1
|
Scapicchio C, Imbriani M, Lizzi F, Quattrocchi M, Retico A, Saponaro S, Tenerani MI, Tofani A, Zafaranchi A, Fantacci ME. Investigation of a potential upstream harmonization based on image appearance matching to improve radiomics features robustness: a phantom study. Biomed Phys Eng Express 2024; 10:045006. [PMID: 38653209 DOI: 10.1088/2057-1976/ad41e7] [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: 10/27/2023] [Accepted: 04/23/2024] [Indexed: 04/25/2024]
Abstract
Objective. Radiomics is a promising valuable analysis tool consisting in extracting quantitative information from medical images. However, the extracted radiomics features are too sensitive to variations in used image acquisition and reconstruction parameters. This limited robustness hinders the generalizable validity of radiomics-assisted models. Our aim is to investigate a possible harmonization strategy based on matching image quality to improve feature robustness.Approach.We acquired CT scans of a phantom with two scanners across different dose levels and percentages of Iterative Reconstruction algorithms. The detectability index was used as a comprehensive task-based image quality metric. A statistical analysis based on the Intraclass Correlation Coefficient was performed to determine if matching image quality/appearance could enhance the robustness of radiomics features extracted from the phantom images. Additionally, an Artificial Neural Network was trained on these features to automatically classify the scanner used for image acquisition.Main results.We found that the ICC of the features across protocols providing a similar detectability index improves with respect to the ICC of the features across protocols providing a different detectability index. This improvement was particularly noticeable in features relevant for distinguishing between scanners.Significance.This preliminary study demonstrates that a harmonization based on image quality/appearance matching could improve radiomics features robustness and heterogeneous protocols can be used to obtain a similar image appearance in terms of the detectability index. Thus protocols with a lower dose level could be selected to reduce the amount of radiation dose delivered to the patient and simultaneously obtain a more robust quantitative analysis.
Collapse
Affiliation(s)
- Camilla Scapicchio
- Department of Physics, University of Pisa, Pisa, Italy
- National Institute for Nuclear Physics, Pisa Division, Italy
| | | | - Francesca Lizzi
- National Institute for Nuclear Physics, Pisa Division, Italy
| | | | | | - Sara Saponaro
- National Institute for Nuclear Physics, Pisa Division, Italy
| | - Maria Irene Tenerani
- Department of Physics, University of Pisa, Pisa, Italy
- National Institute for Nuclear Physics, Pisa Division, Italy
| | - Alessandro Tofani
- Medical Physics Department, Azienda Toscana Nord Ovest Area Nord, Lucca, Italy
| | - Arman Zafaranchi
- Department of Physics, University of Pisa, Pisa, Italy
- National Institute for Nuclear Physics, Pisa Division, Italy
- Department of Computer Science, University of Pisa, Pisa, Italy
| | - Maria Evelina Fantacci
- Department of Physics, University of Pisa, Pisa, Italy
- National Institute for Nuclear Physics, Pisa Division, Italy
| |
Collapse
|
2
|
Huang YC, Huang SM, Yeh JH, Chang TC, Tsan DL, Lin CY, Tu SJ. Utility of CT Radiomics and Delta Radiomics for Survival Evaluation in Locally Advanced Nasopharyngeal Carcinoma with Concurrent Chemoradiotherapy. Diagnostics (Basel) 2024; 14:941. [PMID: 38732355 PMCID: PMC11083477 DOI: 10.3390/diagnostics14090941] [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: 02/08/2024] [Revised: 04/23/2024] [Accepted: 04/26/2024] [Indexed: 05/13/2024] Open
Abstract
BACKGROUND A high incidence rate of nasopharyngeal carcinoma (NPC) has been observed in Southeast Asia compared to other parts of the world. Radiomics is a computational tool to predict outcomes and may be used as a prognostic biomarker for advanced NPC treated with concurrent chemoradiotherapy. Recently, radiomic analysis of the peripheral tumor microenvironment (TME), which is the region surrounding the gross tumor volume (GTV), has shown prognostic usefulness. In this study, not only was gross tumor volume (GTVt) analyzed but also tumor peripheral regions (GTVp) were explored in terms of the TME concept. Both radiomic features and delta radiomic features were analyzed using CT images acquired in a routine radiotherapy process. METHODS A total of 50 patients with NPC stages III, IVA, and IVB were enrolled between September 2004 and February 2014. Survival models were built using Cox regression with clinical factors (i.e., gender, age, overall stage, T stage, N stage, and treatment dose) and radiomic features. Radiomic features were extracted from GTVt and GTVp. GTVp was created surrounding GTVt for TME consideration. Furthermore, delta radiomics, which is the longitudinal change in quantitative radiomic features, was utilized for analysis. Finally, C-index values were computed using leave-one-out cross-validation (LOOCV) to evaluate the performances of all prognosis models. RESULTS Models were built for three different clinical outcomes, including overall survival (OS), local recurrence-free survival (LRFS), and progression-free survival (PFS). The range of the C-index in clinical factor models was (0.622, 0.729). All radiomics models, including delta radiomics models, were in the range of (0.718, 0.872). Among delta radiomics models, GTVt and GTVp were in the range of (0.833, 0.872) and (0.799, 0.834), respectively. CONCLUSIONS Radiomic analysis on the proximal region surrounding the gross tumor volume of advanced NPC patients for survival outcome evaluation was investigated, and preliminary positive results were obtained. Radiomic models and delta radiomic models demonstrated performance that was either superior to or comparable with that of conventional clinical models.
Collapse
Affiliation(s)
- Yen-Cho Huang
- Department of Radiation Oncology, Keelung Chang Gung Memorial Hospital, Keelung 20445, Taiwan; (Y.-C.H.); (S.-M.H.); (J.-H.Y.)
- Department of Medical Imaging and Radiological Sciences, College of Medicine, Chang Gung University, Tao-Yuan 33302, Taiwan
| | - Shih-Ming Huang
- Department of Radiation Oncology, Keelung Chang Gung Memorial Hospital, Keelung 20445, Taiwan; (Y.-C.H.); (S.-M.H.); (J.-H.Y.)
| | - Jih-Hsiang Yeh
- Department of Radiation Oncology, Keelung Chang Gung Memorial Hospital, Keelung 20445, Taiwan; (Y.-C.H.); (S.-M.H.); (J.-H.Y.)
| | - Tung-Chieh Chang
- Department of Radiation Oncology, Linkuo Chang Gung Memorial Hospital, Tao-Yuan 33305, Taiwan; (T.-C.C.); (D.-L.T.)
| | - Din-Li Tsan
- Department of Radiation Oncology, Linkuo Chang Gung Memorial Hospital, Tao-Yuan 33305, Taiwan; (T.-C.C.); (D.-L.T.)
| | - Chien-Yu Lin
- Department of Medical Imaging and Radiological Sciences, College of Medicine, Chang Gung University, Tao-Yuan 33302, Taiwan
- Department of Radiation Oncology, Linkuo Chang Gung Memorial Hospital, Tao-Yuan 33305, Taiwan; (T.-C.C.); (D.-L.T.)
- Particle Physics and Beam Delivery Core Laboratory, Linkou Chang Gung Memorial Hospital, Tao-Yuan 33305, Taiwan
| | - Shu-Ju Tu
- Department of Medical Imaging and Radiological Sciences, College of Medicine, Chang Gung University, Tao-Yuan 33302, Taiwan
- Department of Medical Imaging and Intervention, Linkou Chang Gung Memorial Hospital, Tao-Yuan 33305, Taiwan
- Department of Nuclear Medicine, Linkou Chang Gung Memorial Hospital, Tao-Yuan 33305, Taiwan
| |
Collapse
|
3
|
Samartha MVS, Dubey NK, Jena B, Maheswar G, Lo WC, Saxena S. AI-driven estimation of O6 methylguanine-DNA-methyltransferase (MGMT) promoter methylation in glioblastoma patients: a systematic review with bias analysis. J Cancer Res Clin Oncol 2024; 150:57. [PMID: 38291266 PMCID: PMC10827977 DOI: 10.1007/s00432-023-05566-5] [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: 07/07/2023] [Accepted: 11/27/2023] [Indexed: 02/01/2024]
Abstract
BACKGROUND Accurate and non-invasive estimation of MGMT promoter methylation status in glioblastoma (GBM) patients is of paramount clinical importance, as it is a predictive biomarker associated with improved overall survival (OS). In response to the clinical need, recent studies have focused on the development of non-invasive artificial intelligence (AI)-based methods for MGMT estimation. In this systematic review, we not only delve into the technical aspects of these AI-driven MGMT estimation methods but also emphasize their profound clinical implications. Specifically, we explore the potential impact of accurate non-invasive MGMT estimation on GBM patient care and treatment decisions. METHODS Employing a PRISMA search strategy, we identified 33 relevant studies from reputable databases, including PubMed, ScienceDirect, Google Scholar, and IEEE Explore. These studies were comprehensively assessed using 21 diverse attributes, encompassing factors such as types of imaging modalities, machine learning (ML) methods, and cohort sizes, with clear rationales for attribute scoring. Subsequently, we ranked these studies and established a cutoff value to categorize them into low-bias and high-bias groups. RESULTS By analyzing the 'cumulative plot of mean score' and the 'frequency plot curve' of the studies, we determined a cutoff value of 6.00. A higher mean score indicated a lower risk of bias, with studies scoring above the cutoff mark categorized as low-bias (73%), while 27% fell into the high-bias category. CONCLUSION Our findings underscore the immense potential of AI-based machine learning (ML) and deep learning (DL) methods in non-invasively determining MGMT promoter methylation status. Importantly, the clinical significance of these AI-driven advancements lies in their capacity to transform GBM patient care by providing accurate and timely information for treatment decisions. However, the translation of these technical advancements into clinical practice presents challenges, including the need for large multi-institutional cohorts and the integration of diverse data types. Addressing these challenges will be critical in realizing the full potential of AI in improving the reliability and accessibility of MGMT estimation while lowering the risk of bias in clinical decision-making.
Collapse
Affiliation(s)
- Mullapudi Venkata Sai Samartha
- Department of Computer Science & Engineering, International Institute of Information Technology, Bhubaneswar, 751003, India
| | - Navneet Kumar Dubey
- Victory Biotechnology Co., Ltd., Taipei, 114757, Taiwan
- Executive Programme in Healthcare Management, Indian Institute of Management, Lucknow, 226013, India
| | - Biswajit Jena
- Institute of Technical Education and Research, SOA Deemed to be University, Bhubaneswar, 751030, India
| | - Gorantla Maheswar
- Department of Computer Science & Engineering, International Institute of Information Technology, Bhubaneswar, 751003, India
| | - Wen-Cheng Lo
- Division of Neurosurgery, Department of Surgery, School of Medicine, College of Medicine, Taipei Medical University, Taipei, 11031, Taiwan.
- Department of Neurosurgery, Taipei Medical University Hospital, Taipei, 11031, Taiwan.
- Taipei Neuroscience Institute, Taipei Medical University, Taipei, 11031, Taiwan.
| | - Sanjay Saxena
- Department of Computer Science & Engineering, International Institute of Information Technology, Bhubaneswar, 751003, India.
| |
Collapse
|
4
|
Gu X, Shu Z, Zheng X, Wei S, Ma M, He H, Shi Y, Gong X, Chen S, Wang X. A novel CT-responsive hydrogel for the construction of an organ simulation phantom for the repeatability and stability study of radiomic features. J Mater Chem B 2023; 11:11073-11081. [PMID: 37986572 DOI: 10.1039/d3tb01706k] [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: 11/22/2023]
Abstract
Radiomic features have demonstrated reliable outcomes in tumor grading and detecting precancerous lesions in medical imaging analysis. However, the repeatability and stability of these features have faced criticism. In this study, we aim to enhance the repeatability and stability of radiomic features by introducing a novel CT-responsive hydrogel material. The newly developed CT-responsive hydrogel, mineralized by in situ metal ions, exhibits exceptional repeatability, stability, and uniformity. Moreover, by adjusting the concentration of metal ions, it achieves remarkable CT similarity comparable to that of human organs on CT scans. To create a phantom, the hydrogel was molded into a universal model, displaying controllable CT values ranging from 53 HU to 58 HU, akin to human liver tissue. Subsequently, 1218 radiomic features were extracted from the CT-responsive hydrogel organ simulation phantom. Impressively, 85-97.2% of the extracted features exhibited good repeatability and stability during coefficient of variability analysis. This finding emphasizes the potential of CT-responsive hydrogel in consistently extracting the same features, providing a novel approach to address the issue of repeatability in radiomic features.
Collapse
Affiliation(s)
- Xiaokai Gu
- College of Materials Science and Engineering, Zhejiang University of Technology, Hangzhou 310014, P. R. China.
- Department of Radiology, Zhejiang Provincial People's Hospital, Hangzhou 310014, P. R. China.
| | - Zhenyu Shu
- Department of Radiology, Zhejiang Provincial People's Hospital, Hangzhou 310014, P. R. China.
| | - Xiaoli Zheng
- Department of Radiology, Zhejiang Provincial People's Hospital, Hangzhou 310014, P. R. China.
| | - Sailong Wei
- College of Materials Science and Engineering, Zhejiang University of Technology, Hangzhou 310014, P. R. China.
| | - Meng Ma
- College of Materials Science and Engineering, Zhejiang University of Technology, Hangzhou 310014, P. R. China.
| | - Huiwen He
- College of Materials Science and Engineering, Zhejiang University of Technology, Hangzhou 310014, P. R. China.
| | - Yanqin Shi
- College of Materials Science and Engineering, Zhejiang University of Technology, Hangzhou 310014, P. R. China.
| | - Xiangyang Gong
- Department of Radiology, Zhejiang Provincial People's Hospital, Hangzhou 310014, P. R. China.
| | - Si Chen
- College of Materials Science and Engineering, Zhejiang University of Technology, Hangzhou 310014, P. R. China.
| | - Xu Wang
- College of Materials Science and Engineering, Zhejiang University of Technology, Hangzhou 310014, P. R. China.
| |
Collapse
|
5
|
Higgins H, Nakhla A, Lotfalla A, Khalil D, Doshi P, Thakkar V, Shirini D, Bebawy M, Ammari S, Lopci E, Schwartz LH, Postow M, Dercle L. Recent Advances in the Field of Artificial Intelligence for Precision Medicine in Patients with a Diagnosis of Metastatic Cutaneous Melanoma. Diagnostics (Basel) 2023; 13:3483. [PMID: 37998619 PMCID: PMC10670510 DOI: 10.3390/diagnostics13223483] [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: 09/20/2023] [Revised: 10/27/2023] [Accepted: 10/31/2023] [Indexed: 11/25/2023] Open
Abstract
Standard-of-care medical imaging techniques such as CT, MRI, and PET play a critical role in managing patients diagnosed with metastatic cutaneous melanoma. Advancements in artificial intelligence (AI) techniques, such as radiomics, machine learning, and deep learning, could revolutionize the use of medical imaging by enhancing individualized image-guided precision medicine approaches. In the present article, we will decipher how AI/radiomics could mine information from medical images, such as tumor volume, heterogeneity, and shape, to provide insights into cancer biology that can be leveraged by clinicians to improve patient care both in the clinic and in clinical trials. More specifically, we will detail the potential role of AI in enhancing detection/diagnosis, staging, treatment planning, treatment delivery, response assessment, treatment toxicity assessment, and monitoring of patients diagnosed with metastatic cutaneous melanoma. Finally, we will explore how these proof-of-concept results can be translated from bench to bedside by describing how the implementation of AI techniques can be standardized for routine adoption in clinical settings worldwide to predict outcomes with great accuracy, reproducibility, and generalizability in patients diagnosed with metastatic cutaneous melanoma.
