1
|
Cao R, Fu L, Huang B, Liu Y, Wang X, Liu J, Wang H, Jiang X, Yang Z, Sha X, Zhao N. Brain metastasis magnetic resonance imaging-based deep learning for predicting epidermal growth factor receptor ( EGFR) mutation and subtypes in metastatic non-small cell lung cancer. Quant Imaging Med Surg 2024; 14:4749-4762. [PMID: 39022238 PMCID: PMC11250349 DOI: 10.21037/qims-23-1744] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/08/2023] [Accepted: 05/06/2024] [Indexed: 07/20/2024]
Abstract
Background The preoperative identification of epidermal growth factor receptor (EGFR) mutations and subtypes based on magnetic resonance imaging (MRI) of brain metastases (BM) is necessary to facilitate individualized therapy. This study aimed to develop a deep learning model to preoperatively detect EGFR mutations and identify the location of EGFR mutations in patients with non-small cell lung cancer (NSCLC) and BM. Methods We included 160 and 72 patients who underwent contrast-enhanced T1-weighted (T1w-CE) and T2-weighted (T2W) MRI at Liaoning Cancer Hospital and Institute (center 1) and Shengjing Hospital of China Medical University (center 2) to form a training cohort and an external validation cohort, respectively. A multiscale feature fusion network (MSF-Net) was developed by adaptively integrating features based on different stages of residual network (ResNet) 50 and by introducing channel and spatial attention modules. The external validation set from center 2 was used to assess the performance of MSF-Net and to compare it with that of handcrafted radiomics features. Receiver operating characteristic (ROC) curves, accuracy, precision, recall, and F1-score were used to evaluate the effectiveness of the models. Gradient-weighted class activation mapping (Grad-CAM) was used to demonstrate the attention of the MSF-Net model. Results The developed MSF-Net generated a better diagnostic performance than did the handcrafted radiomics in terms of the microaveraged area under the curve (AUC) (MSF-Net: 0.91; radiomics: 0.80) and macroaveraged AUC (MSF-Net: 0.90; radiomics: 0.81) for predicting EGFR mutations and subtypes. Conclusions This study provides an end-to-end and noninvasive imaging tool for the preoperative prediction of EGFR mutation status and subtypes based on BM, which may be helpful for facilitating individualized clinical treatment plans.
Collapse
Affiliation(s)
- Ran Cao
- School of Intelligent Medicine, China Medical University, Shenyang, China
- Department of Biomedical Engineering, School of Information Science and Technology, Fudan University, Shanghai, China
| | - Langyuan Fu
- School of Intelligent Medicine, China Medical University, Shenyang, China
| | - Bo Huang
- Department of Pathology, Cancer Hospital of China Medical University, Liaoning Cancer Hospital and Institute, Shenyang, China
| | - Yan Liu
- School of Intelligent Medicine, China Medical University, Shenyang, China
| | - Xiaoyu Wang
- Department of Radiology, Cancer Hospital of China Medical University, Liaoning Cancer Hospital and Institute, Shenyang, China
| | - Jiani Liu
- Department of Radiology, Cancer Hospital of China Medical University, Liaoning Cancer Hospital and Institute, Shenyang, China
| | - Haotian Wang
- Department of Radiology, Cancer Hospital of China Medical University, Liaoning Cancer Hospital and Institute, Shenyang, China
| | - Xiran Jiang
- School of Intelligent Medicine, China Medical University, Shenyang, China
| | - Zhiguang Yang
- Department of Radiology, Shengjing Hospital of China Medical University, Shenyang, China
| | - Xianzheng Sha
- School of Intelligent Medicine, China Medical University, Shenyang, China
| | - Nannan Zhao
- Department of Radiology, Cancer Hospital of China Medical University, Liaoning Cancer Hospital and Institute, Shenyang, China
| |
Collapse
|
2
|
Zheng J, Zhang Z, Wang J, Zhao R, Liu S, Yang G, Liu Z, Deng Z. Metabolic syndrome prediction model using Bayesian optimization and XGBoost based on traditional Chinese medicine features. Heliyon 2023; 9:e22727. [PMID: 38125549 PMCID: PMC10730568 DOI: 10.1016/j.heliyon.2023.e22727] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/31/2023] [Revised: 11/16/2023] [Accepted: 11/17/2023] [Indexed: 12/23/2023] Open
Abstract
