Yixin Wang1,2,3, Jinwei Lang1,2, Joey Zhaoyu Zuo1,2, Yaqin Dong4, Zongtao Hu1,3, Xiuli Xu3, Yongkang Zhang3, Qinjie Wang1,2, Lizhuang Yang1,2,3, Stephen T C Wong5, Hongzhi Wang6,7,8, Hai Li9,10,11. 1. Anhui Province Key Laboratory of Medical Physics and Technology, Institute of Health and Medical Technology, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei, 230031, People's Republic of China. 2. University of Science and Technology of China, Hefei, 230026, People's Republic of China. 3. Department of Oncology, Hefei Cancer Hospital, Chinese Academy of Sciences, Hefei, 230031, People's Republic of China. 4. Department of Radiation Oncology, The First Affiliated Hospital of Anhui Medical University, Hefei, 230022, People's Republic of China. 5. Department of Systems Medicine and Bioengineering, Houston Methodist Cancer Center, Weill Cornell Medical College, Houston, TX, 77030, USA. 6. Anhui Province Key Laboratory of Medical Physics and Technology, Institute of Health and Medical Technology, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei, 230031, People's Republic of China. wanghz@hfcas.ac.cn. 7. University of Science and Technology of China, Hefei, 230026, People's Republic of China. wanghz@hfcas.ac.cn. 8. Department of Oncology, Hefei Cancer Hospital, Chinese Academy of Sciences, Hefei, 230031, People's Republic of China. wanghz@hfcas.ac.cn. 9. Anhui Province Key Laboratory of Medical Physics and Technology, Institute of Health and Medical Technology, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei, 230031, People's Republic of China. hli@cmpt.ac.cn. 10. University of Science and Technology of China, Hefei, 230026, People's Republic of China. hli@cmpt.ac.cn. 11. Department of Oncology, Hefei Cancer Hospital, Chinese Academy of Sciences, Hefei, 230031, People's Republic of China. hli@cmpt.ac.cn.
Abstract
OBJECTIVE: To develop and validate a pretreatment magnetic resonance imaging (MRI)-based radiomic-clinical model to assess the treatment response of whole-brain radiotherapy (WBRT) by using SHapley Additive exPlanations (SHAP), which is derived from game theory, and can explain the output of different machine learning models. METHODS: We retrospectively enrolled 228 patients with brain metastases from two medical centers (184 in the training cohort and 44 in the validation cohort). Treatment responses of patients were categorized as a non-responding group vs. a responding group according to the Response Assessment in Neuro-Oncology Brain Metastases (RANO-BM) criteria. For each tumor, 960 features were extracted from the MRI sequence. The least absolute shrinkage and selection operator (LASSO) was used for feature selection. A support vector machine (SVM) model incorporating clinical factors and radiomic features wase used to construct the radiomic-clinical model. SHAP method explained the SVM model by prioritizing the importance of features, in terms of assessment contribution. RESULTS: Three radiomic features and three clinical factors were identified to build the model. Radiomic-clinical model yielded AUCs of 0.928 (95%CI 0.901-0.949) and 0.851 (95%CI 0.816-0.886) for assessing the treatment response in the training cohort and validation cohort, respectively. SHAP summary plot illustrated the feature's value affected the feature's impact attributed to model, and SHAP force plot showed the integration of features' impact attributed to individual response. CONCLUSION: The radiomic-clinical model with the SHAP method can be useful for assessing the treatment response of WBRT and may assist clinicians in directing personalized WBRT strategies in an understandable manner. KEY POINTS: • Radiomic-clinical model can be useful for assessing the treatment response of WBRT. • SHAP could explain and visualize radiomic-clinical machine learning model in a clinician-friendly way.
