Yihuai Hu1, Chenyi Xie2, Hong Yang1, Joshua W K Ho3, Jing Wen4, Lujun Han5, Ka-On Lam6, Ian Y H Wong7, Simon Y K Law7, Keith W H Chiu2, Varut Vardhanabhuti8, Jianhua Fu9. 1. Department of Thoracic Surgery, Sun Yat-sen University Cancer Center, Guangzhou, China; State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangzhou, China; Guangdong Esophageal Cancer Institute, Guangzhou, China. 2. Department of Diagnostic Radiology, Li Ka Shing Faculty of Medicine, University of Hong Kong, Hong Kong, China. 3. School of Biomedical Sciences, Li Ka Shing Faculty of Medicine, University of Hong Kong, Hong Kong, China. 4. State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangzhou, China; Guangdong Esophageal Cancer Institute, Guangzhou, China. 5. State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangzhou, China; Department of Medical Imaging, Sun Yat-sen University Cancer Center, Guangzhou, China. 6. Department of Clinical Oncology, Li Ka Shing Faculty of Medicine, University of Hong Kong, Hong Kong, China. 7. Department of Surgery, Li Ka Shing Faculty of Medicine, University of Hong Kong, Hong Kong, China. 8. Department of Diagnostic Radiology, Li Ka Shing Faculty of Medicine, University of Hong Kong, Hong Kong, China. Electronic address: varv@hku.hk. 9. Department of Thoracic Surgery, Sun Yat-sen University Cancer Center, Guangzhou, China; State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangzhou, China; Guangdong Esophageal Cancer Institute, Guangzhou, China. Electronic address: fu_jh@outlook.com.
Abstract
BACKGROUND: Deep learning is promising to predict treatment response. We aimed to evaluate and validate the predictive performance of the CT-based model using deep learning features for predicting pathologic complete response to neoadjuvant chemoradiotherapy (nCRT) in esophageal squamous cell carcinoma (ESCC). MATERIALS AND METHODS: Patients were retrospectively enrolled between April 2007 and December 2018 from two institutions. We extracted deep learning features of six pre-trained convolutional neural networks, respectively, from pretreatment CT images in the training cohort (n = 161). Support vector machine was adopted as the classifier. Validation was performed in an external testing cohort (n = 70). We assessed the performance using the area under the receiver operating characteristics curve (AUC) and selected an optimal model, which was compared with a radiomics model developed from the training cohort. A clinical model consisting of clinical factors only was also built for baseline comparison. We further conducted a radiogenomics analysis using gene expression profiles to reveal underlying biology associated with radiological prediction. RESULTS: The optimal model with features extracted from ResNet50 achieved an AUC and accuracy of 0.805 (95% CI, 0.696-0.913) and 77.1% (65.6%-86.3%) in the testing cohort, compared with 0.725 (0.605-0.846)) and 67.1% (54.9%-77.9%) for the radiomics model. All the radiological models showed better predictive performance than the clinical model. Radiogenomics analysis suggested a potential association mainly with WNT signaling pathway and tumor microenvironment. CONCLUSIONS: The novel and noninvasive deep learning approach could provide efficient and accurate prediction of treatment response to nCRT in ESCC, and benefit clinical decision making of therapeutic strategy.
BACKGROUND: Deep learning is promising to predict treatment response. We aimed to evaluate and validate the predictive performance of the CT-based model using deep learning features for predicting pathologic complete response to neoadjuvant chemoradiotherapy (nCRT) in esophageal squamous cell carcinoma (ESCC). MATERIALS AND METHODS:Patients were retrospectively enrolled between April 2007 and December 2018 from two institutions. We extracted deep learning features of six pre-trained convolutional neural networks, respectively, from pretreatment CT images in the training cohort (n = 161). Support vector machine was adopted as the classifier. Validation was performed in an external testing cohort (n = 70). We assessed the performance using the area under the receiver operating characteristics curve (AUC) and selected an optimal model, which was compared with a radiomics model developed from the training cohort. A clinical model consisting of clinical factors only was also built for baseline comparison. We further conducted a radiogenomics analysis using gene expression profiles to reveal underlying biology associated with radiological prediction. RESULTS: The optimal model with features extracted from ResNet50 achieved an AUC and accuracy of 0.805 (95% CI, 0.696-0.913) and 77.1% (65.6%-86.3%) in the testing cohort, compared with 0.725 (0.605-0.846)) and 67.1% (54.9%-77.9%) for the radiomics model. All the radiological models showed better predictive performance than the clinical model. Radiogenomics analysis suggested a potential association mainly with WNT signaling pathway and tumor microenvironment. CONCLUSIONS: The novel and noninvasive deep learning approach could provide efficient and accurate prediction of treatment response to nCRT in ESCC, and benefit clinical decision making of therapeutic strategy.