Metabolic syndrome (MetS) has a high prevalence and is prone to many complications. However, current MetS diagnostic methods require blood tests that are not conducive to self-testing, so a user-friendly and accurate method for predicting MetS is needed to facilitate early detection and treatment. In this study, a MetS prediction model based on a simple, small number of Traditional Chinese Medicine (TCM) clinical indicators and biological indicators combined with machine learning algorithms is investigated. Electronic medical record data from 2040 patients who visited outpatient clinics at Guangdong Chinese medicine hospitals from 2020 to 2021 were used to investigate the fusion of Bayesian optimization (BO) and eXtreme gradient boosting (XGBoost) in order to create a BO-XGBoost model for screening nineteen key features in three categories: individual bio-information, TCM indicators, and TCM habits that influence MetS prediction. Subsequently, the predictive diagnostic model for MetS was developed. The experimental results revealed that the model proposed in this paper achieved values of 93.35 %, 90.67 %, 80.40 %, and 0.920 for the F1, sensitivity, FRS, and AUC metrics, respectively. These values outperformed those of the seven other tested machine learning models. Finally, this study developed an intelligent prediction application for MetS based on the proposed model, which can be utilized by ordinary users to perform self-diagnosis through a web-based questionnaire, thereby accomplishing the objective of early detection and intervention for MetS.
Collapse
Affiliation(s)
- Jianhua Zheng
- College of Information Science and Technology, Zhongkai University of Agriculture and Engineering, Guangzhou, 510225, China
- Guangdong Provincial Key Laboratory of Traditional Chinese Medicine Informatization, Guangzhou, 510630, China
| | - Zihao Zhang
- College of Information Science and Technology, Zhongkai University of Agriculture and Engineering, Guangzhou, 510225, China
| | - Jinhe Wang
- Xiyuan Hospital of China Academy of Chinese Medical Sciences, Beijing, 100091, China
| | - Ruolin Zhao
- College of Information Science and Technology, Zhongkai University of Agriculture and Engineering, Guangzhou, 510225, China
| | - Shuangyin Liu
- College of Information Science and Technology, Zhongkai University of Agriculture and Engineering, Guangzhou, 510225, China
- Guangdong Provincial Key Laboratory of Traditional Chinese Medicine Informatization, Guangzhou, 510630, China
| | - Gaolin Yang
- College of Information Science and Technology, Zhongkai University of Agriculture and Engineering, Guangzhou, 510225, China
| | - Zhengjie Liu
- Guangdong Provincial Hospital of Chinese Medicine, Guangzhou, 510120, China
- The Second Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangzhou, 510120, China
| | - Zhengyuan Deng
- College of Information Science and Technology, Zhongkai University of Agriculture and Engineering, Guangzhou, 510225, China
- Network and Educational Technology Center, Jinan University, Guangzhou, 510630, China
| |
Collapse
|
3
|
Zhou Z, Wang M, Zhao R, Shao Y, Xing L, Qiu Q, Yin Y. A multi-task deep learning model for EGFR genotyping prediction and GTV segmentation of brain metastasis. J Transl Med 2023; 21:788. [PMID: 37936137 PMCID: PMC10629110 DOI: 10.1186/s12967-023-04681-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/27/2023] [Accepted: 10/29/2023] [Indexed: 11/09/2023] Open
Abstract
BACKGROUND The precise prediction of epidermal growth factor receptor (EGFR) mutation status and gross tumor volume (GTV) segmentation are crucial goals in computer-aided lung adenocarcinoma brain metastasis diagnosis. However, these two tasks present continuous difficulties due to the nonuniform intensity distributions, ambiguous boundaries, and variable shapes of brain metastasis (BM) in MR images.The existing approaches for tackling these challenges mainly rely on single-task algorithms, which overlook the interdependence between these two tasks. METHODS To comprehensively address these challenges, we propose a multi-task deep learning model that simultaneously enables GTV segmentation and EGFR subtype classification. Specifically, a multi-scale self-attention encoder that consists of a convolutional self-attention module is designed to extract the shared spatial and global information for a GTV segmentation decoder and an EGFR genotype classifier. Then, a hybrid CNN-Transformer classifier consisting of a convolutional block and a Transformer block is designed to combine the global and local information. Furthermore, the task correlation and heterogeneity issues are solved with a multi-task loss function, aiming to balance the above two tasks by incorporating segmentation and classification loss functions with learnable weights. RESULTS The experimental results demonstrate that our proposed model achieves excellent performance, surpassing that of single-task learning approaches. Our proposed model achieves a mean Dice score of 0.89 for GTV segmentation and an EGFR genotyping accuracy of 0.88 on an internal testing set, and attains an accuracy of 0.81 in the EGFR genotype prediction task and an average Dice score of 0.85 in the GTV segmentation task on the external testing set. This shows that our proposed method has outstanding performance and generalization. CONCLUSION With the introduction of an efficient feature extraction module, a hybrid CNN-Transformer classifier, and a multi-task loss function, the proposed multi-task deep learning network significantly enhances the performance achieved in both GTV segmentation and EGFR genotyping tasks. Thus, the model can serve as a noninvasive tool for facilitating clinical treatment.