Collapse
Affiliation(s)
- Hayley Higgins
- Department of Clinical Medicine, Touro College of Osteopathic Medicine, Middletown, NY 10940, USA; (A.L.); (M.B.)
| | - Abanoub Nakhla
- Department of Clinical Medicine, American University of the Caribbean School of Medicine, 33027 Cupecoy, Sint Maarten, The Netherlands;
| | - Andrew Lotfalla
- Department of Clinical Medicine, Touro College of Osteopathic Medicine, Middletown, NY 10940, USA; (A.L.); (M.B.)
| | - David Khalil
- Department of Clinical Medicine, Campbell University School of Osteopathic Medicine, Lillington, NC 27546, USA; (D.K.); (P.D.); (V.T.)
| | - Parth Doshi
- Department of Clinical Medicine, Campbell University School of Osteopathic Medicine, Lillington, NC 27546, USA; (D.K.); (P.D.); (V.T.)
| | - Vandan Thakkar
- Department of Clinical Medicine, Campbell University School of Osteopathic Medicine, Lillington, NC 27546, USA; (D.K.); (P.D.); (V.T.)
| | - Dorsa Shirini
- Department of Radiology, Shahid Beheshti University of Medical Sciences, Tehran 1981619573, Iran;
| | - Maria Bebawy
- Department of Clinical Medicine, Touro College of Osteopathic Medicine, Middletown, NY 10940, USA; (A.L.); (M.B.)
| | - Samy Ammari
- Département d’Imagerie Médicale Biomaps, UMR1281 INSERM, CEA, CNRS, Gustave Roussy, Université Paris-Saclay, 94800 Villejuif, France;
- ELSAN Département de Radiologie, Institut de Cancérologie Paris Nord, 95200 Sarcelles, France
| | - Egesta Lopci
- Nuclear Medicine Unit, IRCCS Humanitas Research Hospital, 20089 Rozzano, Italy;
| | - Lawrence H. Schwartz
- Department of Radiology, New York-Presbyterian, Columbia University Irving Medical Center, New York, NY 10032, USA;
| | - Michael Postow
- Melanoma Service, Department of Medicine, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA
- Weill Cornell Medical College, New York, NY 10065, USA
| | - Laurent Dercle
- Department of Radiology, Shahid Beheshti University of Medical Sciences, Tehran 1981619573, Iran;
| |
Collapse
|
6
|
Wang Y, Zhu J, Lu X, Cheng W, Xu L, Wang X, Wang J, Yang J, Niu F, Chen W, Sun X, Li W, Wen Z, Guan H, Yan F. Development and validation of radiomics nomograms for preoperative prediction of characteristics in non-small cell lung cancer and circulating tumor cells. Medicine (Baltimore) 2023; 102:e35830. [PMID: 37932991 PMCID: PMC10627624 DOI: 10.1097/md.0000000000035830] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/31/2023] [Accepted: 10/06/2023] [Indexed: 11/08/2023] Open
Abstract
To develop and validate 3 radiomics nomograms for preoperative prediction of pathological and progression diagnosis in non-small cell lung cancer (NSCLC) as well as circulating tumor cells (CTCs). A total of 224 and 134 patients diagnosed with NSCLC were respectively gathered in 2018 and 2019 in this study. There were totally 1197 radiomics features that were extracted and quantified from the images produced by computed tomography. Then we selected the radiomics features with predictive value by least absolute shrinkage and selection operator and combined them into radiomics signature. Logistic regression models were built using radiomics signature as the only predictor, which were then converted to nomograms for individualized predictions. Finally, the performance of the nomograms was assessed on both cohorts. Additionally, immunohistochemical correlation analysis was also performed. As for discrimination, the area under the curve of pathological diagnosis nomogram and progression diagnosis nomogram in NSCLC were both higher than 90% in the training cohort and higher than 80% in the validation cohort. The performance of the CTC-diagnosis nomogram was somehow unexpected where the area under the curve were range from 60% to 70% in both cohorts. As for calibration, nonsignificant statistics (P > .05) yielded by Hosmer-Lemeshow tests suggested no departure between model prediction and perfect fit. Additionally, decision curve analyses demonstrated the clinically usefulness of the nomograms. We developed radiomics-based nomograms for pathological, progression and CTC diagnosis prediction in NSCLC respectively. Nomograms for pathological and progression diagnosis were demonstrated well-performed to facilitate the individualized preoperative prediction, while the nomogram for CTC-diagnosis prediction needed improvement.
Collapse
Affiliation(s)
- Yang Wang
- Department of Radiology, Zhujiang Hospital, Southern Medical University, Haizhu District, Guangzhou, Guangdong, P.R. China
| | - Junkai Zhu
- State Key Laboratory of Natural Medicines, Research Center of Biostatistics and Computational Pharmacy, China Pharmaceutical University, Nanjing, P.R. China
| | - Xiaofan Lu
- State Key Laboratory of Natural Medicines, Research Center of Biostatistics and Computational Pharmacy, China Pharmaceutical University, Nanjing, P.R. China
| | - Wenxuan Cheng
- State Key Laboratory of Natural Medicines, Research Center of Biostatistics and Computational Pharmacy, China Pharmaceutical University, Nanjing, P.R. China
| | - Li Xu
- State Key Laboratory of Natural Medicines, Research Center of Biostatistics and Computational Pharmacy, China Pharmaceutical University, Nanjing, P.R. China
| | - Xin Wang
- State Key Laboratory of Natural Medicines, Research Center of Biostatistics and Computational Pharmacy, China Pharmaceutical University, Nanjing, P.R. China
| | - Jian Wang
- Department of Radiology, Zhujiang Hospital, Southern Medical University, Haizhu District, Guangzhou, Guangdong, P.R. China
| | - Jun Yang
- Department of Pathology, Nanjing Drum Tower Hospital, Nanjing, P.R. China
| | - Fengnan Niu
- Department of Pathology, Nanjing Drum Tower Hospital, Nanjing, P.R. China
| | - Wenping Chen
- Department of Radiology, Nanjing Drum Tower Hospital, The Affiliated Hospital of Nanjing University Medical School, Nanjing, P.R. China
| | - Xu Sun
- Université Paris Cité, Paris, France
| | - Wenyi Li
- Suzhou Science & Technology Town Hospital, Suzhou, P.R. China
| | - Zhibo Wen
- Department of Radiology, Zhujiang Hospital, Southern Medical University, Haizhu District, Guangzhou, Guangdong, P.R. China
| | - Haitao Guan
- Department of Endocrinology, Tongren Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, P.R. China
| | - Fangrong Yan
- State Key Laboratory of Natural Medicines, Research Center of Biostatistics and Computational Pharmacy, China Pharmaceutical University, Nanjing, P.R. China
| |
Collapse
|
7
|
Canahuate G, Wentzel A, Mohamed ASR, van Dijk LV, Vock DM, Elgohari B, Elhalawani H, Fuller CD, Marai GE. Spatially-aware clustering improves AJCC-8 risk stratification performance in oropharyngeal carcinomas. Oral Oncol 2023; 144:106460. [PMID: 37390759 PMCID: PMC10561377 DOI: 10.1016/j.oraloncology.2023.106460] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/08/2021] [Revised: 05/26/2023] [Accepted: 06/05/2023] [Indexed: 07/02/2023]
Abstract
OBJECTIVE Evaluate the effectiveness of machine learning tools that incorporate spatial information such as disease location and lymph node metastatic patterns-of-spread, for prediction of survival and toxicity in HPV+ oropharyngeal cancer (OPC). MATERIALS & METHODS 675 HPV+ OPC patients that were treated at MD Anderson Cancer Center between 2005 and 2013 with curative intent IMRT were retrospectively collected under IRB approval. Risk stratifications incorporating patient radiometric data and lymph node metastasis patterns via an anatomically-adjacent representation with hierarchical clustering were identified. These clusterings were combined into a 3-level patient stratification and included along with other known clinical features in a Cox model for predicting survival outcomes, and logistic regression for toxicity, using independent subsets for training and validation. RESULTS Four groups were identified and combined into a 3-level stratification. The inclusion of patient stratifications in predictive models for 5-yr Overall survival (OS), 5-year recurrence free survival, (RFS) and Radiation-associated dysphagia (RAD) consistently improved model performance measured using the area under the curve (AUC). Test set AUC improvements over models with clinical covariates, was 9 % for predicting OS, and 18 % for predicting RFS, and 7 % for predicting RAD. For models with both clinical and AJCC covariates, AUC improvement was 7 %, 9 %, and 2 % for OS, RFS, and RAD, respectively. CONCLUSION Including data-driven patient stratifications considerably improve prognosis for survival and toxicity outcomes over the performance achieved by clinical staging and clinical covariates alone. These stratifications generalize well to across cohorts, and sufficient information for reproducing these clusters is included.
Collapse
Affiliation(s)
- Guadalupe Canahuate
- Department of Electrical and Computer Engineering, University of Iowa, Iowa City, IA 52242, USA.
| | - Andrew Wentzel
- Department of Computer Science, The University of Illinois at Chicago, Chicago, IL 60612, USA
| | - Abdallah S R Mohamed
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
| | - Lisanne V van Dijk
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
| | - David M Vock
- Division of Biostatistics, University of Minnesota, Minneapolis, MN 55455, USA
| | - Baher Elgohari
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
| | - Hesham Elhalawani
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
| | - Clifton D Fuller
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
| | - G Elisabeta Marai
- Department of Computer Science, The University of Illinois at Chicago, Chicago, IL 60612, USA
| |
Collapse
|
8
|
Davey A, Thor M, van Herk M, Faivre-Finn C, Rimner A, Deasy JO, McWilliam A. Predicting cancer relapse following lung stereotactic radiotherapy: an external validation study using real-world evidence. Front Oncol 2023; 13:1156389. [PMID: 37503315 PMCID: PMC10369005 DOI: 10.3389/fonc.2023.1156389] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/01/2023] [Accepted: 06/27/2023] [Indexed: 07/29/2023] Open
Abstract
Purpose For patients receiving lung stereotactic ablative radiotherapy (SABR), evidence suggests that high peritumor density predicts an increased risk of microscopic disease (MDE) and local-regional failure, but only if there is low or heterogenous incidental dose surrounding the tumor (GTV). A data-mining method (Cox-per-radius) has been developed to investigate this dose-density interaction. We apply the method to predict local relapse (LR) and regional failure (RF) in patients with non-small cell lung cancer. Methods 199 patients treated in a routine setting were collated from a single institution for training, and 76 patients from an external institution for validation. Three density metrics (mean, 90th percentile, standard deviation (SD)) were studied in 1mm annuli between 0.5cm inside and 2cm outside the GTV boundary. Dose SD and fraction of volume receiving less than 30Gy were studied in annuli 0.5-2cm outside the GTV to describe incidental MDE dosage. Heat-maps were created that correlate with changes in LR and RF rates due to the interaction between dose heterogeneity and density at each distance combination. Regions of significant improvement were studied in Cox proportional hazards models, and explored with and without re-fitting in external data. Correlations between the dose component of the interaction and common dose metrics were reported. Results Local relapse occurred at a rate of 6.5% in the training cohort, and 18% in the validation cohort, which included larger and more centrally located tumors. High peritumor density in combination with high dose variability (0.5 - 1.6cm) predicts LR. No interactions predicted RF. The LR interaction improved the predictive ability compared to using clinical variables alone (optimism-adjusted C-index; 0.82 vs 0.76). Re-fitting model coefficients in external data confirmed the importance of this interaction (C-index; 0.86 vs 0.76). Dose variability in the 0.5-1.6 cm annular region strongly correlates with heterogeneity inside the target volume (SD; ρ = 0.53 training, ρ = 0.65 validation). Conclusion In these real-world cohorts, the combination of relatively high peritumor density and high dose variability predicts increase in LR, but not RF, following lung SABR. This external validation justifies potential use of the model to increase low-dose CTV margins for high-risk patients.
Collapse
Affiliation(s)
- Angela Davey
- Division of Cancer Sciences, School of Medical Sciences, Faculty of Biology, Medicine and Health, The University of Manchester, Manchester, United Kingdom
| | - Maria Thor
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY, United States
| | - Marcel van Herk
- Division of Cancer Sciences, School of Medical Sciences, Faculty of Biology, Medicine and Health, The University of Manchester, Manchester, United Kingdom
| | - Corinne Faivre-Finn
- Division of Cancer Sciences, School of Medical Sciences, Faculty of Biology, Medicine and Health, The University of Manchester, Manchester, United Kingdom
- Department of Clinical Oncology, The Christie NHS Foundation Trust, Manchester, United Kingdom
| | - Andreas Rimner
- Department of Radiation Oncology, Memorial Sloan Kettering Cancer Center, New York, NY, United States
| | - Joseph O. Deasy
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY, United States
| | - Alan McWilliam
- Division of Cancer Sciences, School of Medical Sciences, Faculty of Biology, Medicine and Health, The University of Manchester, Manchester, United Kingdom
| |
Collapse
|
9
|
Ger RB, Wei L, Naqa IE, Wang J. The Promise and Future of Radiomics for Personalized Radiotherapy Dosing and Adaptation. Semin Radiat Oncol 2023; 33:252-261. [PMID: 37331780 PMCID: PMC11214660 DOI: 10.1016/j.semradonc.2023.03.003] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 06/20/2023]
Abstract
Quantitative image analysis, also known as radiomics, aims to analyze large-scale quantitative features extracted from acquired medical images using hand-crafted or machine-engineered feature extraction approaches. Radiomics has great potential for a variety of clinical applications in radiation oncology, an image-rich treatment modality that utilizes computed tomography (CT), magnetic resonance imaging (MRI), and positron emission tomography (PET) for treatment planning, dose calculation, and image guidance. A promising application of radiomics is in predicting treatment outcomes after radiotherapy such as local control and treatment-related toxicity using features extracted from pretreatment and on-treatment images. Based on these individualized predictions of treatment outcomes, radiotherapy dose can be sculpted to meet the specific needs and preferences of each patient. Radiomics can aid in tumor characterization for personalized targeting, especially for identifying high-risk regions within a tumor that cannot be easily discerned based on size or intensity alone. Radiomics-based treatment response prediction can aid in developing personalized fractionation and dose adjustments. In order to make radiomics models more applicable across different institutions with varying scanners and patient populations, further efforts are needed to harmonize and standardize the acquisition protocols by minimizing uncertainties within the imaging data.
Collapse
Affiliation(s)
- Rachel B Ger
- Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins Medicine, Baltimore, MD
| | - Lise Wei
- Department of Radiation Oncology, University of Michigan, Ann Arbor, MI
| | - Issam El Naqa
- Department of Machine Learning, Moffitt Cancer Center and Research Institute, Tampa, FL
| | - Jing Wang
- Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, TX..
| |
Collapse
|
10
|
Zhong J, Pan Z, Chen Y, Wang L, Xia Y, Wang L, Li J, Lu W, Shi X, Feng J, Yan F, Zhang H, Yao W. Robustness of radiomics features of virtual unenhanced and virtual monoenergetic images in dual-energy CT among different imaging platforms and potential role of CT number variability. Insights Imaging 2023; 14:79. [PMID: 37166511 PMCID: PMC10175529 DOI: 10.1186/s13244-023-01426-5] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/18/2023] [Accepted: 04/05/2023] [Indexed: 05/12/2023] Open
Abstract
OBJECTIVES To evaluate robustness of dual-energy CT (DECT) radiomics features of virtual unenhanced (VUE) image and virtual monoenergetic image (VMI) among different imaging platforms. METHODS A phantom with sixteen clinical-relevant densities was scanned on ten DECT platforms with comparable scan parameters. Ninety-four radiomic features were extracted via Pyradiomics from VUE images and VMIs at energy level of 70 keV (VMI70keV). Test-retest repeatability was assessed by Bland-Altman analysis. Inter-platform reproducibility of VUE images and VMI70keV was evaluated by coefficient of variation (CV) and quartile coefficient of dispersion (QCD) among platforms, and by intraclass correlation coefficient (ICC) and concordance correlation coefficient (CCC) between platform pairs. The correlation between variability of CT number radiomics reproducibility was estimated. RESULTS 92.02% and 92.87% of features were repeatable between scan-rescans for VUE images and VMI70keV, respectively. Among platforms, 11.30% and 28.39% features of VUE images, and 15.16% and 28.99% features of VMI70keV were with CV < 10% and QCD < 10%. The average percentages of radiomics features with ICC > 0.90 and CCC > 0.90 between platform pairs were 10.00% and 9.86% in VUE images and 11.23% and 11.23% in VMI70keV. The CT number inter-platform reproducibility using CV and QCD showed negative correlations with percentage of the first-order radiomics features with CV < 10% and QCD < 10%, in both VUE images and VMI70keV (r2 0.3870-0.6178, all p < 0.001). CONCLUSIONS The majority of DECT radiomics features were non-reproducible. The differences in CT number were considered as an indicator of inter-platform DECT radiomics variation. Critical relevance statement: The majority of radiomics features extracted from the VUE images and the VMI70keV were non-reproducible among platforms, while synchronizing energy levels of VMI to reduce the CT number value variability may be a potential way to mitigate radiomics instability.
