The radiomic-clinical model using the SHAP method for assessing the treatment response of whole-brain radiotherapy: a multicentric study

doi:10.1007/s00330-022-08887-0

	The radiomic-clinical model using the SHAP method for assessing the treatment response of whole-brain radiotherapy: a multicentric study
	Wang, Yixin 2,3,4; Lang, Jinwei 2,3; Zuo, Joey Zhaoyu 2,3; Dong, Yaqin 1; Hu, Zongtao 2,4; Xu, Xiuli 4; Zhang, Yongkang 4; Wang, Qinjie 2,3; Yang, Lizhuang 2,3,4; Wong, Stephen T. C.5
刊名	EUROPEAN RADIOLOGY
	2022-06-09
关键词	Magnetic resonance imaging Neoplasm metastasis Machine learning Radiotherapy Game theory
ISSN号	0938-7994
DOI	10.1007/s00330-022-08887-0
通讯作者	Wang, Hongzhi(wanghz@hfcas.ac.cn) ; Li, Hai(hli@cmpt.ac.cn)
英文摘要	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.
资助项目	Key R&D Program of Anhui Province[201904a07020104] ; Natural Science Fund of Anhui Province[2008085MC69] ; Collaborative Innovation Program of Hefei Science Center[2020HSC-CIP001] ; Collaborative Innovation Program of Hefei Science Center[2021HSC-CIP013] ; General scientific research project of Anhui Provincial Health Commission[AHWJ2021b150] ; Natural Science Fund of Hefei City[2021033] ; CAS Anhui Province Key Laboratory of Medical Physics and Technology[LMPT201904] ; Director's Fund of Hefei Cancer Hospital of CAS[YZJJ2019C14] ; Director's Fund of Hefei Cancer Hospital of CAS[YZJJ2019A04]
WOS关键词	CELL LUNG-CANCER ; GRADED PROGNOSTIC ASSESSMENT ; RADIATION-THERAPY ; BREAST-CANCER ; METASTASES ; SURVIVAL ; STRATIFICATION ; PREDICTION ; EFFICACY
WOS研究方向	Radiology, Nuclear Medicine & Medical Imaging
语种	英语
出版者	SPRINGER
WOS记录号	WOS:000808417600002
资助机构	Key R&D Program of Anhui Province ; Natural Science Fund of Anhui Province ; Collaborative Innovation Program of Hefei Science Center ; General scientific research project of Anhui Provincial Health Commission ; Natural Science Fund of Hefei City ; CAS Anhui Province Key Laboratory of Medical Physics and Technology ; Director's Fund of Hefei Cancer Hospital of CAS
内容类型	期刊论文
源URL	[http://ir.hfcas.ac.cn:8080/handle/334002/131175]
专题	中国科学院合肥物质科学研究院
通讯作者	Wang, Hongzhi; Li, Hai
作者单位	1.Anhui Med Univ, Dept Radiat Oncol, Affiliated Hosp 1, Hefei 230022, Peoples R China 2.Chinese Acad Sci, Hefei Inst Phys Sci, Inst Hlth & Med Technol, Anhui Prov Key Lab Med Phys & Technol, Hefei 230031, Peoples R China 3.Univ Sci & Technol China, Hefei 230026, Peoples R China 4.Chinese Acad Sci, Hefei Canc Hosp, Dept Oncol, Hefei 230031, Peoples R China 5.Houston Methodist Canc Ctr, Dept Syst Med & Bioengn, Weill Cornell Med Coll, Houston, TX 77030 USA
推荐引用方式 GB/T 7714	Wang, Yixin,Lang, Jinwei,Zuo, Joey Zhaoyu,et al. The radiomic-clinical model using the SHAP method for assessing the treatment response of whole-brain radiotherapy: a multicentric study[J]. EUROPEAN RADIOLOGY,2022.
APA	Wang, Yixin.,Lang, Jinwei.,Zuo, Joey Zhaoyu.,Dong, Yaqin.,Hu, Zongtao.,...&Li, Hai.(2022).The radiomic-clinical model using the SHAP method for assessing the treatment response of whole-brain radiotherapy: a multicentric study.EUROPEAN RADIOLOGY.
MLA	Wang, Yixin,et al."The radiomic-clinical model using the SHAP method for assessing the treatment response of whole-brain radiotherapy: a multicentric study".EUROPEAN RADIOLOGY (2022).