Collapse
Affiliation(s)
- Zichun Zhou
- Department of Radiation Oncology and Physics, Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical Sciences, 440 Jiyan Road, Jinan, 250117, Shandong, China
| | - Min Wang
- Department of Radiation Oncology, Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical Sciences, 440 Jiyan Road, Jinan, 250117, Shandong, China
| | - Rubin Zhao
- Department of Radiation Oncology and Technology, Linyi People's Hospital, 27 Jiefang Road, Linyi, 276003, Shandong, China
| | - Yan Shao
- Shanghai Chest Hospital, School of Medicine, Shanghai Jiaotong University, 241 Huaihai West Road, Shanghai, 200030, China
| | - Ligang Xing
- Department of Radiation Oncology, Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical Sciences, 440 Jiyan Road, Jinan, 250117, Shandong, China
| | - Qingtao Qiu
- Department of Radiation Oncology and Physics, Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical Sciences, 440 Jiyan Road, Jinan, 250117, Shandong, China.
| | - Yong Yin
- Department of Radiation Oncology and Physics, Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical Sciences, 440 Jiyan Road, Jinan, 250117, Shandong, China.
| |
Collapse
|
4
|
Formica C, Bonanno L, Giambò FM, Maresca G, Latella D, Marra A, Cucinotta F, Bonanno C, Lombardo M, Tomarchio O, Quartarone A, Marino S, Calabrò RS, Lo Buono V. Paving the Way for Predicting the Progression of Cognitive Decline: The Potential Role of Machine Learning Algorithms in the Clinical Management of Neurodegenerative Disorders. J Pers Med 2023; 13:1386. [PMID: 37763152 PMCID: PMC10533011 DOI: 10.3390/jpm13091386] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/03/2023] [Revised: 09/05/2023] [Accepted: 09/13/2023] [Indexed: 09/29/2023] Open
Abstract
Alzheimer's disease (AD) is the most common form of neurodegenerative disorder. The prodromal phase of AD is mild cognitive impairment (MCI). The capacity to predict the transitional phase from MCI to AD represents a challenge for the scientific community. The adoption of artificial intelligence (AI) is useful for diagnostic, predictive analysis starting from the clinical epidemiology of neurodegenerative disorders. We propose a Machine Learning Model (MLM) where the algorithms were trained on a set of neuropsychological, neurophysiological, and clinical data to predict the diagnosis of cognitive decline in both MCI and AD patients. METHODS We built a dataset with clinical and neuropsychological data of 4848 patients, of which 2156 had a diagnosis of AD, and 2684 of MCI, for the Machine Learning Model, and 60 patients were enrolled for the test dataset. We trained an ML algorithm using RoboMate software based on the training dataset, and then calculated its accuracy using the test dataset. RESULTS The Receiver Operating Characteristic (ROC) analysis revealed that diagnostic accuracy was 86%, with an appropriate cutoff value of 1.5; sensitivity was 72%; and specificity reached a value of 91% for clinical data prediction with MMSE. CONCLUSION This method may support clinicians to provide a second opinion concerning high prognostic power in the progression of cognitive impairment. The MLM used in this study is based on big data that were confirmed in enrolled patients and given a credibility about the presence of determinant risk factors also supported by a cognitive test score.