Collapse
Affiliation(s)
- Jingyu Zhong
- Department of Imaging, Tongren Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200336, China
| | - Zilai Pan
- Department of Radiology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200025, China
| | - Yong Chen
- Department of Radiology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200025, China
| | - Lingyun Wang
- Department of Radiology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200025, China
| | - Yihan Xia
- Department of Radiology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200025, China
| | - Lan Wang
- Department of Radiology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200025, China
| | - Jianying Li
- Computed Tomography Research Center, GE Healthcare, Beijing, 100176, China
| | - Wei Lu
- Computed Tomography Research Center, GE Healthcare, Shanghai, 201203, China
| | - Xiaomeng Shi
- Department of Materials, Imperial College London, London, SW7 2AZ, UK
| | - Jianxing Feng
- Haohua Technology Co., Ltd., Shanghai, 201100, China
| | - Fuhua Yan
- Department of Radiology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200025, China
| | - Huan Zhang
- Department of Radiology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200025, China.
| | - Weiwu Yao
- Department of Imaging, Tongren Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200336, China.
| |
Collapse
|
11
|
Kiser K, Zhang J, Kim SG. Textural Features of Mouse Glioma Models Measured by Dynamic Contrast-Enhanced MR Images with 3D Isotropic Resolution. Tomography 2023; 9:721-735. [PMID: 37104129 PMCID: PMC10141208 DOI: 10.3390/tomography9020058] [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: 02/04/2023] [Revised: 03/20/2023] [Accepted: 03/23/2023] [Indexed: 04/28/2023] Open
Abstract
This paper investigates the effect of anisotropic resolution on the image textural features of pharmacokinetic (PK) parameters of a murine glioma model using dynamic contrast-enhanced (DCE) MR images acquired with an isotropic resolution at 7T with pre-contrast T1 mapping. The PK parameter maps of whole tumors at isotropic resolution were generated using the two-compartment exchange model combined with the three-site-two-exchange model. The textural features of these isotropic images were compared with those of simulated, thick-slice, anisotropic images to assess the influence of anisotropic voxel resolution on the textural features of tumors. The isotropic images and parameter maps captured distributions of high pixel intensity that were absent in the corresponding anisotropic images with thick slices. A significant difference was observed in 33% of the histogram and textural features extracted from anisotropic images and parameter maps, compared to those extracted from corresponding isotropic images. Anisotropic images in different orthogonal orientations demonstrated 42.1% of the histogram and textural features to be significantly different from those of isotropic images. This study demonstrates that the anisotropy of voxel resolution needs to be carefully considered when comparing the textual features of tumor PK parameters and contrast-enhanced images.
Collapse
Affiliation(s)
- Karl Kiser
- Department of Radiology, Weill Cornell Medical College, New York, NY 10065, USA
| | | | | |
Collapse
|
12
|
Shoemaker K, Ger R, Court LE, Aerts H, Vannucci M, Peterson CB. Bayesian feature selection for radiomics using reliability metrics. Front Genet 2023; 14:1112914. [PMID: 36968604 PMCID: PMC10030957 DOI: 10.3389/fgene.2023.1112914] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/30/2022] [Accepted: 02/23/2023] [Indexed: 03/10/2023] Open
Abstract
Introduction: Imaging of tumors is a standard step in diagnosing cancer and making subsequent treatment decisions. The field of radiomics aims to develop imaging based biomarkers using methods rooted in artificial intelligence applied to medical imaging. However, a challenging aspect of developing predictive models for clinical use is that many quantitative features derived from image data exhibit instability or lack of reproducibility across different imaging systems or image-processing pipelines.Methods: To address this challenge, we propose a Bayesian sparse modeling approach for image classification based on radiomic features, where the inclusion of more reliable features is favored via a probit prior formulation.Results: We verify through simulation studies that this approach can improve feature selection and prediction given correct prior information. Finally, we illustrate the method with an application to the classification of head and neck cancer patients by human papillomavirus status, using as our prior information a reliability metric quantifying feature stability across different imaging systems.
Collapse
Affiliation(s)
- Katherine Shoemaker
- Department of Mathematics and Statistics, University of Houston-Downtown, Houston, TX, United States
- *Correspondence: Katherine Shoemaker,
| | - Rachel Ger
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University School of Medicine, Baltimore, MD, United States
| | - Laurence E. Court
- Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, United States
| | - Hugo Aerts
- Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, MA, United States
- Department of Radiation Oncology, Brigham and Women’s Hospital, Harvard Medical School, Dana-Farber Cancer Institute, Boston, MA, United States
- Radiology and Nuclear Medicine, CARIM & GROW, Maastricht University, Maastricht, Netherlands
| | - Marina Vannucci
- Department of Statistics, Rice University, Houston, TX, United States
| | - Christine B. Peterson
- Department of Biostatistics, The University of Texas MD Anderson Cancer Center, Houston, TX, United States
| |
Collapse
|
13
|
Li Y, Sijtsema NM, de Vette SPM, Steenbakkers RJHM, Zhang F, Noordzij W, Van den Bosch L, Langendijk JA, van Dijk LV. Validation of the 18F-FDG PET image biomarker model predicting late xerostomia after head and neck cancer radiotherapy. Radiother Oncol 2023; 180:109458. [PMID: 36608769 DOI: 10.1016/j.radonc.2022.109458] [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: 09/13/2022] [Revised: 12/23/2022] [Accepted: 12/28/2022] [Indexed: 01/05/2023]
Abstract
BACKGROUND AND PURPOSE Previously, PET image biomarkers (PET-IBMs) - the 90th percentile standardized uptake value (P90-SUV) and the Mean SUV (Mean-SUV) of the contralateral parotid gland (cPG) - were identified as predictors for late-xerostomia following head and neck cancer (HNC) radiotherapy. The aim of the current study was to assess in an independent validation cohort whether these pre-treatment PET-IBM can improve late-xerostomia prediction compared to the prediction with baseline xerostomia and mean cPG dose alone. MATERIALS AND METHODS The prediction endpoint was patient-rated moderate-to-severe xerostomia at 12 months after radiotherapy. The PET-IBMs were extracted from pre-treatment 18 F-FDG PET images. The performance of the model (base model) with baseline xerostomia and mean cPG dose alone and models with additionally P90-SUV or Mean-SUV were tested in the current independent validation cohort. Specifically, model discrimination (area under the curve: AUC) and calibration (calibration plot) were evaluated. RESULTS The current validation cohort consisted of 137 patients of which 40% developed moderate-to-severe xerostomia at 12 months. Both the PET-P90 model (AUC:PET-P90 = 0.71) and the PET-Mean model (AUC: PET-Mean = 0.70) performed well in the current validation cohort. Moreover, their performance were improved compared to the base model (AUC:base model= 0.68). The calibration plots showed a good fit of the prediction to the actual rates for all tested models. CONCLUSION PET-IBMs showed an improved prediction of late-xerostomia when added to the base model in this validation cohort. This contributed to the published hypothesis that PET-IBMs include individualized information and can serve as a pre-treatment risk factor for late-xerostomia.
Collapse
Affiliation(s)
- Yan Li
- Department of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, Netherlands.
| | - Nanna Maria Sijtsema
- Department of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, Netherlands
| | | | | | - Fan Zhang
- Department of Epidemiology, University Medical Center Groningen, University of Groningen, Groningen, Netherlands
| | - Walter Noordzij
- Department of Nuclear Medicine, University Medical Center Groningen, University of Groningen, Groningen, Netherlands
| | - Lisa Van den Bosch
- Department of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, Netherlands
| | - Johannes Albertus Langendijk
- Department of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, Netherlands
| | - Lisanne Vania van Dijk
- Department of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, Netherlands
| |
Collapse
|
14
|
Bidzińska J, Szurowska E. See Lung Cancer with an AI. Cancers (Basel) 2023; 15:cancers15041321. [PMID: 36831662 PMCID: PMC9954317 DOI: 10.3390/cancers15041321] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/20/2023] [Revised: 02/13/2023] [Accepted: 02/17/2023] [Indexed: 02/22/2023] Open
Abstract
A lot has happened in the field of lung cancer screening in recent months. The ongoing discussion and documentation published by the scientific community and policymakers are of great importance to the entire European community and perhaps beyond. Lung cancer is the main worldwide killer. Low-dose computed tomography-based screening, together with smoking cessation, is the only tool to fight lung cancer, as it has already been proven in the United States of America but also European randomized controlled trials. Screening requires a lot of well-organized specialized work, but it can be supported by artificial intelligence (AI). Here we discuss whether and how to use AI for patients, radiologists, pulmonologists, thoracic surgeons, and all hospital staff supporting screening process benefits.
Collapse
|
15
|
Zhang S, Mu W, Dong D, Wei J, Fang M, Shao L, Zhou Y, He B, Zhang S, Liu Z, Liu J, Tian J. The Applications of Artificial Intelligence in Digestive System Neoplasms: A Review. HEALTH DATA SCIENCE 2023; 3:0005. [PMID: 38487199 PMCID: PMC10877701 DOI: 10.34133/hds.0005] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 09/05/2022] [Accepted: 12/05/2022] [Indexed: 03/17/2024]
Abstract
Importance Digestive system neoplasms (DSNs) are the leading cause of cancer-related mortality with a 5-year survival rate of less than 20%. Subjective evaluation of medical images including endoscopic images, whole slide images, computed tomography images, and magnetic resonance images plays a vital role in the clinical practice of DSNs, but with limited performance and increased workload of radiologists or pathologists. The application of artificial intelligence (AI) in medical image analysis holds promise to augment the visual interpretation of medical images, which could not only automate the complicated evaluation process but also convert medical images into quantitative imaging features that associated with tumor heterogeneity. Highlights We briefly introduce the methodology of AI for medical image analysis and then review its clinical applications including clinical auxiliary diagnosis, assessment of treatment response, and prognosis prediction on 4 typical DSNs including esophageal cancer, gastric cancer, colorectal cancer, and hepatocellular carcinoma. Conclusion AI technology has great potential in supporting the clinical diagnosis and treatment decision-making of DSNs. Several technical issues should be overcome before its application into clinical practice of DSNs.
Collapse
Affiliation(s)
- Shuaitong Zhang
- School of Engineering Medicine, Beihang University, Beijing, China
- Key Laboratory of Big Data-Based Precision Medicine, Beihang University, Ministry of Industry and Information Technology, Beijing, China
| | - Wei Mu
- School of Engineering Medicine, Beihang University, Beijing, China
- Key Laboratory of Big Data-Based Precision Medicine, Beihang University, Ministry of Industry and Information Technology, Beijing, China
| | - Di Dong
- CAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing, China
| | - Jingwei Wei
- CAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing, China
| | - Mengjie Fang
- School of Engineering Medicine, Beihang University, Beijing, China
- Key Laboratory of Big Data-Based Precision Medicine, Beihang University, Ministry of Industry and Information Technology, Beijing, China
| | - Lizhi Shao
- CAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing, China
| | - Yu Zhou
- CAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing, China
| | - Bingxi He
- School of Engineering Medicine, Beihang University, Beijing, China
- Key Laboratory of Big Data-Based Precision Medicine, Beihang University, Ministry of Industry and Information Technology, Beijing, China
| | - Song Zhang
- CAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing, China
| | - Zhenyu Liu
- CAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing, China
| | - Jianhua Liu
- Department of Oncology, Guangdong Provincial People's Hospital/Second Clinical Medical College of Southern Medical University/Guangdong Academy of Medical Sciences, Guangzhou, Guangdong, China
| | - Jie Tian
- School of Engineering Medicine, Beihang University, Beijing, China
- Key Laboratory of Big Data-Based Precision Medicine, Beihang University, Ministry of Industry and Information Technology, Beijing, China
- CAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing, China
| |
Collapse
|
16
|
Zhong J, Xia Y, Chen Y, Li J, Lu W, Shi X, Feng J, Yan F, Yao W, Zhang H. Deep learning image reconstruction algorithm reduces image noise while alters radiomics features in dual-energy CT in comparison with conventional iterative reconstruction algorithms: a phantom study. Eur Radiol 2023; 33:812-824. [PMID: 36197579 DOI: 10.1007/s00330-022-09119-1] [Citation(s) in RCA: 7] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/21/2022] [Revised: 06/26/2022] [Accepted: 08/17/2022] [Indexed: 02/03/2023]
Abstract
OBJECTIVES To compare image quality between a deep learning image reconstruction (DLIR) algorithm and conventional iterative reconstruction (IR) algorithms in dual-energy CT (DECT) and to assess the impact of these algorithms on radiomics robustness. METHODS A phantom with clinical-relevant densities was imaged on seven DECT scanners with the same voxel size using typical abdominal-pelvis examination protocols. On one DECT scanner, raw data were reconstructed using both conventional IR (adaptive statistical iterative reconstruction-V, ASIR-V) and DLIR. Nine sets of corresponding images were generated on other six DECT scanners using scanner-equipped conventional IR. Regions of interest were delineated through rigid registrations. Image quality was compared. Pyradiomics platform was used for radiomics feature extraction. Test-retest repeatability was assessed by Bland-Altman analysis for repeated scans. Inter-reconstruction algorithm reproducibility between conventional IR and DLIR was tested by intraclass correlation coefficient (ICC) and concordance correlation coefficient (CCC). Inter-scanner reproducibility was evaluated by coefficient of variation (CV) and quartile coefficient of dispersion (QCD). Robust features were identified. RESULTS DLIR significantly improved image quality. Ninety-four radiomics features were extracted and nine features were considered as robust. 93.87% features were repeatable between repeated scans. ASIR-V images showed higher reproducibility to other conventional IR than DLIR (ICC mean, 0.603 vs 0.558, p = 0.001; CCC mean, 0.554 vs 0.510, p = 0.004). 7.45% and 26.83% features were reproducible among scanners evaluated by CV and QCD, respectively. CONCLUSIONS DLIR improves quality of DECT images but may alter radiomics features compared to conventional IR. Nine robust DECT radiomics features were identified. KEY POINTS • DLIR improves DECT image quality in terms of signal-to-noise ratio and contrast-to-noise ratio compared with ASIR-V and showed the highest noise reduction rate and lowest peak frequency shift. • Most of radiomics features are repeatable between repeated DECT scans, while inter-reconstruction algorithm reproducibility between conventional IR and DLIR, and inter-scanner reproducibility, are low. • Although DLIR may alter radiomics features compared to IR algorithms, nine radiomics features survived repeatability and reproducibility analysis among DECT scanners and reconstruction algorithms, which allows further validation and clinical-relevant analysis.
