average Pearson correlation coefficient (0.532). The mean diameter of the right ICA vessel segment was the most important feature contributing to prediction of age in two out of the four regression models considered. An ML of tortuosity descriptors and diameter features extracted from MRA data showed a modest correlation between real age and ML-predicted age. Further studies are warranted for the assessment of the model's age predictions in patients with intracranial vessel diseases.
Collapse
Affiliation(s)
| | | | - Yoon-Chul Kim
- Division of Digital Healthcare, College of Software and Digital Healthcare Convergence, Yonsei University, Wonju 26493, Republic of Korea; (H.-S.Y.); (J.O.)
| |
Collapse
|
48
|
Lin P, He L, Tian N, Qi X. The evaluation of six genes combined value in glioma diagnosis and prognosis. J Cancer Res Clin Oncol 2023; 149:12413-12433. [PMID: 37439825 DOI: 10.1007/s00432-023-05082-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/29/2023] [Accepted: 06/29/2023] [Indexed: 07/14/2023]
Abstract
PURPOSE Glioma is the most common and fatal type of brain tumour. Owing to its aggressiveness and lethality, early diagnosis and prediction of patient survival are very important. This study aimed to identify key genes and biomarkers for glioma that can guide clinicians in making rapid diagnosis and prognostication. METHODS Data mining of The Cancer Genome Atlas (TCGA), Chinese Glioma Genome Atlas (CGGA), Repository of Molecular Brain Neoplasia Data, and Genotype-Tissue Expression Project brain expression data revealed significantly differentially expressed genes (DEGs), and the risk scores of individual patients were calculated. WGCNA was utilized to screen for genes most related to clinical diagnosis. Prognostic genes associated with glioma were selected via combining the LASSO regression with univariate and multivariate Cox regression and protein-protein interaction network analyses. Then, a nomogram was constructed. And CGGA dataset was utilized to validated. The protein expression levels of the signature were detected using the human protein atlas. Drug response prediction was carried out using the package "pRRophetic". RESULTS A six-gene signature (KLF6, CHI3L1, SERPINE1, ANGPT2, TGFBR1, and PTX3) was identified and used to stratify patients into low- and high-risk groups. Survival, ROC curve, and Cox analyses clarified that the six hub genes were a favourable independent prognostic factor for patients with glioma. A nomogram was set up by integrating clinical parameters with risk signatures, showing high precision for predicting 2-, 3-, 4-, 5-years survival. In addition, the expression of most genes was consistent with protein expression. Furthermore, the sensitivity to the top ten drugs in the GDSC database of the high-risk group was significantly higher than the low-risk group. CONCLUSION Based on genetic profiles and clinicopathological features, including age, grade, isocitrate dehydrogenase mutation status, we constructed a comprehensive prognostic model for patients with glioma. These signatures can be regarded as biomarkers to predict the prognosis of gliomas, possibly providing more therapeutic strategies for future clinical research.
Collapse
Affiliation(s)
- Ping Lin
- Department of Medical Research Center, Shaoxing People's Hospital, Shaoxing, Zhejiang, China
| | - Lingyan He
- Department of Traditional Chinese Medicine, Shaoxing People's Hospital, Shaoxing, Zhejiang, China
| | - Nan Tian
- College of Life Science, Zhejiang Chinese Medical University, Hangzhou, Zhejiang, China.
| | - Xuchen Qi
- Department of Neurosurgery, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine, Hangzhou, Zhejiang, China.
- Department of Neurosurgery, Shaoxing People's Hospital, Shaoxing, Zhejiang, China.
