Image-based deep learning model for predicting pathological response in rectal cancer using post-chemoradiotherapy magnetic resonance imaging. (August 2021)

• Record Type: Journal Article
• Authors: Jang, Bum-Sup; Lim, Yu Jin; Song, Changhoon; Jeon, Seung Hyuck; Lee, Keun-Wook; Kang, Sung-Bum; Lee, Yoon Jin; Kim, Jae-Sung
• Is Part Of: Radiotherapy and oncology. Volume 161(2021)
• Page Start: 183
• Page End: 190
• Publication Date: 2021-08
• Subjects: Rectal cancer -- Concurrent chemoradiation -- Tumor regression -- Transfer learning -- Deep learning -- MRI; Oncology -- Periodicals; Radiotherapy -- Periodicals; Tumors -- Periodicals; Medical Oncology -- Periodicals; Neoplasms -- radiotherapy -- Periodicals; Radiotherapy -- Periodicals; Radiothérapie -- Périodiques; Cancérologie -- Périodiques; Tumeurs -- Périodiques; Electronic journals; 616.9940642
• DOI: 10.1016/j.radonc.2021.06.019
• Languages: English
• ISSNs: 0167-8140

Abstract

Highlights: We develop imaging-based deep learning models for predicting pathological response and good response in patients with rectal cancer after post-chemoradiotherapy. These models were trained from preoperative T2-weighted axial rectal MR images without segmentation. Both models showed acceptable performance in the holdout testing set ( N = 117). Abstract: Introduction: To develop an image-based deep learning model for predicting pathological response in rectal cancer using post-chemoradiotherapy magnetic resonance (MR) imaging. Materials and methods: A total of 466 patients with locally advanced rectal cancer who received preoperative chemoradiotherapy followed by surgical resection were collected from single center, among whom 113 (24.3%) were allocated to the holdout testing set. Complete response (pCR) was defined as Dworak tumor regression grade (TRG) 4, while good response (GR) was defined as TRG 3 or 4. Based on post-chemoradiotherapy T2-weighted axial MR images, two deep learning models were developed to predict pCR and GR, respectively. The prediction performance of the deep learning models was evaluated in the testing set and was compared to that of a senior radiologist and a radiation oncologist. Results: The deep learning model showed an area under the receiver operating characteristic curve, sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of 0.76, 0.30, 0.96, 0.67, 0.87, and 85.0% for predicting pCR and 0.72, 0.54, 0.81, 0.60, 0.77, and 71.7% for predicting GR, respectively. The deep learning model had a superior predictive performance than the observers. Fair agreement between the ground truth and the model was shown for pCR prediction (kappa = 0.34) and GR prediction (kappa = 0.36). Conclusions: The post-chemoradiotherapy T2-weighted axial MR image-based deep learning model showed acceptable performance in predicting pCR or GR in patients with rectal cancer, compared with human observers.