Collapse
Affiliation(s)
- Jingyu Zhong
- Department of Imaging, Tongren Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200336, China
| | - Yihan Xia
- Department of Radiology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200025, China
| | - Yong Chen
- Department of Radiology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200025, China
| | - Jianying Li
- Computed Tomography Research Center, GE Healthcare, Beijing, 100176, China
| | - Wei Lu
- Computed Tomography Research Center, GE Healthcare, Shanghai, 201203, China
| | - Xiaomeng Shi
- Department of Materials, Imperial College London, South Kensington Campus, London, SW7 2AZ, UK
| | - Jianxing Feng
- Haohua Technology Co., Ltd., Shanghai, 201100, China
| | - Fuhua Yan
- Department of Radiology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200025, China
| | - Weiwu Yao
- Department of Imaging, Tongren Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200336, China.
| | - Huan Zhang
- Department of Radiology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200025, China.
| |
Collapse
|
17
|
van Dijk LV, Mohamed AS, Ahmed S, Nipu N, Marai GE, Wahid K, Sijtsema NM, Gunn B, Garden AS, Moreno A, Hope AJ, Langendijk JA, Fuller CD. Head and neck cancer predictive risk estimator to determine control and therapeutic outcomes of radiotherapy (HNC-PREDICTOR): development, international multi-institutional validation, and web implementation of clinic-ready model-based risk stratification for head and neck cancer. Eur J Cancer 2023; 178:150-161. [PMID: 36442460 PMCID: PMC9853413 DOI: 10.1016/j.ejca.2022.10.011] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/01/2022] [Revised: 10/13/2022] [Accepted: 10/16/2022] [Indexed: 01/24/2023]
Abstract
BACKGROUND Personalised radiotherapy can improve treatment outcomes of patients with head and neck cancer (HNC), where currently a 'one-dose-fits-all' approach is the standard. The aim was to establish individualised outcome prediction based on multi-institutional international 'big-data' to facilitate risk-based stratification of patients with HNC. METHODS The data of 4611 HNC radiotherapy patients from three academic cancer centres were split into four cohorts: a training (n = 2241), independent test (n = 786), and external validation cohorts 1 (n = 1087) and 2 (n = 497). Tumour- and patient-related clinical variables were considered in a machine learning pipeline to predict overall survival (primary end-point) and local and regional tumour control (secondary end-points); serially, imaging features were considered for optional model improvement. Finally, patients were stratified into high-, intermediate-, and low-risk groups. RESULTS Performance score, AJCC8thstage, pack-years, and Age were identified as predictors for overall survival, demonstrating good performance in both the training cohort (c-index = 0.72 [95% CI, 0.66-0.77]) and in all three validation cohorts (c-indices: 0.76 [0.69-0.83], 0.73 [0.68-0.77], and 0.75 [0.68-0.80]). Excellent stratification of patients with HNC into high, intermediate, and low mortality risk was achieved; with 5-year overall survival rates of 17-46% for the high-risk group compared to 92-98% for the low-risk group. The addition of morphological image feature further improved the performance (c-index = 0.73 [0.64-0.81]). These models are integrated in a clinic-ready interactive web interface: https://uic-evl.github.io/hnc-predictor/ CONCLUSIONS: Robust model-based prediction was able to stratify patients with HNC in distinct high, intermediate, and low mortality risk groups. This can effectively be capitalised for personalised radiotherapy, e.g., for tumour radiation dose escalation/de-escalation.
Collapse
Affiliation(s)
- Lisanne V van Dijk
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA; Department of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, the Netherlands.
| | - Abdallah Sr Mohamed
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Sara Ahmed
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Nafiul Nipu
- Department of Computer Science, The University of Illinois Chicago, Chicago, USA
| | - G Elisabeta Marai
- Department of Computer Science, The University of Illinois Chicago, Chicago, USA
| | - Kareem Wahid
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Nanna M Sijtsema
- Department of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, the Netherlands
| | - Brandon Gunn
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Adam S Garden
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Amy Moreno
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA; MD Anderson Stiefel Center for Oropharyngeal Cancer Research and Education (MDA-SCORE), Houston, TX, USA
| | - Andrew J Hope
- Department of Radiation Oncology, University of Toronto, Toronto, Canada; Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network, Toronto, Canada
| | - Johannes A Langendijk
- Department of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, the Netherlands
| | - Clifton D Fuller
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA; MD Anderson Stiefel Center for Oropharyngeal Cancer Research and Education (MDA-SCORE), Houston, TX, USA
| |
Collapse
|
18
|
Nie K, Xiao Y. Radiomics in clinical trials: perspectives on standardization. Phys Med Biol 2022; 68. [PMID: 36384049 DOI: 10.1088/1361-6560/aca388] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/09/2022] [Accepted: 11/16/2022] [Indexed: 11/17/2022]
Abstract
The term biomarker is used to describe a biological measure of the disease behavior. The existing imaging biomarkers are associated with the known tissue biological characteristics and follow a well-established roadmap to be implemented in routine clinical practice. Recently, a new quantitative imaging analysis approach named radiomics has emerged. It refers to the extraction of a large number of advanced imaging features with high-throughput computing. Extensive research has demonstrated its value in predicting disease behavior, progression, and response to therapeutic options. However, there are numerous challenges to establishing it as a clinically viable solution, including lack of reproducibility and transparency. The data-driven nature also does not offer insights into the underpinning biology of the observed relationships. As such, additional effort is needed to establish it as a qualified biomarker to inform clinical decisions. Here we review the technical difficulties encountered in the clinical applications of radiomics and current effort in addressing some of these challenges in clinical trial designs. By addressing these challenges, the true potential of radiomics can be unleashed.
Collapse
Affiliation(s)
- Ke Nie
- Rutgers-Cancer Institute of New Jersey, Rutgers-Robert Wood Johnson Medical School, Department of Radiation Oncology, New Brunswick, NJ, 08901, United States of America
| | - Ying Xiao
- University of Pennsylvania, Department of Radiation Oncology, 3400 Civic Center Blvd, TRC-2 West Philadelphia, PA 19104, United States of America
| |
Collapse
|
19
|
CT radiomics to predict Deauville score 4 positive and negative Hodgkin lymphoma manifestations. Sci Rep 2022; 12:20008. [PMID: 36411307 PMCID: PMC9678888 DOI: 10.1038/s41598-022-24227-0] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/10/2022] [Accepted: 11/11/2022] [Indexed: 11/23/2022] Open
Abstract
18F-FDG-PET/CT is standard to assess response in Hodgkin lymphoma by quantifying metabolic activity with the Deauville score. PET/CT, however, is time-consuming, cost-extensive, linked to high radiation and has a low availability. As an alternative, we investigated radiomics from non-contrast-enhanced computed tomography (NECT) scans. 75 PET/CT examinations of 43 patients on two different scanners were included. Target lesions were classified as Deauville score 4 positive (DS4+) or negative (DS4-) based on their SUVpeak and then segmented in NECT images. From these segmentations, 107 features were extracted with PyRadiomics. All further statistical analyses were then performed scanner-wise: differences between DS4+ and DS4- manifestations were assessed with the Mann-Whitney-U-test and single feature performances with the ROC-analysis. To further verify the reliability of the results, the number of features was reduced using different techniques. The feature median showed a high sensitivity for DS4+ manifestations on both scanners (scanner A: 0.91, scanner B: 0.85). It furthermore was the only feature that remained in both datasets after applying different feature reduction techniques. The feature median from NECT concordantly has a high sensitivity for DS4+ Hodgkin manifestations on two different scanners and thus could provide a surrogate for increased metabolic activity in PET/CT.
Collapse
|
20
|
Yang Z, Lafata KJ, Chen X, Bowsher J, Chang Y, Wang C, Yin FF. Quantification of lung function on CT images based on pulmonary radiomic filtering. Med Phys 2022; 49:7278-7286. [PMID: 35770964 DOI: 10.1002/mp.15837] [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: 06/14/2021] [Revised: 06/06/2022] [Accepted: 06/08/2022] [Indexed: 12/13/2022] Open
Abstract
PURPOSE To develop a radiomics filtering technique for characterizing spatial-encoded regional pulmonary ventilation information on lung computed tomography (CT). METHODS The lung volume was segmented on 46 CT images, and a 3D sliding window kernel was implemented across the lung volume to capture the spatial-encoded image information. Fifty-three radiomic features were extracted within the kernel, resulting in a fourth-order tensor object. As such, each voxel coordinate of the original lung was represented as a 53-dimensional feature vector, such that radiomic features could be viewed as feature maps within the lungs. To test the technique as a potential pulmonary ventilation biomarker, the radiomic feature maps were compared to paired functional images (Galligas PET or DTPA-SPECT) based on the Spearman correlation (ρ) analysis. RESULTS The radiomic feature maps GLRLM-based Run-Length Non-Uniformity and GLCOM-based Sum Average are found to be highly correlated with the functional imaging. The achieved ρ (median [range]) for the two features are 0.46 [0.05, 0.67] and 0.45 [0.21, 0.65] across 46 patients and 2 functional imaging modalities, respectively. CONCLUSIONS The results provide evidence that local regions of sparsely encoded heterogeneous lung parenchyma on CT are associated with diminished radiotracer uptake and measured lung ventilation defects on PET/SPECT imaging. These findings demonstrate the potential of radiomics to serve as a complementary tool to the current lung quantification techniques and provide hypothesis-generating data for future studies.
Collapse
Affiliation(s)
- Zhenyu Yang
- Department of Radiation Oncology, Duke University Medical Center, Durham, North Carolina, USA
- Medical Physics Graduate Program, Duke Kunshan University, Kunshan, Jiangsu, China
| | - Kyle J Lafata
- Department of Radiation Oncology, Duke University Medical Center, Durham, North Carolina, USA
- Department of Radiology, Duke University, Durham, North Carolina, USA
- Department of Electrical and Computer Engineering, Duke University, Durham, North Carolina, USA
| | - Xinru Chen
- Medical Physics Graduate Program, Duke Kunshan University, Kunshan, Jiangsu, China
| | - James Bowsher
- Medical Physics Graduate Program, Duke Kunshan University, Kunshan, Jiangsu, China
| | - Yushi Chang
- Department of Radiation Oncology, Duke University Medical Center, Durham, North Carolina, USA
| | - Chunhao Wang
- Department of Radiation Oncology, Duke University Medical Center, Durham, North Carolina, USA
| | - Fang-Fang Yin
- Department of Radiation Oncology, Duke University Medical Center, Durham, North Carolina, USA
- Medical Physics Graduate Program, Duke Kunshan University, Kunshan, Jiangsu, China
| |
Collapse
|
21
|
Soliman MA, Kelahan LC, Magnetta M, Savas H, Agrawal R, Avery RJ, Aouad P, Liu B, Xue Y, Chae YK, Salem R, Benson AB, Yaghmai V, Velichko YS. A Framework for Harmonization of Radiomics Data for Multicenter Studies and Clinical Trials. JCO Clin Cancer Inform 2022; 6:e2200023. [PMID: 36332157 PMCID: PMC9668564 DOI: 10.1200/cci.22.00023] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/16/2022] [Revised: 07/01/2022] [Accepted: 09/21/2022] [Indexed: 11/06/2022] Open
Abstract
PURPOSE Variability in computed tomography images intrinsic to individual scanners limits the application of radiomics in clinical and research settings. The development of reproducible and generalizable radiomics-based models to assess lesions requires harmonization of data. The purpose of this study was to develop, test, and analyze the efficacy of a radiomics data harmonization model. MATERIALS AND METHODS Radiomic features from biopsy-proven untreated hepatic metastasis (N = 380) acquired from 167 unique patients with pancreatic, colon, and breast cancers were analyzed. Radiomic features from volume-match 551 samples of normal liver tissue and 188 hepatic cysts were included as references. A novel linear mixed effect model was used to identify effects associated with lesion size, tissue type, and scanner model. Six separate machine learning models were then used to test the effectiveness of radiomic feature harmonization using multivariate analysis. RESULTS Proposed model identifies and removes scanner-associated effects while preserving cancer-specific functional dependence of radiomic features on the tumor size. Data harmonization improves the performance of classification models by reducing the scanner-associated variability. For example, the multiclass logistic regression model, LogitBoost, demonstrated the improvement in sensitivity in the range from 15% to 40% for each type of liver metastasis, whereas the overall model accuracy and the kappa coefficient increased by 5% and 8% accordingly. CONCLUSION The model removed scanner-associated effects while preserving cancer-specific functional dependence of radiomic features.
Collapse
Affiliation(s)
- Moataz A.S. Soliman
- Department of Radiology, Feinberg School of Medicine, Northwestern University, Chicago, IL
| | - Linda C. Kelahan
- Department of Radiology, Feinberg School of Medicine, Northwestern University, Chicago, IL
| | - Michael Magnetta
- Department of Radiology, Feinberg School of Medicine, Northwestern University, Chicago, IL
| | - Hatice Savas
- Department of Radiology, Feinberg School of Medicine, Northwestern University, Chicago, IL
| | - Rishi Agrawal
- Department of Radiology, Feinberg School of Medicine, Northwestern University, Chicago, IL
| | - Ryan J. Avery
- Department of Radiology, Feinberg School of Medicine, Northwestern University, Chicago, IL
| | - Pascale Aouad
- Department of Radiology, Feinberg School of Medicine, Northwestern University, Chicago, IL
| | - Benjamin Liu
- Department of Radiology, Feinberg School of Medicine, Northwestern University, Chicago, IL
| | - Yue Xue
- Department of Pathology, Feinberg School of Medicine, Northwestern University, Chicago, IL
| | - Young K. Chae
- Department of Medicine, Division of Hematology/Oncology, Feinberg School of Medicine, Northwestern University, Chicago, IL
- Robert H. Lurie Comprehensive Cancer Center, Northwestern University, Chicago, IL
| | - Riad Salem
- Department of Radiology, Feinberg School of Medicine, Northwestern University, Chicago, IL
- Robert H. Lurie Comprehensive Cancer Center, Northwestern University, Chicago, IL
| | - Al B. Benson
- Department of Medicine, Division of Hematology/Oncology, Feinberg School of Medicine, Northwestern University, Chicago, IL
- Robert H. Lurie Comprehensive Cancer Center, Northwestern University, Chicago, IL
| | - Vahid Yaghmai
- Department of Radiological Sciences, University of California, Irvine UCI Health, University of California Irvine, Orange, CA
| | - Yuri S. Velichko
- Department of Radiology, Feinberg School of Medicine, Northwestern University, Chicago, IL
- Robert H. Lurie Comprehensive Cancer Center, Northwestern University, Chicago, IL
| |
Collapse
|
22
|
Cui Y, Yin FF. Impact of image quality on radiomics applications. Phys Med Biol 2022; 67. [DOI: 10.1088/1361-6560/ac7fd7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/12/2022] [Accepted: 07/08/2022] [Indexed: 11/12/2022]
Abstract
Abstract
Radiomics features extracted from medical images have been widely reported to be useful in the patient specific outcome modeling for variety of assessment and prediction purposes. Successful application of radiomics features as imaging biomarkers, however, is dependent on the robustness of the approach to the variation in each step of the modeling workflow. Variation in the input image quality is one of the main sources that impacts the reproducibility of radiomics analysis when a model is applied to broader range of medical imaging data. The quality of medical image is generally affected by both the scanner related factors such as image acquisition/reconstruction settings and the patient related factors such as patient motion. This article aimed to review the published literatures in this field that reported the impact of various imaging factors on the radiomics features through the change in image quality. The literatures were categorized by different imaging modalities and also tabulated based on the imaging parameters and the class of radiomics features included in the study. Strategies for image quality standardization were discussed based on the relevant literatures and recommendations for reducing the impact of image quality variation on the radiomics in multi-institutional clinical trial were summarized at the end of this article.
Collapse
|
23
|
Bao J, Feng X, Ma Y, Wang Y, Qi J, Qin C, Tan X, Tian Y. The latest application progress of radiomics in prediction and diagnosis of liver diseases. Expert Rev Gastroenterol Hepatol 2022; 16:707-719. [PMID: 35880549 DOI: 10.1080/17474124.2022.2104711] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/04/2022]
Abstract
INTRODUCTION Early detection and individualized treatment of patients with liver disease is the key to survival. Radiomics can extract high-throughput quantitative features by multimode imaging, which has good application prospects for the diagnosis, staging and prognosis of benign and malignant liver diseases. Therefore, this paper summarizes the current research status in the field of liver disease, in order to help these patients achieve personalized and precision medical care. AREAS COVERED This paper uses several keywords on the PubMed database to search the references, and reviews the workflow of traditional radiomics, as well as the characteristics and influencing factors of different imaging modes. At the same time, the references on the application of imaging in different benign and malignant liver diseases were also summarized. EXPERT OPINION For patients with liver disease, the traditional imaging evaluation can only provide limited information. Radiomics exploits the characteristics of high-throughput and high-dimensional extraction, enabling liver imaging capabilities far beyond the scope of traditional visual image analysis. Recent studies have demonstrated the prospect of this technology in personalized diagnosis and treatment decision in various fields of the liver. However, further clinical validation is needed in its application and practice.
