Kubota Shunsuke, Wakiya Taiichi, Morohashi Hajime, Miura Takuya, Kanda Taishu, Matsuzaka Masashi, Sasaki Yoshihiro, Sakamoto Yoshiyuki, Hakamada Kenichi
Department of Gastroenterological Surgery, Hirosaki University Graduate School of Medicine, Hirosaki, Japan.
Department of Medical Informatics, Hirosaki University Hospital, Hirosaki, Japan.
J Anus Rectum Colon. 2025 Apr 25;9(2):202-212. doi: 10.23922/jarc.2024-085. eCollection 2025.
Predicting the response to chemotherapy can lead to the optimization of neoadjuvant chemotherapy (NAC). The present study aimed to develop a non-invasive prediction model of therapeutic response to NAC for rectal cancer (RC).
A dataset of the prechemotherapy computed tomography (CT) images of 57 patients from multiple institutions who underwent rectal surgery after three courses of S-1 and oxaliplatin (SOX) NAC for RC was collected. The therapeutic response to NAC was pathologically confirmed. It was then predicted whether they were pathologic responders or non-responders. Cases were divided into training, validation and test datasets. A CT patch-based predictive model was developed using a residual convolutional neural network and the predictive performance was evaluated. Binary logistic regression analysis of prechemotherapy clinical factors showed that none of the independent variables were significantly associated with the non-responders.
Among the 49 patients in the training and validation datasets, there were 21 (42.9%) and 28 (57.1%) responders and non-responders, respectively. A total of 3,857 patches were extracted from the 49 patients. In the validation dataset, the average sensitivity, specificity and accuracy was 97.3, 95.7 and 96.8%, respectively. Furthermore, the area under the receiver operating characteristic curve (AUC) was 0.994 (95% CI, 0.991-0.997; P<0.001). In the test dataset, which included 750 patches from 8 patients, the predictive model demonstrated high specificity (89.9%) and the AUC was 0.846 (95% CI, 0.817-0.875; P<0.001).
The non-invasive deep learning model using prechemotherapy CT images exhibited high predictive performance in predicting the pathological therapeutic response to SOX NAC.
预测化疗反应有助于优化新辅助化疗（NAC）。本研究旨在建立一种直肠癌（RC）新辅助化疗治疗反应的无创预测模型。
收集了来自多个机构的57例接受S-1和奥沙利铂（SOX）新辅助化疗三个疗程后行直肠手术患者的化疗前计算机断层扫描（CT）图像数据集。新辅助化疗的治疗反应经病理证实。然后预测他们是病理反应者还是无反应者。病例分为训练集、验证集和测试集。使用残差卷积神经网络建立基于CT图像块的预测模型，并评估其预测性能。化疗前临床因素的二元逻辑回归分析显示，没有一个自变量与无反应者显著相关。
在训练集和验证集中的49例患者中，分别有21例（42.9%）反应者和28例（57.1%）无反应者。从49例患者中总共提取了3857个图像块。在验证集中，平均灵敏度、特异度和准确率分别为97.3%、95.7%和96.8%。此外，受试者工作特征曲线（AUC）下面积为0.994（95%CI，0.991-0.997；P<0.001）。在测试集中，包括来自8例患者的750个图像块，预测模型显示出高特异度（89.9%），AUC为0.846（95%CI，0.817-0.875；P<0.001）。
使用化疗前CT图像的无创深度学习模型在预测SOX新辅助化疗的病理治疗反应方面表现出较高的预测性能。