OBJECTIVE: To develop and validate a pretreatment magnetic resonance imaging (MRI)-based radiomic-clinical model to assess the treatment response of whole-brain radiotherapy (WBRT) by using SHapley Additive exPlanations (SHAP), which is derived from game theory, and can explain the output of different machine learning models. METHODS: We retrospectively enrolled 228 patients with brain metastases from two medical centers (184 in the training cohort and 44 in the validation cohort). Treatment responses of patients were categorized as a non-responding group vs. a responding group according to the Response Assessment in Neuro-Oncology Brain Metastases (RANO-BM) criteria. For each tumor, 960 features were extracted from the MRI sequence. The least absolute shrinkage and selection operator (LASSO) was used for feature selection. A support vector machine (SVM) model incorporating clinical factors and radiomic features wase used to construct the radiomic-clinical model. SHAP method explained the SVM model by prioritizing the importance of features, in terms of assessment contribution. RESULTS: Three radiomic features and three clinical factors were identified to build the model. Radiomic-clinical model yielded AUCs of 0.928 (95%CI 0.901-0.949) and 0.851 (95%CI 0.816-0.886) for assessing the treatment response in the training cohort and validation cohort, respectively. SHAP summary plot illustrated the feature's value affected the feature's impact attributed to model, and SHAP force plot showed the integration of features' impact attributed to individual response. CONCLUSION: The radiomic-clinical model with the SHAP method can be useful for assessing the treatment response of WBRT and may assist clinicians in directing personalized WBRT strategies in an understandable manner. KEY POINTS: • Radiomic-clinical model can be useful for assessing the treatment response of WBRT. • SHAP could explain and visualize radiomic-clinical machine learning model in a clinician-friendly way.
Authors: Paul W Sperduto; Brian Berkey; Laurie E Gaspar; Minesh Mehta; Walter Curran Journal: Int J Radiat Oncol Biol Phys Date: 2007-10-10 Impact factor: 7.038
Authors: Paul D Brown; Karla V Ballman; Jane H Cerhan; S Keith Anderson; Xiomara W Carrero; Anthony C Whitton; Jeffrey Greenspoon; Ian F Parney; Nadia N I Laack; Jonathan B Ashman; Jean-Paul Bahary; Costas G Hadjipanayis; James J Urbanic; Fred G Barker; Elana Farace; Deepak Khuntia; Caterina Giannini; Jan C Buckner; Evanthia Galanis; David Roberge Journal: Lancet Oncol Date: 2017-07-04 Impact factor: 41.316
Authors: Paul W Sperduto; Samuel T Chao; Penny K Sneed; Xianghua Luo; John Suh; David Roberge; Amit Bhatt; Ashley W Jensen; Paul D Brown; Helen Shih; John Kirkpatrick; Amanda Schwer; Laurie E Gaspar; John B Fiveash; Veronica Chiang; Jonathan Knisely; Christina Maria Sperduto; Minesh Mehta Journal: Int J Radiat Oncol Biol Phys Date: 2009-11-26 Impact factor: 7.038
Authors: Sarah B Goldberg; Scott N Gettinger; Amit Mahajan; Anne C Chiang; Roy S Herbst; Mario Sznol; Apostolos John Tsiouris; Justine Cohen; Alexander Vortmeyer; Lucia Jilaveanu; James Yu; Upendra Hegde; Stephanie Speaker; Matthew Madura; Amanda Ralabate; Angel Rivera; Elin Rowen; Heather Gerrish; Xiaopan Yao; Veronica Chiang; Harriet M Kluger Journal: Lancet Oncol Date: 2016-06-03 Impact factor: 41.316
Authors: David W Andrews; Charles B Scott; Paul W Sperduto; Adam E Flanders; Laurie E Gaspar; Michael C Schell; Maria Werner-Wasik; William Demas; Janice Ryu; Jean-Paul Bahary; Luis Souhami; Marvin Rotman; Minesh P Mehta; Walter J Curran Journal: Lancet Date: 2004-05-22 Impact factor: 79.321
Authors: John H Suh; Rupesh Kotecha; Samuel T Chao; Manmeet S Ahluwalia; Arjun Sahgal; Eric L Chang Journal: Nat Rev Clin Oncol Date: 2020-02-20 Impact factor: 66.675