Collapse
Affiliation(s)
- Jiaying Bao
- Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, P.R. China
| | - Xiao Feng
- Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, P.R. China
| | - Yan Ma
- Department of Ultrasound, Zibo Central Hospital, Zibo, P.R. China
| | - Yanyan Wang
- Departments of Emergency Medicine, Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, Shandong, P.R. China
| | - Jianni Qi
- Central Laboratory, Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, Shandong, P.R. China
| | - Chengyong Qin
- Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, P.R. China
| | - Xu Tan
- Department of Gynecology, Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, Shandong, P.R. China
| | - Yongmei Tian
- Department of Geriatrics, Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, Shandong, P.R. China
| |
Collapse
|
24
|
Role of Artificial Intelligence in Radiogenomics for Cancers in the Era of Precision Medicine. Cancers (Basel) 2022; 14:cancers14122860. [PMID: 35740526 PMCID: PMC9220825 DOI: 10.3390/cancers14122860] [Citation(s) in RCA: 26] [Impact Index Per Article: 13.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/15/2022] [Revised: 06/03/2022] [Accepted: 06/07/2022] [Indexed: 12/12/2022] Open
Abstract
Simple Summary Recently, radiogenomics has played a significant role and offered a new understanding of cancer’s biology and behavior in response to standard therapy. It also provides a more precise prognosis, investigation, and analysis of the patient’s cancer. Over the years, Artificial Intelligence (AI) has provided a significant strength in radiogenomics. In this paper, we offer computational and oncological prospects of the role of AI in radiogenomics, as well as its offers, achievements, opportunities, and limitations in the current clinical practices. Abstract Radiogenomics, a combination of “Radiomics” and “Genomics,” using Artificial Intelligence (AI) has recently emerged as the state-of-the-art science in precision medicine, especially in oncology care. Radiogenomics syndicates large-scale quantifiable data extracted from radiological medical images enveloped with personalized genomic phenotypes. It fabricates a prediction model through various AI methods to stratify the risk of patients, monitor therapeutic approaches, and assess clinical outcomes. It has recently shown tremendous achievements in prognosis, treatment planning, survival prediction, heterogeneity analysis, reoccurrence, and progression-free survival for human cancer study. Although AI has shown immense performance in oncology care in various clinical aspects, it has several challenges and limitations. The proposed review provides an overview of radiogenomics with the viewpoints on the role of AI in terms of its promises for computational as well as oncological aspects and offers achievements and opportunities in the era of precision medicine. The review also presents various recommendations to diminish these obstacles.
Collapse
|
25
|
Deep Neural Networks and Machine Learning Radiomics Modelling for Prediction of Relapse in Mantle Cell Lymphoma. Cancers (Basel) 2022; 14:cancers14082008. [PMID: 35454914 PMCID: PMC9028737 DOI: 10.3390/cancers14082008] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/03/2022] [Revised: 04/05/2022] [Accepted: 04/12/2022] [Indexed: 12/12/2022] Open
Abstract
Simple Summary Mantle cell lymphoma (MCL) is an aggressive lymphoid tumour with a poor prognosis. There exist no routine biomarkers for the early prediction of relapse. Our study compared the potential of radiomics-based machine learning and 3D deep learning models as non-invasive biomarkers to risk-stratify MCL patients, thus promoting precision imaging in clinical oncology. Abstract Mantle cell lymphoma (MCL) is a rare lymphoid malignancy with a poor prognosis characterised by frequent relapse and short durations of treatment response. Most patients present with aggressive disease, but there exist indolent subtypes without the need for immediate intervention. The very heterogeneous behaviour of MCL is genetically characterised by the translocation t(11;14)(q13;q32), leading to Cyclin D1 overexpression with distinct clinical and biological characteristics and outcomes. There is still an unfulfilled need for precise MCL prognostication in real-time. Machine learning and deep learning neural networks are rapidly advancing technologies with promising results in numerous fields of application. This study develops and compares the performance of deep learning (DL) algorithms and radiomics-based machine learning (ML) models to predict MCL relapse on baseline CT scans. Five classification algorithms were used, including three deep learning models (3D SEResNet50, 3D DenseNet, and an optimised 3D CNN) and two machine learning models based on K-nearest Neighbor (KNN) and Random Forest (RF). The best performing method, our optimised 3D CNN, predicted MCL relapse with a 70% accuracy, better than the 3D SEResNet50 (62%) and the 3D DenseNet (59%). The second-best performing method was the KNN-based machine learning model (64%) after principal component analysis for improved accuracy. Our optimised CNN developed by ourselves correctly predicted MCL relapse in 70% of the patients on baseline CT imaging. Once prospectively tested in clinical trials with a larger sample size, our proposed 3D deep learning model could facilitate clinical management by precision imaging in MCL.
Collapse
|
26
|
Hoye J, Smith T, Abadi E, Solomon JB, Samei E. Correction for Systematic Bias in Radiomics Measurements Due to Variation in Imaging Protocols. Acad Radiol 2022; 29:e61-e72. [PMID: 34130922 DOI: 10.1016/j.acra.2021.04.012] [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: 08/04/2020] [Revised: 02/28/2021] [Accepted: 04/01/2021] [Indexed: 11/01/2022]
Abstract
RATIONALE AND OBJECTIVES The accuracy of measured radiomics features is affected by CT imaging protocols. This study aims to ascertain if applying bias corrections can improve the classification performance of the radiomics features. MATERIALS AND METHODS A cohort of 144 Non-Small Cell Lung Cancer patient CT images was used to calculate radiomics features for use in predictive models of patient pathological stage. Simulation models of the tumors, matched to patient lesion qualities of size, contrast, and degree of spiculation, were used to both create and assess protocol-specific correction factors. The usefulness of correction was first assessed by applying the corrections to simulated lesion phantoms with known properties using a corrected paired Student's t-test. The sensitivity of radiomics features to correction factors was assessed by applying a library of possible theoretical correction factors to the uncorrected radiomics from the patient data. The data were then used to assess the effect of the correction on prediction performance (AUC) from a logistic regression radiomics model across the patient cases. RESULTS The correction factors were shown to reduce the bias of radiomics features, caused by protocols, provided that the correction factors were derived from lesion models with similar properties. The sensitivity of the radiomics features to changes due to protocol effects was on average 89% among all features. The corrections applied to patient data resulted in a small increase of 0.0074 in AUC that was not statistically significant (p=0.60). CONCLUSION Protocol-specific correction factors can be applied to radiomics studies to control for biases introduced by different imaging protocols. The correction factors should ideally be lesion-specific, derived using lesion models that echo patient lesion characteristics in terms of size, contrast, and degree of spiculation. Small corrections in the 10% range offers only a small improvement in the predictability of radiomics.
Collapse
|
27
|
Rinaldi L, Pezzotta F, Santaniello T, De Marco P, Bianchini L, Origgi D, Cremonesi M, Milani P, Mariani M, Botta F. HeLLePhant: A phantom mimicking non-small cell lung cancer for texture analysis in CT images. Phys Med 2022; 97:13-24. [PMID: 35334407 DOI: 10.1016/j.ejmp.2022.03.010] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/19/2021] [Revised: 02/01/2022] [Accepted: 03/14/2022] [Indexed: 01/06/2023] Open
Abstract
PURPOSE Phantoms mimicking human tissue heterogeneity and intensity are required to establish radiomic features robustness in Computed Tomography (CT) images. We developed inserts with two different techniques for the radiomic study of Non-Small Cell Lung Cancer (NSCLC) lesions. METHODS We developed two insert prototypes: two 3D-printed made of glycol-modified polyethylene terephthalate (PET-G), and nine with sodium polyacrylate plus iodinated contrast medium. The inserts were put in a handcraft phantom (HeLLePhant). We also analysed four materials of a commercial homogeneous phantom (Catphan® 424) and collected 29 NSCLC patients for comparison. All the CT acquisitions were performed with the same clinical protocol and scanner at 120kVp. The HeLLePhant phantom was scanned ten times in fixed condition at 120kVp and 100kVp for repeatability investigation. We extracted 153 radiomic features using Pyradiomics. To compare the features between phantoms and patients, we computed how many phantom features fell in the range between 10th and 90th percentile of the corresponding patient values. We deemed repeatable the features with a coefficient of variation (CV) less than or equal to 0.10. RESULTS The best similarity with the patients was obtained with the polyacrylate inserts (55.6-90.2%), the worst with Catphan (15.7-19.0%). For the PET-G inserts 35.3% and 36.6% of the features match the patient range. We found high repeatability for all the inserts of the HeLLePhant phantom (74.3-100% at 120kVp, 75.7-97.9% at 100kVp), and observed a texture dependency in repeatability. CONCLUSIONS Our study shows a promising way to construct heterogeneous inserts mimicking a target tissue for radiomic studies.
Collapse
Affiliation(s)
- Lisa Rinaldi
- Department of Physics, Università degli Studi di Pavia and INFN, via Bassi 6, 27100 Pavia, Italy; Radiation Research Unit, IEO, European Institute of Oncology IRCCS, via Ripamonti 435, 20141 Milan, Italy.
| | - Federico Pezzotta
- CIMaINa, Department of Physics, Università degli Studi di Milano, via Celoria 16, 20133, Milan, Italy
| | - Tommaso Santaniello
- CIMaINa, Department of Physics, Università degli Studi di Milano, via Celoria 16, 20133, Milan, Italy
| | - Paolo De Marco
- Medical Physics Unit, IEO European Institute of Oncology IRCCS, via Ripamonti 435, 20141 Milan, Italy
| | - Linda Bianchini
- Department of Physics, Università degli Studi di Milano, via Celoria 16, 20133, Milan, Italy
| | - Daniela Origgi
- Medical Physics Unit, IEO European Institute of Oncology IRCCS, via Ripamonti 435, 20141 Milan, Italy
| | - Marta Cremonesi
- Radiation Research Unit, IEO, European Institute of Oncology IRCCS, via Ripamonti 435, 20141 Milan, Italy
| | - Paolo Milani
- CIMaINa, Department of Physics, Università degli Studi di Milano, via Celoria 16, 20133, Milan, Italy
| | - Manuel Mariani
- Department of Physics, Università degli Studi di Pavia and INFN, via Bassi 6, 27100 Pavia, Italy
| | - Francesca Botta
- Medical Physics Unit, IEO European Institute of Oncology IRCCS, via Ripamonti 435, 20141 Milan, Italy
| |
Collapse
|
28
|
Radiomics of Patients with Locally Advanced Rectal Cancer: Effect of Preprocessing on Features Estimation from Computed Tomography Imaging. BIOMED RESEARCH INTERNATIONAL 2022; 2022:2003286. [PMID: 35355820 PMCID: PMC8958068 DOI: 10.1155/2022/2003286] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 05/03/2021] [Revised: 01/14/2022] [Accepted: 01/30/2022] [Indexed: 12/24/2022]
Abstract
The purpose of this study was to investigate the effect of image preprocessing on radiomic features estimation from computed tomography (CT) imaging of locally advanced rectal cancer (LARC). CT images of 20 patients with LARC were used to estimate 105 radiomic features of 7 classes (shape, first-order, GLCM, GLDM, GLRLM, GLSZM, and NGTDM). Radiomic features were estimated for 6 different isotropic resampling voxel sizes, using 10 interpolation algorithms (at fixed bin width) and 6 different bin widths (at fixed interpolation algorithm). The intraclass correlation coefficient (ICC) and the coefficient of variation (CV) were calculated to assess the variability in radiomic features estimation due to preprocessing. A repeated measures correlation analysis was performed to assess any linear correlation between radiomic feature estimate and resampling voxel size or bin width. Reproducibility of radiomic feature estimate, when assessed through ICC analysis, was nominally excellent (ICC > 0.9) for shape features, good (0.75 < ICC ≤ 0.9) or moderate (0.5 < ICC ≤ 0.75) for first-order features, and moderate or poor (0 ≤ ICC ≤ 0.5) for textural features. A number of radiomic features characterized by good or excellent reproducibility in terms of ICC showed however median CV values greater than 15%. For most textural features, a significant (p < 0.05) correlation between their estimate and resampling voxel size or bin width was found. In CT imaging of patients with LARC, the estimate of textural features, as well as of first-order features to a lesser extent, is appreciably biased by preprocessing. Accordingly, this should be taken into account when planning clinical or research studies, as well as when comparing results from different studies and performing multicenter studies.
Collapse
|
29
|
Ziegelmayer S, Reischl S, Harder F, Makowski M, Braren R, Gawlitza J. Feature Robustness and Diagnostic Capabilities of Convolutional Neural Networks Against Radiomics Features in Computed Tomography Imaging. Invest Radiol 2022; 57:171-177. [PMID: 34524173 DOI: 10.1097/rli.0000000000000827] [Citation(s) in RCA: 8] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/27/2022]
Abstract
MATERIALS AND METHODS Imaging phantoms were scanned twice on 3 computed tomography scanners from 2 different manufactures with varying tube voltages and currents. Phantoms were segmented, and features were extracted using PyRadiomics and a pretrained CNN. After standardization the concordance correlation coefficient (CCC), mean feature variance, feature range, and the coefficient of variant were calculated to assess feature robustness. In addition, the cosine similarity was calculated for the vectorized activation maps for an exemplary phantom. For the in vivo comparison, the radiomics and CNN features of 30 patients with hepatocellular carcinoma (HCC) and 30 patients with hepatic colon carcinoma metastasis were compared. RESULTS In total, 851 radiomics features and 256 CNN features were extracted for each phantom. For all phantoms, the global CCC of the CNN features was above 98%, whereas the highest CCC for the radiomics features was 36%. The mean feature variance and feature range was significantly lower for the CNN features. Using a coefficient of variant ≤0.2 as a threshold to define robust features and averaging across all phantoms 346 of 851 (41%) radiomics features and 196 of 256 (77%) CNN features were found to be robust. The cosine similarity was greater than 0.98 for all scanner and parameter variations. In the retrospective analysis, 122 of the 256 CNN (49%) features showed significant differences between HCC and hepatic colon metastasis. DISCUSSION Convolutional neural network features were more stable compared with radiomics features against technical variations. Moreover, the possibility of tumor entity differentiation based on CNN features was shown. Combined with visualization methods, CNN features are expected to increase reproducibility of quantitative image representations. Further studies are warranted to investigate the impact of feature stability on radiological image-based prediction of clinical outcomes.
Collapse
Affiliation(s)
- Sebastian Ziegelmayer
- From the Institute of Diagnostic and Interventional Radiology, School of Medicine, Klinikum rechts der Isar, Technical University Munich
| | - Stefan Reischl
- From the Institute of Diagnostic and Interventional Radiology, School of Medicine, Klinikum rechts der Isar, Technical University Munich
| | - Felix Harder
- From the Institute of Diagnostic and Interventional Radiology, School of Medicine, Klinikum rechts der Isar, Technical University Munich
| | - Marcus Makowski
- From the Institute of Diagnostic and Interventional Radiology, School of Medicine, Klinikum rechts der Isar, Technical University Munich
| | | | - Joshua Gawlitza
- From the Institute of Diagnostic and Interventional Radiology, School of Medicine, Klinikum rechts der Isar, Technical University Munich
| |
Collapse
|
30
|
Shapira N, Donovan K, Mei K, Geagan M, Roshkovan L, Litt HI, Gang GJ, Stayman JW, Shinohara RT, Noël PB. PixelPrint: Three-dimensional printing of realistic patient-specific lung phantoms for CT imaging. PROCEEDINGS OF SPIE--THE INTERNATIONAL SOCIETY FOR OPTICAL ENGINEERING 2022; 12031:120310N. [PMID: 35664728 PMCID: PMC9164709 DOI: 10.1117/12.2611805] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/25/2023]
Abstract
Phantoms are essential tools for assessing and verifying performance in computed tomography (CT). Realistic patient-based lung phantoms that accurately represent textures and densities are essential in developing and evaluating novel CT hardware and software. This study introduces PixelPrint, a 3D-printing solution to create patient-specific lung phantoms with accurate contrast and textures. PixelPrint converts patient images directly into printer instructions, where density is modeled as the ratio of filament to voxel volume to emulate local attenuation values. For evaluation of PixelPrint, phantoms based on four COVID-19 pneumonia patients were manufactured and scanned with the original (clinical) CT scanners and protocols. Density and geometrical accuracies between phantom and patient images were evaluated for various anatomical features in the lung, and a radiomic feature comparison was performed for mild, moderate, and severe COVID-19 pneumonia patient-based phantoms. Qualitatively, CT images of the patient-based phantoms closely resemble the original CT images, both in texture and contrast levels, with clearly visible vascular and parenchymal structures. Regions-of-interest (ROIs) comparing attenuation demonstrated differences below 15 HU. Manual size measurements performed by an experienced thoracic radiologist revealed a high degree of geometrical correlation between identical patient and phantom features, with differences smaller than the intrinsic spatial resolution of the images. Radiomic feature analysis revealed high correspondence, with correlations of 0.95-0.99 between patient and phantom images. Our study demonstrates the feasibility of 3D-printed patient-based lung phantoms with accurate geometry, texture, and contrast that will enable protocol optimization, CT research and development advancements, and generation of ground-truth datasets for radiomic evaluations.