Collapse
Affiliation(s)
- Caterina Formica
- IRCCS Centro Neurolesi “Bonino Pulejo”, 98124 Messina, Italy; (C.F.); (L.B.); (F.M.G.); (G.M.); (A.M.); (F.C.); (C.B.); (A.Q.); (S.M.); (R.S.C.); (V.L.B.)
| | - Lilla Bonanno
- IRCCS Centro Neurolesi “Bonino Pulejo”, 98124 Messina, Italy; (C.F.); (L.B.); (F.M.G.); (G.M.); (A.M.); (F.C.); (C.B.); (A.Q.); (S.M.); (R.S.C.); (V.L.B.)
| | - Fabio Mauro Giambò
- IRCCS Centro Neurolesi “Bonino Pulejo”, 98124 Messina, Italy; (C.F.); (L.B.); (F.M.G.); (G.M.); (A.M.); (F.C.); (C.B.); (A.Q.); (S.M.); (R.S.C.); (V.L.B.)
| | - Giuseppa Maresca
- IRCCS Centro Neurolesi “Bonino Pulejo”, 98124 Messina, Italy; (C.F.); (L.B.); (F.M.G.); (G.M.); (A.M.); (F.C.); (C.B.); (A.Q.); (S.M.); (R.S.C.); (V.L.B.)
| | - Desiree Latella
- IRCCS Centro Neurolesi “Bonino Pulejo”, 98124 Messina, Italy; (C.F.); (L.B.); (F.M.G.); (G.M.); (A.M.); (F.C.); (C.B.); (A.Q.); (S.M.); (R.S.C.); (V.L.B.)
| | - Angela Marra
- IRCCS Centro Neurolesi “Bonino Pulejo”, 98124 Messina, Italy; (C.F.); (L.B.); (F.M.G.); (G.M.); (A.M.); (F.C.); (C.B.); (A.Q.); (S.M.); (R.S.C.); (V.L.B.)
| | - Fabio Cucinotta
- IRCCS Centro Neurolesi “Bonino Pulejo”, 98124 Messina, Italy; (C.F.); (L.B.); (F.M.G.); (G.M.); (A.M.); (F.C.); (C.B.); (A.Q.); (S.M.); (R.S.C.); (V.L.B.)
| | - Carmen Bonanno
- IRCCS Centro Neurolesi “Bonino Pulejo”, 98124 Messina, Italy; (C.F.); (L.B.); (F.M.G.); (G.M.); (A.M.); (F.C.); (C.B.); (A.Q.); (S.M.); (R.S.C.); (V.L.B.)
| | | | - Orazio Tomarchio
- Department of Electrical Engineering, Electronics and Computer Science, University of Catania, 95131 Catania, Italy;
| | - Angelo Quartarone
- IRCCS Centro Neurolesi “Bonino Pulejo”, 98124 Messina, Italy; (C.F.); (L.B.); (F.M.G.); (G.M.); (A.M.); (F.C.); (C.B.); (A.Q.); (S.M.); (R.S.C.); (V.L.B.)
| | - Silvia Marino
- IRCCS Centro Neurolesi “Bonino Pulejo”, 98124 Messina, Italy; (C.F.); (L.B.); (F.M.G.); (G.M.); (A.M.); (F.C.); (C.B.); (A.Q.); (S.M.); (R.S.C.); (V.L.B.)
| | - Rocco Salvatore Calabrò
- IRCCS Centro Neurolesi “Bonino Pulejo”, 98124 Messina, Italy; (C.F.); (L.B.); (F.M.G.); (G.M.); (A.M.); (F.C.); (C.B.); (A.Q.); (S.M.); (R.S.C.); (V.L.B.)
| | - Viviana Lo Buono
- IRCCS Centro Neurolesi “Bonino Pulejo”, 98124 Messina, Italy; (C.F.); (L.B.); (F.M.G.); (G.M.); (A.M.); (F.C.); (C.B.); (A.Q.); (S.M.); (R.S.C.); (V.L.B.)
| |
Collapse
|