| |
Collapse
|
49
|
Guo Y, Ma Z, Pei D, Duan W, Guo Y, Liu Z, Guan F, Wang Z, Xing A, Guo Z, Luo L, Wang W, Yu B, Zhou J, Ji Y, Yan D, Cheng J, Liu X, Yan J, Zhang Z. Improving Noninvasive Classification of Molecular Subtypes of Adult Gliomas With Diffusion-Weighted MR Imaging: An Externally Validated Machine Learning Algorithm. J Magn Reson Imaging 2023; 58:1234-1242. [PMID: 36727433 DOI: 10.1002/jmri.28630] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/16/2022] [Revised: 01/20/2023] [Accepted: 01/20/2023] [Indexed: 02/03/2023] Open
Abstract
BACKGROUND Genetic testing for molecular markers of gliomas sometimes is unavailable because of time-consuming and expensive, even limited tumor specimens or nonsurgery cases. PURPOSE To train a three-class radiomic model classifying three molecular subtypes including isocitrate dehydrogenase (IDH) mutations and 1p/19q-noncodeleted (IDHmut-noncodel), IDH wild-type (IDHwt), IDH-mutant and 1p/19q-codeleted (IDHmut-codel) of adult gliomas and investigate whether radiomic features from diffusion-weighted imaging (DWI) could bring additive value. STUDY TYPE Retrospective. POPULATION A total of 755 patients including 111 IDHmut-noncodel, 571 IDHwt, and 73 IDHmut-codel cases were divided into training (n = 480) and internal validation set (n = 275); 139 patients including 21 IDHmut-noncodel, 104 IDHwt, and 14 IDHmut-codel cases were utilized as external validation set. FIELD STRENGTH/SEQUENCE A 1.5 T or 3.0 T/multiparametric MRI, including T1-weighted (T1), T1-weighted gadolinium contrast-enhanced (T1c), T2-weighted (T2), fluid attenuated inversion recovery (FLAIR), and DWI. ASSESSMENT The performance of multiparametric radiomic model (random-forest model) using 22 selected features from T1, T2, FLAIR, T1c images and apparent diffusion coefficient (ADC) maps, and conventional radiomic model using 20 selected features from T1, T2, FLAIR, and T1c images was assessed in internal and external validation sets by comparing probability values and actual incidence. STATISTICAL TESTS Mann-Whitney U test, Chi-Squared test, Wilcoxon test, receiver operating curve (ROC), and area under the curve (AUC); DeLong analysis. P < 0.05 was statistically significant. RESULTS The multiparametric radiomic model achieved AUC values for IDHmut-noncodel, IDHwt, and IDHmut-codel of 0.8181, 0.8524, and 0.8502 in internal validation set and 0.7571, 0.7779, and 0.7491 in external validation set, respectively. Multiparametric radiomic model showed significantly better diagnostic performance after DeLong analysis, especially in classifying IDHwt and IDHmut-noncodel subtypes. DATA CONCLUSION Radiomic features from DWI could bring additive value and improve the performance of conventional MRI-based radiomic model for classifying the molecular subtypes especially IDHmut-noncodel and IDHwt of adult gliomas. LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY Stage 2.
Collapse
Affiliation(s)
- Yang Guo
- Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China
- Department of Neurosurgery, The Henan Provincial People's Hospital, Zhengzhou, Henan, China
| | - Zeyu Ma
- Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China
| | - Dongling Pei
- Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China
| | - Wenchao Duan
- Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China
| | - Yu Guo
- Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China
| | - Zhongyi Liu
- Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China
| | - Fangzhan Guan
- Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China
| | - Zilong Wang
- Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China
| | - Aoqi Xing
- Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China
| | - Zhixuan Guo
- Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China
| | - Lin Luo
- Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China
| | - Weiwei Wang
- Department of Pathology, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China
| | - Bin Yu
- Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China
| | - Jinqiao Zhou
- Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China
| | - Yuchen Ji
- Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China
| | - Dongming Yan
- Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China
| | - Jingliang Cheng
- Department of MRI, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China
| | - Xianzhi Liu
- Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China
| | - Jing Yan
- Department of MRI, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China
| | - Zhenyu Zhang
- Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China
| |
Collapse
|
50
|
Wu Z, Yang Y, Zha Y. Radiomics Features on Magnetic Resonance Images Can Predict C5aR1 Expression Levels and Prognosis in High-Grade Glioma. Cancers (Basel) 2023; 15:4661. [PMID: 37760630 PMCID: PMC10527364 DOI: 10.3390/cancers15184661] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/15/2023] [Revised: 09/16/2023] [Accepted: 09/18/2023] [Indexed: 09/29/2023] Open
Abstract
BACKGROUND The complement component C5a receptor 1 (C5aR1) regulates cancer immunity. This retrospective study aimed to assess its prognostic value in high-grade glioma (HGG) and predict C5aR1 expression using a radiomics approach. METHODS Among 298 patients with HGG, 182 with MRI data were randomly divided into training and test groups for radiomics analysis. We examined the association between C5aR1 expression and prognosis through Kaplan-Meier and Cox regression analyses. We used maximum relevance-minimum redundancy and recursive feature elimination algorithms for radiomics feature selection. We then built a support vector machine (SVM) and a logistic regression model, investigating their performances using receiver operating characteristic, calibration curves, and decision curves. RESULTS C5aR1 expression was elevated in HGG and was an independent prognostic factor (hazard ratio = 3.984, 95% CI: 2.834-5.607). Both models presented with >0.8 area under the curve values in the training and test datasets, indicating efficient discriminatory ability, with SVM performing marginally better. The radiomics score calculated using the SVM model correlated significantly with overall survival (p < 0.01). CONCLUSIONS Our results highlight C5aR1's role in HGG development and prognosis, supporting its potential as a prognostic biomarker. Our radiomics model can noninvasively and effectively predict C5aR1 expression and patient prognosis in HGG.
Collapse
Affiliation(s)
| | | | - Yunfei Zha
- Department of Radiology, Renmin Hospital of Wuhan University, Wuhan 430000, China; (Z.W.); (Y.Y.)
| |
Collapse
|