Collapse
Affiliation(s)
- Nadav Shapira
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA
| | - Kevin Donovan
- Department of Biostatistics, Epidemiology and Informatics, University of Pennsylvania, Philadelphia, PA, USA
| | - Kai Mei
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA
| | - Michael Geagan
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA
| | - Leonid Roshkovan
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA
| | - Harold I. Litt
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA
| | - Grace J. Gang
- Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD, USA
| | - J. Webster Stayman
- Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD, USA
| | - Russell T. Shinohara
- Department of Biostatistics, Epidemiology and Informatics, University of Pennsylvania, Philadelphia, PA, USA
| | - Peter B. Noël
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA
- Department of Diagnostic and Interventional Radiology, School of Medicine & Klinikum rechts der Isar, Technical University of Munich, Munich, Germany
| |
Collapse
|
31
|
Mei K, Geagan M, Roshkovan L, Litt HI, Gang GJ, Shapira N, Stayman JW, Noël PB. Three-dimensional printing of patient-specific lung phantoms for CT imaging: Emulating lung tissue with accurate attenuation profiles and textures. Med Phys 2021; 49:825-835. [PMID: 34910309 DOI: 10.1002/mp.15407] [Citation(s) in RCA: 19] [Impact Index Per Article: 6.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/04/2021] [Revised: 11/22/2021] [Accepted: 11/22/2021] [Indexed: 11/10/2022] Open
Abstract
PURPOSE Phantoms are a basic tool for assessing and verifying performance in CT research and clinical practice. Patient-based realistic lung phantoms accurately representing textures and densities are essential in developing and evaluating novel CT hardware and software. This study introduces PixelPrint, a 3D printing solution to create patient-based lung phantoms with accurate attenuation profiles and textures. METHODS PixelPrint, a software tool, was developed to convert patient digital imaging and communications in medicine (DICOM) images directly into FDM printer instructions (G-code). Density was modeled as the ratio of filament to voxel volume to emulate attenuation profiles for each voxel, with the filament ratio controlled through continuous modification of the printing speed. A calibration phantom was designed to determine the mapping between filament line width and Hounsfield units (HU) within the range of human lungs. For evaluation of PixelPrint, a phantom based on a single human lung slice was manufactured and scanned with the same CT scanner and protocol used for the patient scan. Density and geometrical accuracy between phantom and patient CT data were evaluated for various anatomical features in the lung. RESULTS For the calibration phantom, measured mean HU show a very high level of linear correlation with respect to the utilized filament line widths, (r > 0.999). Qualitatively, the CT image of the patient-based phantom closely resembles the original CT image both in texture and contrast levels (from -800 to 0 HU), with clearly visible vascular and parenchymal structures. Regions of interest comparing attenuation illustrated differences below 15 HU. Manual size measurements performed by an experienced thoracic radiologist reveal a high degree of geometrical correlation of details between identical patient and phantom features, with differences smaller than the intrinsic spatial resolution of the scans. CONCLUSION The present study demonstrates the feasibility of 3D-printed patient-based lung phantoms with accurate organ geometry, image texture, and attenuation profiles. PixelPrint will enable applications in the research and development of CT technology, including further development in radiomics.
Collapse
Affiliation(s)
- Kai Mei
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA
| | - Michael Geagan
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA
| | - Leonid Roshkovan
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA
| | - Harold I Litt
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA
| | - Grace J Gang
- Department of Biomedical Engineering, Johns Hopkins University, Baltimore, Maryland, USA
| | - Nadav Shapira
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA
| | - J Webster Stayman
- Department of Biomedical Engineering, Johns Hopkins University, Baltimore, Maryland, USA
| | - Peter B Noël
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA.,Department of Diagnostic and Interventional Radiology, School of Medicine & Klinikum rechts der Isar, Technical University of Munich, München, Germany
| |
Collapse
|
32
|
Jimenez-Del-Toro O, Aberle C, Bach M, Schaer R, Obmann MM, Flouris K, Konukoglu E, Stieltjes B, Müller H, Depeursinge A. The Discriminative Power and Stability of Radiomics Features With Computed Tomography Variations: Task-Based Analysis in an Anthropomorphic 3D-Printed CT Phantom. Invest Radiol 2021; 56:820-825. [PMID: 34038065 DOI: 10.1097/rli.0000000000000795] [Citation(s) in RCA: 13] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
Abstract
OBJECTIVES The aims of this study were to determine the stability of radiomics features against computed tomography (CT) parameter variations and to study their discriminative power concerning tissue classification using a 3D-printed CT phantom based on real patient data. MATERIALS AND METHODS A radiopaque 3D phantom was developed using real patient data and a potassium iodide solution paper-printing technique. Normal liver tissue and 3 lesion types (benign cyst, hemangioma, and metastasis) were manually annotated in the phantom. The stability and discriminative power of 86 radiomics features were assessed in measurements taken from 240 CT series with 8 parameter variations of reconstruction algorithms, reconstruction kernels, slice thickness, and slice spacing. Pairwise parameter group and pairwise tissue class comparisons were performed using Wilcoxon signed rank tests. RESULTS In total, 19,264 feature stability tests and 8256 discriminative power tests were performed. The 8 CT parameter variation pairwise group comparisons had statistically significant differences on average in 78/86 radiomics features. On the other hand, 84% of the univariate radiomics feature tests had a successful and statistically significant differentiation of the 4 classes of liver tissue. The 86 radiomics features were ranked according to the cumulative sum of successful stability and discriminative power tests. CONCLUSIONS The differences in radiomics feature values obtained from different types of liver tissue are generally greater than the intraclass differences resulting from CT parameter variations.
Collapse
Affiliation(s)
| | - Christoph Aberle
- Department of Radiology, University Hospital Basel, University of Basel, Basel
| | - Michael Bach
- Department of Radiology, University Hospital Basel, University of Basel, Basel
| | - Roger Schaer
- From the University of Applied Sciences Western Switzerland (HES-SO) Valais, Sierre
| | - Markus M Obmann
- Department of Radiology, University Hospital Basel, University of Basel, Basel
| | | | | | - Bram Stieltjes
- Department of Radiology, University Hospital Basel, University of Basel, Basel
| | | | | |
Collapse
|
33
|
Tabatabaei M, Tasorian B, Goyal M, Moini A, Sotoudeh H. Feasibility of Radiomics to Differentiate Coronavirus Disease 2019 (COVID-19) from H1N1 Influenza Pneumonia on Chest Computed Tomography: A Proof of Concept. IRANIAN JOURNAL OF MEDICAL SCIENCES 2021; 46:420-427. [PMID: 34840382 PMCID: PMC8611216 DOI: 10.30476/ijms.2021.88036.1858] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 09/08/2020] [Revised: 01/09/2021] [Accepted: 01/20/2021] [Indexed: 01/19/2023]
Abstract
BACKGROUND Chest computed tomography (CT) plays an essential role in diagnosing coronavirus disease 2019 (COVID-19). However, CT findings are often nonspecific among different viral pneumonia conditions. The differentiation between COVID-19 and influenza can be challenging when seasonal influenza concurs with the COVID-19 pandemic. This study was conducted to test the ability of radiomics-artificial intelligence (AI) to perform this task. METHODS In this retrospective study, chest CT images from 47 patients with COVID-19 (after February 2020) and 19 patients with H1N1 influenza (before September 2019) pneumonia were collected from three hospitals affiliated with Arak University of Medical Sciences, Arak, Iran. All pulmonary lesions were segmented on CT images. Multiple radiomics features were extracted from the lesions and used to develop support-vector machine (SVM), k-nearest neighbor (k-NN), decision tree, neural network, adaptive boosting (AdaBoost), and random forest. RESULTS The patients with COVID-19 and H1N1 influenza were not significantly different in age and sex (P=0.13 and 0.99, respectively). Nonetheless, the average time between initial symptoms/hospitalization and chest CT was shorter in the patients with COVID-19 (P=0.001 and 0.01, respectively). After the implementation of the inclusion and exclusion criteria, 453 pulmonary lesions were included in this study. On the harmonized features, random forest yielded the highest performance (area under the curve=0.97, sensitivity=89%, precision=90%, F1 score=89%, and classification accuracy=89%). CONCLUSION In our preliminary study, radiomics feature extraction, conjoined with AI, especially random forest and neural network, appeared to yield very promising results in the differentiation between COVID-19 and H1N1 influenza on chest CT.
Collapse
Affiliation(s)
- Mohsen Tabatabaei
- Health Information Management, Office of Vice Chancellor for Research, Arak University of Medical Sciences, Arak, Iran
| | - Baharak Tasorian
- Internal Medicine Department, Arak University of Medical Sciences, Arak, Iran
| | - Manu Goyal
- Postdoctoral Research Associate in Medical Imaging at Dartmouth College, Hanover, NH 03755 USA
| | - Abdollatif Moini
- Department of Internal Medicine of Amir Al Momenin Hospital, Arak University of Medical Sciences, Arak, Iran
| | | |
Collapse
|
34
|
Hoye J, Solomon JB, Sauer TJ, Samei E. Quantification of Minimum Detectable Difference in Radiomics Features Across Lesions and CT Imaging Conditions. Acad Radiol 2021; 28:1570-1581. [PMID: 32828664 DOI: 10.1016/j.acra.2020.07.029] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/28/2020] [Revised: 07/06/2020] [Accepted: 07/16/2020] [Indexed: 12/20/2022]
Abstract
RATIONALE AND OBJECTIVES The 3-fold purpose of this study was to (1) develop a method to relate measured differences in radiomics features in different computed tomography (CT) scans to one another and to true feature differences; (2) quantify minimum detectable change in radiomics features based on measured radiomics features from pairs of synthesized CT images acquired under variable CT scan settings, and (3) ascertain and inform the recommendations of the Quantitative Imaging Biomarkers Alliance (QIBA) for nodule volumetry. MATERIALS AND METHODS Images of anthropomorphic lung nodule models were simulated using resolution and noise properties for 297 unique imaging conditions. Nineteen morphology features were calculated from both the segmentation masks derived from the imaged nodules and from ground truth nodules. Analysis was performed to calculate minimum detectable difference of radiomics features as a function of imaging protocols in comparison to QIBA guidelines. RESULTS The minimum detectable differences ranged from 1% to 175% depending on the specific feature and set of imaging protocols. The results showed that QIBA protocol recommendations result in improved minimum detectable difference as compared to the range of possible protocols. The results showed that the minimum detectable differences may be improved from QIBA's current recommendation by further restricting the slice thickness requirement to be between 0.5 mm and 1 mm. CONCLUSION Minimum detectable differences of radiomics features were quantified for lung nodules across a wide range of possible protocols. The results can be used prospectively to inform decision-making about imaging protocols to provide superior quantification of radiomics features.
Collapse
|
35
|
Gong XQ, Tao YY, Wu YK, Liu N, Yu X, Wang R, Zheng J, Liu N, Huang XH, Li JD, Yang G, Wei XQ, Yang L, Zhang XM. Progress of MRI Radiomics in Hepatocellular Carcinoma. Front Oncol 2021; 11:698373. [PMID: 34616673 PMCID: PMC8488263 DOI: 10.3389/fonc.2021.698373] [Citation(s) in RCA: 21] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/21/2021] [Accepted: 08/31/2021] [Indexed: 02/05/2023] Open
Abstract
Background Hepatocellular carcinoma (HCC) is the sixth most common cancer in the world and the third leading cause of cancer-related death. Although the diagnostic scheme of HCC is currently undergoing refinement, the prognosis of HCC is still not satisfactory. In addition to certain factors, such as tumor size and number and vascular invasion displayed on traditional imaging, some histopathological features and gene expression parameters are also important for the prognosis of HCC patients. However, most parameters are based on postoperative pathological examinations, which cannot help with preoperative decision-making. As a new field, radiomics extracts high-throughput imaging data from different types of images to build models and predict clinical outcomes noninvasively before surgery, rendering it a powerful aid for making personalized treatment decisions preoperatively. Objective This study reviewed the workflow of radiomics and the research progress on magnetic resonance imaging (MRI) radiomics in the diagnosis and treatment of HCC. Methods A literature review was conducted by searching PubMed for search of relevant peer-reviewed articles published from May 2017 to June 2021.The search keywords included HCC, MRI, radiomics, deep learning, artificial intelligence, machine learning, neural network, texture analysis, diagnosis, histopathology, microvascular invasion, surgical resection, radiofrequency, recurrence, relapse, transarterial chemoembolization, targeted therapy, immunotherapy, therapeutic response, and prognosis. Results Radiomics features on MRI can be used as biomarkers to determine the differential diagnosis, histological grade, microvascular invasion status, gene expression status, local and systemic therapeutic responses, and prognosis of HCC patients. Conclusion Radiomics is a promising new imaging method. MRI radiomics has high application value in the diagnosis and treatment of HCC.
Collapse
Affiliation(s)
- Xue-Qin Gong
- Medical Imaging Key Laboratory of Sichuan Province, Department of Radiology, Medical Research Center, Affiliated Hospital of North Sichuan Medical College, Nanchong, China
| | - Yun-Yun Tao
- Medical Imaging Key Laboratory of Sichuan Province, Department of Radiology, Medical Research Center, Affiliated Hospital of North Sichuan Medical College, Nanchong, China
| | - Yao-Kun Wu
- Medical Imaging Key Laboratory of Sichuan Province, Department of Radiology, Medical Research Center, Affiliated Hospital of North Sichuan Medical College, Nanchong, China
| | - Ning Liu
- Medical Imaging Key Laboratory of Sichuan Province, Department of Radiology, Medical Research Center, Affiliated Hospital of North Sichuan Medical College, Nanchong, China
| | - Xi Yu
- Medical Imaging Key Laboratory of Sichuan Province, Department of Radiology, Medical Research Center, Affiliated Hospital of North Sichuan Medical College, Nanchong, China
| | - Ran Wang
- Medical Imaging Key Laboratory of Sichuan Province, Department of Radiology, Medical Research Center, Affiliated Hospital of North Sichuan Medical College, Nanchong, China
| | - Jing Zheng
- Medical Imaging Key Laboratory of Sichuan Province, Department of Radiology, Medical Research Center, Affiliated Hospital of North Sichuan Medical College, Nanchong, China
| | - Nian Liu
- Medical Imaging Key Laboratory of Sichuan Province, Department of Radiology, Medical Research Center, Affiliated Hospital of North Sichuan Medical College, Nanchong, China
| | - Xiao-Hua Huang
- Medical Imaging Key Laboratory of Sichuan Province, Department of Radiology, Medical Research Center, Affiliated Hospital of North Sichuan Medical College, Nanchong, China
| | - Jing-Dong Li
- Department of Hepatocellular Surgery, Institute of Hepato-Biliary-Intestinal Disease, Affiliated Hospital of North Sichuan Medical College, Nanchong, China
| | - Gang Yang
- Department of Hepatocellular Surgery, Institute of Hepato-Biliary-Intestinal Disease, Affiliated Hospital of North Sichuan Medical College, Nanchong, China
| | - Xiao-Qin Wei
- School of Medical Imaging, North Sichuan Medical College, Nanchong, China
| | - Lin Yang
- Medical Imaging Key Laboratory of Sichuan Province, Department of Radiology, Medical Research Center, Affiliated Hospital of North Sichuan Medical College, Nanchong, China
| | - Xiao-Ming Zhang
- Medical Imaging Key Laboratory of Sichuan Province, Department of Radiology, Medical Research Center, Affiliated Hospital of North Sichuan Medical College, Nanchong, China
| |
Collapse
|
36
|
Xue C, Yuan J, Lo GG, Chang ATY, Poon DMC, Wong OL, Zhou Y, Chu WCW. Radiomics feature reliability assessed by intraclass correlation coefficient: a systematic review. Quant Imaging Med Surg 2021; 11:4431-4460. [PMID: 34603997 DOI: 10.21037/qims-21-86] [Citation(s) in RCA: 63] [Impact Index Per Article: 21.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/22/2021] [Accepted: 05/17/2021] [Indexed: 12/13/2022]
Abstract
Radiomics research is rapidly growing in recent years, but more concerns on radiomics reliability are also raised. This review attempts to update and overview the current status of radiomics reliability research in the ever expanding medical literature from the perspective of a single reliability metric of intraclass correlation coefficient (ICC). To conduct this systematic review, Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines were followed. After literature search and selection, a total of 481 radiomics studies using CT, PET, or MRI, covering a wide range of subject and disease types, were included for review. In these highly heterogeneous studies, feature reliability to image segmentation was much more investigated than reliability to other factors, such as image acquisition, reconstruction, post-processing, and feature quantification. The reported ICCs also suggested high radiomics feature reliability to image segmentation. Image acquisition was found to introduce much more feature variability than image segmentation, in particular for MRI, based on the reported ICC values. Image post-processing and feature quantification yielded different levels of radiomics reliability and might be used to mitigate image acquisition-induced variability. Some common flaws and pitfalls in ICC use were identified, and suggestions on better ICC use were given. Due to the extremely high study heterogeneities and possible risks of bias, the degree of radiomics feature reliability that has been achieved could not yet be safely synthesized or derived in this review. More future researches on radiomics reliability are warranted.
