Combined deep learning and radiomics in pretreatment radiation esophagitis prediction for patients with esophageal cancer underwent volumetric modulated arc therapy

doi:10.1016/j.radonc.2024.110438

科研成果详情

题名	Combined deep learning and radiomics in pretreatment radiation esophagitis prediction for patients with esophageal cancer underwent volumetric modulated arc therapy
作者	Xie, Congying1; Yu, Xianwen1,2; Tan, Ninghang1,2; Zhang, Jicheng1; Su, Wanyu1,2; Ni, Weihua1,2; Li, Chenyu1; Zhao, Zeshuo1; Xiang, Ziqing1; Shao, Li1; Li, Heng1; Wu, Jianping1,3; Cao, Zhuo 1,4; Jin, Juebin1; Jin, Xiance1,5
发表日期	2024-10
发表期刊	Radiotherapy and Oncology 影响因子和分区
语种	英语
原始文献类型	Article
关键词	Radiation esophagitis Esophageal cancer Radiomics Dosiomics Deep learning
其他关键词	CELL LUNG-CANCER ; VOXEL-BASED ANALYSIS ; RISK-FACTORS ; RADIOTHERAPY ; GRADE ; VMAT
摘要	Purpose: To develop a combined radiomics and deep learning (DL) model in predicting radiation esophagitis (RE) of a grade >= 2 for patients with esophageal cancer (EC) underwent volumetric modulated arc therapy (VMAT) based on computed tomography (CT) and radiation dose (RD) distribution images. Materials and methods: A total of 273 EC patients underwent VMAT were retrospectively reviewed and enrolled from two centers and divided into training (n = 152), internal validation (n = 66), and external validation (n = 55) cohorts, respectively. Radiomic and dosiomic features along with DL features using convolutional neural networks were extracted and screened from CT and RD images to predict RE. The performance of these models was evaluated and compared using the area under curve (AUC) of the receiver operating characteristic curves (ROC). Results: There were 5 and 10 radiomic and dosiomic features were screened, respectively. XGBoost achieved a best AUC of 0.703, 0.694 and 0.801, 0.729 with radiomic and dosiomic features in the internal and external validation cohorts, respectively. ResNet34 achieved a best prediction AUC of 0.642, 0.657 and 0.762, 0.737 for radiomics based DL model (DLR) and RD based DL model (DLD) in the internal and external validation cohorts, respectively. Combined model of DLD + Dosiomics + clinical factors achieved a best AUC of 0.913, 0.821 and 0.805 in the training, internal, and external validation cohorts, respectively. Conclusion: Although the dose was not responsible for the prediction accuracy, the combination of various feature extraction methods was a factor in improving the RE prediction accuracy. Combining DLD with dosiomic features was promising in the pretreatment prediction of RE for EC patients underwent VMAT.
资助项目	Key project of Zhejiang Natural Science Foundation [Z24A050009]; Key project of Zhejiang Provincial Health Science and Technology Program [WKJ-ZJ-2437]; Major project of Wenzhou Science and Technology Bureau [ZY2020011]; Scientific Research Fund of Zhejiang Provincial Education Department [Y202352935]; Zhejiang Engineering Research Center for innovation and application of Intelligent Radiotherapy Technology; Zhejiang-Hong Kong Precision Theranostics of Thoracic Tumors Joint Laboratory; Wenzhou key Laboratory of basic science and translational research of radiation oncology; Zhejiang Key Laboratory of Intelligent Cancer Biomarker Discovery and Translation; Discipline Cluster of Oncology, Wenzhou Medical University
出版者	ELSEVIER IRELAND LTD
ISSN	0167-8140
EISSN	1879-0887
卷号	199
DOI	10.1016/j.radonc.2024.110438
页数	9
WOS类目	Oncology ; Radiology, Nuclear Medicine & Medical Imaging
WOS研究方向	Oncology ; Radiology, Nuclear Medicine & Medical Imaging
WOS记录号	WOS:001273956400001
收录类别	SCIE ; SCOPUS ; PUBMED
URL	查看原文
PubMed ID	39013503
SCOPUSEID	2-s2.0-85198568195
通讯作者地址	[Cao, Zhuo;Jin, Juebin;Jin, Xiance]Wenzhou Med Univ, Affiliated Hosp 1, Dept Radiotherapy Ctr, Wenzhou 325000, Peoples R China.
Scopus学科分类	Hematology;Oncology;Radiology, Nuclear Medicine and Imaging
SCOPUS_ID	SCOPUS_ID:85198568195
引用统计
文献类型	期刊论文
条目标识符	https://kms.wmu.edu.cn/handle/3ETUA0LF/216825
专题	附属第一医院基础医学院（机能实验教学中心）其他_温州医科大学附属衢州医院其他_温州医科大学慈溪生物医药研究院
通讯作者	Cao, Zhuo; Jin, Juebin; Jin, Xiance
作者单位	1.Wenzhou Med Univ, Affiliated Hosp 1, Dept Radiotherapy Ctr, Wenzhou 325000, Peoples R China; 2.Wenzhou Med Univ, Cixi Biomed Res Inst, Wenzhou 315000, Zhejiang, Peoples R China; 3.Wenzhou Med Univ, Quzhou Affiliated Hosp, Quzhou Peoples Hosp, Dept Radiotherapy, Quzhou 324000, Peoples R China; 4.Lishui Peoples Hosp, Dept Resp, Lishui 323000, Peoples R China; 5.Wenzhou Med Univ, Sch Basic Med Sci, Wenzhou 325000, Peoples R China
第一作者单位	附属第一医院
通讯作者单位	附属第一医院
第一作者的第一单位	附属第一医院
推荐引用方式 GB/T 7714	Xie, Congying,Yu, Xianwen,Tan, Ninghang,et al. Combined deep learning and radiomics in pretreatment radiation esophagitis prediction for patients with esophageal cancer underwent volumetric modulated arc therapy[J]. Radiotherapy and Oncology,2024,199.
APA	Xie, Congying., Yu, Xianwen., Tan, Ninghang., Zhang, Jicheng., Su, Wanyu., ... & Jin, Xiance. (2024). Combined deep learning and radiomics in pretreatment radiation esophagitis prediction for patients with esophageal cancer underwent volumetric modulated arc therapy. Radiotherapy and Oncology, 199.
MLA	Xie, Congying,et al."Combined deep learning and radiomics in pretreatment radiation esophagitis prediction for patients with esophageal cancer underwent volumetric modulated arc therapy".Radiotherapy and Oncology 199(2024).