Kato Shinya, Miyoshi Norikatsu, Fujino Shiki, Minami Soichiro, Nagae Ayumi, Hayashi Rie, Sekido Yuki, Hata Tsuyoshi, Hamabe Atsushi, Ogino Takayuki, Tei Mitsuyoshi, Kagawa Yoshinori, Takahashi Hidekazu, Uemura Mamoru, Yamamoto Hirofumi, Doki Yuichiro, Eguchi Hidetoshi
Department of Gastroenterological Surgery, Graduate School of Medicine, Osaka University, Suita, Osaka 565-0871, Japan.
Department of Innovative Oncology Research and Regenerative Medicine, Osaka International Cancer Institute, Osaka 541-8567, Japan.
Oncol Lett. 2023 Sep 20;26(5):474. doi: 10.3892/ol.2023.14062. eCollection 2023 Nov.
In current clinical practice, several treatment methods, including neoadjuvant therapy, are being developed to improve overall survival or local recurrence rates for locally advanced rectal cancer. The response to neoadjuvant therapy is usually evaluated using imaging data collected before and after preoperative treatment or postsurgical pathological diagnosis. However, there is a need to accurately predict the response to preoperative treatment before treatment is administered. The present study used a deep learning network to examine colonoscopy images and construct a model to predict the response of rectal cancer to neoadjuvant chemotherapy. A total of 53 patients who underwent preoperative chemotherapy followed by radical resection for advanced rectal cancer at the Osaka University Hospital between January 2011 and August 2019 were retrospectively analyzed. A convolutional neural network model was constructed using 403 images from 43 patients as the learning set. The diagnostic accuracy of the deep learning model was evaluated using 84 images from 10 patients as the validation set. The model demonstrated a sensitivity, specificity, accuracy, positive predictive value and area under the curve of 77.6% (38/49), 62.9% (22/33), 71.4% (60/84), 74.5% (38/51) and 0.713, respectively, in predicting a poor response to neoadjuvant therapy. Overall, deep learning of colonoscopy images may contribute to an accurate prediction of the response of rectal cancer to neoadjuvant chemotherapy.
在当前的临床实践中，正在开发包括新辅助治疗在内的几种治疗方法，以提高局部晚期直肠癌的总生存率或局部复发率。新辅助治疗的反应通常使用术前治疗前后收集的影像数据或术后病理诊断来评估。然而，在进行治疗之前，需要准确预测对术前治疗的反应。本研究使用深度学习网络检查结肠镜图像，并构建一个模型来预测直肠癌对新辅助化疗的反应。对2011年1月至2019年8月期间在大阪大学医院接受术前化疗然后进行晚期直肠癌根治性切除的53例患者进行了回顾性分析。使用来自43例患者的403张图像作为学习集构建了一个卷积神经网络模型。使用来自10例患者的84张图像作为验证集评估深度学习模型的诊断准确性。在预测对新辅助治疗反应不佳方面，该模型的敏感性、特异性、准确性、阳性预测值和曲线下面积分别为77.6%（38/49）、62.9%（22/33）、71.4%（60/84）、74.5%（38/51）和0.713。总体而言，结肠镜图像的深度学习可能有助于准确预测直肠癌对新辅助化疗的反应。