Collapse
Affiliation(s)
- Cindy Xue
- Medical Physics and Research Department, Hong Kong Sanatorium & Hospital, Happy Valley, Hong Kong, China.,Department of Imaging and Interventional Radiology, Faculty of Medicine, The Chinese University of Hong Kong, Shatin, New Territories, Hong Kong, China
| | - Jing Yuan
- Medical Physics and Research Department, Hong Kong Sanatorium & Hospital, Happy Valley, Hong Kong, China
| | - Gladys G Lo
- Department of Diagnostic & Interventional Radiology, Hong Kong Sanatorium & Hospital, Happy Valley, Hong Kong, China
| | - Amy T Y Chang
- Comprehensive Oncology Centre, Hong Kong Sanatorium & Hospital, Happy Valley, Hong Kong, China
| | - Darren M C Poon
- Comprehensive Oncology Centre, Hong Kong Sanatorium & Hospital, Happy Valley, Hong Kong, China
| | - Oi Lei Wong
- Medical Physics and Research Department, Hong Kong Sanatorium & Hospital, Happy Valley, Hong Kong, China
| | - Yihang Zhou
- Medical Physics and Research Department, Hong Kong Sanatorium & Hospital, Happy Valley, Hong Kong, China
| | - Winnie C W Chu
- Department of Imaging and Interventional Radiology, Faculty of Medicine, The Chinese University of Hong Kong, Shatin, New Territories, Hong Kong, China
| |
Collapse
|
37
|
Mahmoudi S, Martin SS, Ackermann J, Zhdanovich Y, Koch I, Vogl TJ, Albrecht MH, Lenga L, Bernatz S. Potential of high dimensional radiomic features to assess blood components in intraaortic vessels in non-contrast CT scans. BMC Med Imaging 2021; 21:123. [PMID: 34384385 PMCID: PMC8359593 DOI: 10.1186/s12880-021-00654-9] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/03/2021] [Accepted: 07/30/2021] [Indexed: 11/10/2022] Open
Abstract
Background To assess the potential of radiomic features to quantify components of blood in intraaortic vessels to non-invasively predict moderate-to-severe anemia in non-contrast enhanced CT scans. Methods One hundred patients (median age, 69 years; range, 19–94 years) who received CT scans of the thoracolumbar spine and blood-testing for hemoglobin and hematocrit levels ± 24 h between 08/2018 and 11/2019 were retrospectively included. Intraaortic blood was segmented using a spherical volume of interest of 1 cm diameter with consecutive radiomic analysis applying PyRadiomics software. Feature selection was performed applying analysis of correlation and collinearity. The final feature set was obtained to differentiate moderate-to-severe anemia. Random forest machine learning was applied and predictive performance was assessed. A decision-tree was obtained to propose a cut-off value of CT Hounsfield units (HU). Results High correlation with hemoglobin and hematocrit levels was shown for first-order radiomic features (p < 0.001 to p = 0.032). The top 3 features showed high correlation to hemoglobin values (p) and minimal collinearity (r) to the top ranked feature Median (p < 0.001), Energy (p = 0.002, r = 0.387), Minimum (p = 0.032, r = 0.437). Median (p < 0.001) and Minimum (p = 0.003) differed in moderate-to-severe anemia compared to non-anemic state. Median yielded superiority to the combination of Median and Minimum (p(AUC) = 0.015, p(precision) = 0.017, p(accuracy) = 0.612) in the predictive performance employing random forest analysis. A Median HU value ≤ 36.5 indicated moderate-to-severe anemia (accuracy = 0.90, precision = 0.80). Conclusions First-order radiomic features correlate with hemoglobin levels and may be feasible for the prediction of moderate-to-severe anemia. High dimensional radiomic features did not aid augmenting the data in our exemplary use case of intraluminal blood component assessment. Trial registration Retrospectively registered. Supplementary Information The online version contains supplementary material available at 10.1186/s12880-021-00654-9.
Collapse
Affiliation(s)
- Scherwin Mahmoudi
- Department of Diagnostic and Interventional Radiology, University Hospital Frankfurt, Theodor-Stern-Kai 7, 60590, Frankfurt am Main, Germany
| | - Simon S Martin
- Department of Diagnostic and Interventional Radiology, University Hospital Frankfurt, Theodor-Stern-Kai 7, 60590, Frankfurt am Main, Germany
| | - Jörg Ackermann
- Department of Molecular Bioinformatics, Institute of Computer Science, Johann Wolfgang Goethe-University, Robert-Mayer-Str. 11-15, 60325, Frankfurt am Main, Germany
| | - Yauheniya Zhdanovich
- Department of Molecular Bioinformatics, Institute of Computer Science, Johann Wolfgang Goethe-University, Robert-Mayer-Str. 11-15, 60325, Frankfurt am Main, Germany
| | - Ina Koch
- Department of Molecular Bioinformatics, Institute of Computer Science, Johann Wolfgang Goethe-University, Robert-Mayer-Str. 11-15, 60325, Frankfurt am Main, Germany
| | - Thomas J Vogl
- Department of Diagnostic and Interventional Radiology, University Hospital Frankfurt, Theodor-Stern-Kai 7, 60590, Frankfurt am Main, Germany
| | - Moritz H Albrecht
- Department of Diagnostic and Interventional Radiology, University Hospital Frankfurt, Theodor-Stern-Kai 7, 60590, Frankfurt am Main, Germany
| | - Lukas Lenga
- Department of Diagnostic and Interventional Radiology, University Hospital Frankfurt, Theodor-Stern-Kai 7, 60590, Frankfurt am Main, Germany
| | - Simon Bernatz
- Department of Diagnostic and Interventional Radiology, University Hospital Frankfurt, Theodor-Stern-Kai 7, 60590, Frankfurt am Main, Germany.
| |
Collapse
|
38
|
Intra-scan inter-tissue variability can help harmonize radiomics features in CT. Eur Radiol 2021; 32:783-792. [PMID: 34363133 DOI: 10.1007/s00330-021-08154-8] [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: 12/28/2020] [Revised: 06/03/2021] [Accepted: 06/14/2021] [Indexed: 10/20/2022]
Abstract
OBJECTIVE We studied the repeatability and the relative intra-scan variability across acquisition protocols in CT using phantom and unenhanced abdominal series. METHODS We used 17 CT scans from the Credence Cartridge Radiomics Phantom database and 20 unenhanced multi-site non-pathologic abdominal patient series for which we measured spleen and liver tissues. We performed multiple measurements in extracting 9 radiomics features. We defined a "tandem" as the measurement of a given tissue (or material) by a given radiomics. For each tandem, we assessed the proportion of the variability attributable to repetitions, acquisition protocols, material, or patient. We analyzed the distribution of the intra-scan correlation between pairs of tandems and checked the impact of correlation coefficient greater than 0.90 in comparing paired and unpaired differences. RESULTS The repeatability of radiomics features depends on the measured material; 56% of tandems were highly repeatable. Histogram-derived radiomics were generally less repeatable. Nearly 60% of relative radiomics measurements had a correlation coefficient higher than 0.90 allowing paired measurements to improve reliability in detecting the difference between two materials. The analysis of liver and spleen tissues showed that measurement variability was negligible with respect to other variabilities. As for phantom data, we found that gray level zone length matrix (GLZLM)-derived radiomics and gray level co-occurrence matrix (GLCM)-derived radiomics were the most correlating features. For these features, relative intra-scan measurements improved the detection of different materials or tissues. CONCLUSIONS We identified radiomics features for which the intra-scan measurements between tissues are linearly correlated. This property represents an opportunity to improve tissue characterization and inter-site harmonization. KEY POINTS • The repeatability of radiomics features on CT depends on the measured material or tissue. • Some tandems of radiomics features/tissues are linearly affected by the variability of acquisition protocols on CT. • Relative intra-scan measurements are an opportunity for improving quantitative imaging on CT.
Collapse
|
39
|
Impact of Lesion Delineation and Intensity Quantisation on the Stability of Texture Features from Lung Nodules on CT: A Reproducible Study. Diagnostics (Basel) 2021; 11:diagnostics11071224. [PMID: 34359305 PMCID: PMC8304812 DOI: 10.3390/diagnostics11071224] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/29/2021] [Revised: 06/28/2021] [Accepted: 06/28/2021] [Indexed: 12/12/2022] Open
Abstract
Computer-assisted analysis of three-dimensional imaging data (radiomics) has received a lot of research attention as a possible means to improve the management of patients with lung cancer. Building robust predictive models for clinical decision making requires the imaging features to be stable enough to changes in the acquisition and extraction settings. Experimenting on 517 lung lesions from a cohort of 207 patients, we assessed the stability of 88 texture features from the following classes: first-order (13 features), Grey-level Co-Occurrence Matrix (24), Grey-level Difference Matrix (14), Grey-level Run-length Matrix (16), Grey-level Size Zone Matrix (16) and Neighbouring Grey-tone Difference Matrix (five). The analysis was based on a public dataset of lung nodules and open-access routines for feature extraction, which makes the study fully reproducible. Our results identified 30 features that had good or excellent stability relative to lesion delineation, 28 to intensity quantisation and 18 to both. We conclude that selecting the right set of imaging features is critical for building clinical predictive models, particularly when changes in lesion delineation and/or intensity quantisation are involved.
Collapse
|
40
|
Mahmood U, Apte A, Kanan C, Bates DDB, Corrias G, Manneli L, Oh JH, Erdi YE, Nguyen J, O'Deasy J, Shukla-Dave A. Quality control of radiomic features using 3D-printed CT phantoms. J Med Imaging (Bellingham) 2021; 8:033505. [PMID: 34222557 PMCID: PMC8240751 DOI: 10.1117/1.jmi.8.3.033505] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/27/2020] [Accepted: 06/04/2021] [Indexed: 01/01/2023] Open
Abstract
Purpose: The lack of standardization in quantitative radiomic measures of tumors seen on computed tomography (CT) scans is generally recognized as an unresolved issue. To develop reliable clinical applications, radiomics must be robust across different CT scan modes, protocols, software, and systems. We demonstrate how custom-designed phantoms, imprinted with human-derived patterns, can provide a straightforward approach to validating longitudinally stable radiomic signature values in a clinical setting. Approach: Described herein is a prototype process to design an anatomically informed 3D-printed radiomic phantom. We used a multimaterial, ultra-high-resolution 3D printer with voxel printing capabilities. Multiple tissue regions of interest (ROIs), from four pancreas tumors, one lung tumor, and a liver background, were extracted from digital imaging and communication in medicine (DICOM) CT exam files and were merged together to develop a multipurpose, circular radiomic phantom (18 cm diameter and 4 cm width). The phantom was scanned 30 times using standard clinical CT protocols to test repeatability. Features that have been found to be prognostic for various diseases were then investigated for their repeatability and reproducibility across different CT scan modes. Results: The structural similarity index between the segment used from the patients' DICOM image and the phantom CT scan was 0.71. The coefficient variation for all assessed radiomic features was < 1.0 % across 30 repeat scans of the phantom. The percent deviation (pDV) from the baseline value, which was the mean feature value determined from repeat scans, increased with the application of the lung convolution kernel, changes to the voxel size, and increases in the image noise. Gray level co-occurrence features, contrast, dissimilarity, and entropy were particularly affected by different scan modes, presenting with pDV > ± 15 % . Conclusions: Previously discovered prognostic and popular radiomic features are variable in practice and need to be interpreted with caution or excluded from clinical implementation. Voxel-based 3D printing can reproduce tissue morphology seen on CT exams. We believe that this is a flexible, yet practical, way to design custom phantoms to validate and compare radiomic metrics longitudinally, over time, and across systems.
Collapse
Affiliation(s)
- Usman Mahmood
- Memorial Sloan Kettering Cancer Center, Department of Medical Physics, New York, United States
| | - Aditya Apte
- Memorial Sloan Kettering Cancer Center, Department of Medical Physics, New York, United States
| | - Christopher Kanan
- Rochester Institute of Technology, Department of Imaging Science, Rochester, New York, United States
| | - David D B Bates
- Memorial Sloan Kettering Cancer Center, Department of Radiology, New York, United States
| | - Giuseppe Corrias
- Memorial Sloan Kettering Cancer Center, Department of Radiology, New York, United States
| | | | - Jung Hun Oh
- Memorial Sloan Kettering Cancer Center, Department of Medical Physics, New York, United States
| | - Yusuf Emre Erdi
- Memorial Sloan Kettering Cancer Center, Department of Medical Physics, New York, United States
| | | | - Joseph O'Deasy
- Memorial Sloan Kettering Cancer Center, Department of Medical Physics, New York, United States
| | - Amita Shukla-Dave
- Memorial Sloan Kettering Cancer Center, Department of Medical Physics, New York, United States.,Memorial Sloan Kettering Cancer Center, Department of Radiology, New York, United States
| |
Collapse
|
41
|
van Dijk LV, Fuller CD. Artificial Intelligence and Radiomics in Head and Neck Cancer Care: Opportunities, Mechanics, and Challenges. Am Soc Clin Oncol Educ Book 2021; 41:1-11. [PMID: 33929877 DOI: 10.1200/edbk_320951] [Citation(s) in RCA: 10] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/19/2022]
Abstract
The advent of large-scale high-performance computing has allowed the development of machine-learning techniques in oncologic applications. Among these, there has been substantial growth in radiomics (machine-learning texture analysis of images) and artificial intelligence (which uses deep-learning techniques for "learning algorithms"); however, clinical implementation has yet to be realized at scale. To improve implementation, opportunities, mechanics, and challenges, models of imaging-enabled artificial intelligence approaches need to be understood by clinicians who make the treatment decisions. This article aims to convey the basic conceptual premises of radiomics and artificial intelligence using head and neck cancer as a use case. This educational overview focuses on approaches for head and neck oncology imaging, detailing current research efforts and challenges to implementation.
Collapse
Affiliation(s)
- Lisanne V van Dijk
- Department of Radiation Oncology, MD Anderson Cancer Center, Houston, TX.,Department of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, Netherlands
| | - Clifton D Fuller
- Department of Radiation Oncology, MD Anderson Cancer Center, Houston, TX
| |
Collapse
|
42
|
Zhao B. Understanding Sources of Variation to Improve the Reproducibility of Radiomics. Front Oncol 2021; 11:633176. [PMID: 33854969 PMCID: PMC8039446 DOI: 10.3389/fonc.2021.633176] [Citation(s) in RCA: 43] [Impact Index Per Article: 14.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/24/2020] [Accepted: 03/01/2021] [Indexed: 12/12/2022] Open
Abstract
Radiomics is the method of choice for investigating the association between cancer imaging phenotype, cancer genotype and clinical outcome prediction in the era of precision medicine. The fast dispersal of this new methodology has benefited from the existing advances of the core technologies involved in radiomics workflow: image acquisition, tumor segmentation, feature extraction and machine learning. However, despite the rapidly increasing body of publications, there is no real clinical use of a developed radiomics signature so far. Reasons are multifaceted. One of the major challenges is the lack of reproducibility and generalizability of the reported radiomics signatures (features and models). Sources of variation exist in each step of the workflow; some are controllable or can be controlled to certain degrees, while others are uncontrollable or even unknown. Insufficient transparency in reporting radiomics studies further prevents translation of the developed radiomics signatures from the bench to the bedside. This review article first addresses sources of variation, which is illustrated using demonstrative examples. Then, it reviews a number of published studies and progresses made to date in the investigation and improvement of feature reproducibility and model performance. Lastly, it discusses potential strategies and practical considerations to reduce feature variability and improve the quality of radiomics study. This review focuses on CT image acquisition, tumor segmentation, quantitative feature extraction, and the disease of lung cancer.
Collapse
Affiliation(s)
- Binsheng Zhao
- Department of Radiology, Columbia University Irving Medical Center, New York, NY, United States
| |
Collapse
|
43
|
Huang K, Rhee DJ, Ger R, Layman R, Yang J, Cardenas CE, Court LE. Impact of slice thickness, pixel size, and CT dose on the performance of automatic contouring algorithms. J Appl Clin Med Phys 2021; 22:168-174. [PMID: 33779037 PMCID: PMC8130223 DOI: 10.1002/acm2.13207] [Citation(s) in RCA: 19] [Impact Index Per Article: 6.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/13/2020] [Revised: 12/12/2020] [Accepted: 01/30/2021] [Indexed: 12/25/2022] Open
Abstract
Purpose To investigate the impact of computed tomography (CT) image acquisition and reconstruction parameters, including slice thickness, pixel size, and dose, on automatic contouring algorithms. Methods Eleven scans from patients with head‐and‐neck cancer were reconstructed with varying slice thicknesses and pixel sizes. CT dose was varied by adding noise using low‐dose simulation software. The impact of these imaging parameters on two in‐house auto‐contouring algorithms, one convolutional neural network (CNN)‐based and one multiatlas‐based system (MACS) was investigated for 183 reconstructed scans. For each algorithm, auto‐contours for organs‐at‐risk were compared with auto‐contours from scans with 3 mm slice thickness, 0.977 mm pixel size, and 100% CT dose using Dice similarity coefficient (DSC), Hausdorff distance (HD), and mean surface distance (MSD). Results Increasing the slice thickness from baseline value of 3 mm gave a progressive reduction in DSC and an increase in HD and MSD on average for all structures. Reducing the CT dose only had a relatively minimal effect on DSC and HD. The rate of change with respect to dose for both auto‐contouring methods is approximately 0. Changes in pixel size had a small effect on DSC and HD for CNN‐based auto‐contouring with differences in DSC being within 0.07. Small structures had larger deviations from the baseline values than large structures for DSC. The relative differences in HD and MSD between the large and small structures were small. Conclusions Auto‐contours can deviate substantially with changes in CT acquisition and reconstruction parameters, especially slice thickness and pixel size. The CNN was less sensitive to changes in pixel size, and dose levels than the MACS. The results contraindicated more restrictive values for the parameters should be used than a typical imaging protocol for head‐and‐neck.
Collapse
Affiliation(s)
- Kai Huang
- The University of Texas MD Anderson Cancer Center UTHealth Graduate School of Biomedical Sciences, Houston, TX, USA.,Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Dong Joo Rhee
- The University of Texas MD Anderson Cancer Center UTHealth Graduate School of Biomedical Sciences, Houston, TX, USA.,Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Rachel Ger
- Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Rick Layman
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Jinzhong Yang
- Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Carlos E Cardenas
- Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Laurence E Court
- Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| |
Collapse
|
44
|
Gang GJ, Deshpande R, Stayman JW. Standardization of histogram- and GLCM-based radiomics in the presence of blur and noise. Phys Med Biol 2021; 66:074004. [PMID: 33721845 PMCID: PMC8607458 DOI: 10.1088/1361-6560/abeea5] [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: 11/12/2022]
Abstract
Radiomics have been extensively investigated as quantitative biomarkers that can enhance the utility of imaging studies and aid the clinical decision making process. A major challenge to the clinical translation of radiomics is their variability as a result of different imaging and reconstruction protocols. In this work, we present a novel radiomics standardization framework capable of modeling and recovering the underlying radiomic feature in images that have been corrupted by the effects of spatial resolution and noise. We focus on two classes of radiomics based on pixel value distributions - i.e., histograms and gray-level co-occurrence matrices. We developed a model that predicts these distributions in the presence of system blur and noise, and used that model to invert these physical effects and recover the underlying distributions. Specifically, the effect of blur on histogram and GLCM is highly image-dependent, while additive noise convolves the histogram/GLCM of the noiseless image with those of the noise. The recovery method therefore consists of two deconvolution operations: the first in the image domain to remove the effect of system blur, the second in the histogram/GLCM domain to remove the effect of noise. The performance of the proposed recovery strategy was investigated using a set of texture phantoms and an emulated CT imaging chain with a range of realistic blur and noise levels. The proposed method was able to obtain histogram and GLCM estimates that closely resemble the ground truth. The method performed well across imaging conditions and significantly lowered the variability associated with different imaging protocols. This improvement also translated to better classification accuracy, where recovered radiomic values results in greater separation of radiomic clusters for two different texture phantoms as compared to values derived from the original blurred and noisy images. In summary, the novel radiomics standardization framework demonstrates high potential for mitigating radiomic variability as a result of the imaging system and can potentially be integrated as a preprocessing step towards more robust and reproducible radiomic models.
Collapse
Affiliation(s)
- Grace Jianan Gang
- Department of Biomedical Engineering, Johns Hopkins University, Traylor Research Building, 720 Rutland Avenue, Baltimore, Maryland, MD 21205, UNITED STATES
| | - Radhika Deshpande
- Department of Biomedical Engineering, Johns Hopkins University, Baltimore, Maryland, UNITED STATES
| | - Joseph Webster Stayman
- Department of Biomedical Engineering, Johns Hopkins University, 720 Rutland Avenue, Baltimore, Maryland, MD 21205, USA, Baltimore, 21205, UNITED STATES
| |
Collapse
|
45
|
Gao L, Li Y, Zhai Z, Liang T, Zhang Q, Xie S, Chen H. Radiomics study on pulmonary infarction mimicking community-acquired pneumonia. CLINICAL RESPIRATORY JOURNAL 2021; 15:661-669. [PMID: 33686798 DOI: 10.1111/crj.13341] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/09/2019] [Revised: 09/13/2020] [Accepted: 02/15/2021] [Indexed: 12/23/2022]
Abstract
INTRODUCTION AND OBJECTIVES Pulmonary infarction (PI) shares similar symptoms and imaging presentations with community-acquired pneumonia (CAP), which might delay diagnosis and lead to devastating consequences. Noncontrast computed tomography (CT) is the first-line examination for the patients with the respiratory symptoms. This study aimed to investigate a radiomics method to differentiate PI from CAP using noncontrast-enhanced CT. METHODS Noncontrast-enhanced CT images of 54 patients with PI and 64 patients with CAP were retrospectively selected. All patients were confirmed using computed tomography pulmonary angiography (CTPA). A radiomics model was built with 18 texture features that showed significant differences between PI and CAP patients. For comparison, a clinical model using clinical biomarkers and an integrated model combining the radiomics and clinical biomarkers were also generated. An experienced radiologist performed diagnoses using the noncontrast-enhanced CT images. The parameters of the models were generated using a training dataset of 61 patients, whereas the performance of the models was evaluated using receiver operating characteristic (ROC) analysis and Harrell's concordance index (C-index) applied to a separate validation dataset of 57 patients. RESULTS The integrated model achieved the best performance (C-index 0.760, sensitivity 0.703, specificity 0.867, positive predictive value [PPV] 0.826, and negative predictive value [NPV] 0.765). The radiomics model was better than both the clinical model and the radiologist's interpretations (C-index 0.721, 0.707, 0.665, respectively; sensitivity 0.667, 0.630, 0.593; specificity 0.800, 0.785, 0.733; PPV 0.750, 0.739, 0.667; and NPV 0.727, 0.706, 0.667). CONCLUSIONS Radiomics features generated from noncontrast-enhanced CT images allow PI to be differentiated from CAP with considerable accuracy. The radiomics-based method could provide useful information in clinical practice.
Collapse
Affiliation(s)
- Li Gao
- Department of Radiology, Peking University First Hospital, Beijing, China
| | - Yuze Li
- Center for Biomedical Imaging Research, Department of Biomedical Engineering, School of Medicine, Tsinghua University, Beijing, China
| | - Zhenguo Zhai
- Department of Respiratory and Critical Care Medicine, China-Japan Friendship Hospital, Beijing, China
| | - Tian Liang
- Department of Radiology, China-Japan Friendship Hospital, Beijing, China
| | - Qiang Zhang
- Center for Biomedical Imaging Research, Department of Biomedical Engineering, School of Medicine, Tsinghua University, Beijing, China
| | - Sheng Xie
- Department of Radiology, China-Japan Friendship Hospital, Beijing, China
| | - Huijun Chen
- Center for Biomedical Imaging Research, Department of Biomedical Engineering, School of Medicine, Tsinghua University, Beijing, China
| |
Collapse
|
46
|
Deep Learning Based HPV Status Prediction for Oropharyngeal Cancer Patients. Cancers (Basel) 2021; 13:cancers13040786. [PMID: 33668646 PMCID: PMC7917758 DOI: 10.3390/cancers13040786] [Citation(s) in RCA: 14] [Impact Index Per Article: 4.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/28/2021] [Revised: 02/07/2021] [Accepted: 02/09/2021] [Indexed: 12/30/2022] Open
Abstract
Simple Summary Determination of human papillomavirus (HPV) status for oropharyngeal cancer patients depicts a essential diagnostic factor and is important for treatment decisions. Current histological methods are invasive, time consuming and costly. We tested the ability of deep learning models for HPV status testing based on routinely acquired diagnostic CT images. A network trained for sports video clip classification was modified and then fine tuned for HPV status prediction. In this way, very basic information about image structures is induced into the model before training is started, while still allowing for exploitation of full 3D information in the CT images. Usage of this approach helps the network to cope with a small number of training examples and makes it more robust. For comparison, two other models were trained, one not relying on a pre-training task and another one pre-trained on 2D Data. The pre-trained video model preformed best. Abstract Infection with the human papillomavirus (HPV) has been identified as a major risk factor for oropharyngeal cancer (OPC). HPV-related OPCs have been shown to be more radiosensitive and to have a reduced risk for cancer related death. Hence, the histological determination of HPV status of cancer patients depicts an essential diagnostic factor. We investigated the ability of deep learning models for imaging based HPV status detection. To overcome the problem of small medical datasets, we used a transfer learning approach. A 3D convolutional network pre-trained on sports video clips was fine-tuned, such that full 3D information in the CT images could be exploited. The video pre-trained model was able to differentiate HPV-positive from HPV-negative cases, with an area under the receiver operating characteristic curve (AUC) of 0.81 for an external test set. In comparison to a 3D convolutional neural network (CNN) trained from scratch and a 2D architecture pre-trained on ImageNet, the video pre-trained model performed best. Deep learning models are capable of CT image-based HPV status determination. Video based pre-training has the ability to improve training for 3D medical data, but further studies are needed for verification.
Collapse
|
47
|
A comparative study to evaluate CT-based semantic and radiomic features in preoperative diagnosis of invasive pulmonary adenocarcinomas manifesting as subsolid nodules. Sci Rep 2021; 11:66. [PMID: 33462251 PMCID: PMC7814025 DOI: 10.1038/s41598-020-79690-4] [Citation(s) in RCA: 12] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/02/2020] [Accepted: 12/08/2020] [Indexed: 12/21/2022] Open
Abstract
This study aims to predict the histological invasiveness of pulmonary adenocarcinoma spectrum manifesting with subsolid nodules ≦ 3 cm using the preoperative CT-based radiomic approach. A total of 186 patients with 203 SSNs confirmed with surgically pathologic proof were retrospectively reviewed from February 2016 to March 2020 for training cohort modeling. The validation cohort included 50 subjects with 57 SSNs confirmed with surgically pathologic proof from April 2020 to August 2020. CT-based radiomic features were extracted using an open-source software with 3D nodular volume segmentation manually. The association between CT-based conventional features/selected radiomic features and histological invasiveness of pulmonary adenocarcinoma status were analyzed. Diagnostic models were built using conventional CT features, selected radiomic CT features and experienced radiologists. In addition, we compared diagnostic performance between radiomic CT feature, conventional CT features and experienced radiologists. In the training cohort of 203 SSNs, there were 106 invasive lesions and 97 pre-invasive lesions. Logistic analysis identified that a selected radiomic feature named GLCM_Entropy_log10 was the predictor for histological invasiveness of pulmonary adenocarcinoma spectrum (OR: 38.081, 95% CI 2.735–530.309, p = 0.007). The sensitivity and specificity for predicting histological invasiveness of pulmonary adenocarcinoma spectrum using the cutoff value of CT-based radiomic parameter (GLCM_Entropy_log10) were 84.8% and 79.2% respectively (area under curve, 0.878). The diagnostic model of CT-based radiomic feature was compared to those of conventional CT feature (morphologic and quantitative) and three experienced radiologists. The diagnostic performance of radiomic feature was similar to those of the quantitative CT feature (nodular size and solid component, both lung and mediastinal window) in prediction invasive pulmonary adenocarcinoma (IPA). The AUC value of CT radiomic feature was higher than those of conventional CT morphologic feature and three experienced radiologists. The c-statistic of the training cohort model was 0.878 (95% CI 0.831–0.925) and 0.923 (0.854–0.991) in the validation cohort. Calibration was good in both cohorts. The diagnostic performance of CT-based radiomic feature is not inferior to solid component (lung and mediastinal window) and nodular size for predicting invasiveness. CT-based radiomic feature and nomogram could help to differentiate IPA lesions from preinvasive lesions in the both independent training and validation cohorts. The nomogram may help clinicians with decision making in the management of subsolid nodules.
Collapse
|
48
|
Beaumont H, Iannessi A, Bertrand AS, Cucchi JM, Lucidarme O. Harmonization of radiomic feature distributions: impact on classification of hepatic tissue in CT imaging. Eur Radiol 2021; 31:6059-6068. [PMID: 33459855 DOI: 10.1007/s00330-020-07641-8] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/01/2020] [Revised: 11/23/2020] [Accepted: 12/17/2020] [Indexed: 12/15/2022]
Abstract
OBJECTIVES Following the craze for radiomic features (RF), their lack of reliability raised the question of the generalizability of classification models. Inter-site harmonization of images therefore becomes a central issue. We compared RF harmonization processing designed to detect liver diseases in CT images. METHODS We retrospectively analyzed 76 multi-center portal CT series of non-diseased (NDL) and diseased liver (DL) patients. In each series, we positioned volumes of interest in spleen and liver, then extracted 9 RF (histogram and texture). We evaluated two RF harmonization approaches. First, in each series, we computed the Z-score of liver measurements based on those computed in the spleen. Second, we evaluated the ComBat method according to each imaging center; parameters were computed in the spleen and applied to the liver. We compared RF distributions and classification performances before/after harmonization. We classified NDL versus spleen and versus DL tissues. RESULTS The RF distributions were all different between liver and spleen (p < 0.05). The Z-score harmonization outperformed for the detection of liver versus spleen: AUC = 93.1% (p < 0.001). For the detection of DL versus NDL, in a case/control setting, we found no differences between the harmonizations: mean AUC = 73.6% (p = 0.49). Using the whole datasets, the performances were improved using ComBat (p = 0.05) AUC = 82.4% and degraded with Z-score AUC = 67.4% (p = 0.008). CONCLUSIONS Data harmonization requires to first focus on data structuring to not degrade the performances of subsequent classifications. Liver tissue classification after harmonization of spleen-based RF is a promising strategy for improving the detection of DL tissue. KEY POINTS • Variability of acquisition parameter makes radiomics of CT features non-reproducible. • Data harmonization can help circumvent the inter-site variability of acquisition protocols. • Inter-site harmonization must be carefully implemented and requires designing consistent data sets.
Collapse
Affiliation(s)
| | | | | | - Jean Michel Cucchi
- Centre Hospitalier Princesse Grâce, Avenue Pasteur, 98000, Monaco, Monaco
| | | |
Collapse
|
49
|
AIM in Oncology. Artif Intell Med 2021. [DOI: 10.1007/978-3-030-58080-3_94-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/20/2022]
|
50
|
Zhang L, Karimzadeh M, Welch M, McIntosh C, Wang B. Analytics methods and tools for integration of biomedical data in medicine. Artif Intell Med 2021. [DOI: 10.1016/b978-0-12-821259-2.00007-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/30/2022]
|