Department of General Surgery, The Affiliated Hospital of Qingdao University, Qingdao, Shandong 266003, China.
Department of Cardiac Ultrasound, The Affiliated Hospital of Qingdao University, Qingdao, Shandong 266003, China.
Chin Med J (Engl). 2021 Feb 25;134(7):821-828. doi: 10.1097/CM9.0000000000001401.
Colorectal cancer is harmful to the patient's life. The treatment of patients is determined by accurate preoperative staging. Magnetic resonance imaging (MRI) played an important role in the preoperative examination of patients with rectal cancer, and artificial intelligence (AI) in the learning of images made significant achievements in recent years. Introducing AI into MRI recognition, a stable platform for image recognition and judgment can be established in a short period. This study aimed to establish an automatic diagnostic platform for predicting preoperative T staging of rectal cancer through a deep neural network.
A total of 183 rectal cancer patients' data were collected retrospectively as research objects. Faster region-based convolutional neural networks (Faster R-CNN) were used to build the platform. And the platform was evaluated according to the receiver operating characteristic (ROC) curve.
An automatic diagnosis platform for T staging of rectal cancer was established through the study of MRI. The areas under the ROC curve (AUC) were 0.99 in the horizontal plane, 0.97 in the sagittal plane, and 0.98 in the coronal plane. In the horizontal plane, the AUC of T1 stage was 1, AUC of T2 stage was 1, AUC of T3 stage was 1, AUC of T4 stage was 1. In the coronal plane, AUC of T1 stage was 0.96, AUC of T2 stage was 0.97, AUC of T3 stage was 0.97, AUC of T4 stage was 0.97. In the sagittal plane, AUC of T1 stage was 0.95, AUC of T2 stage was 0.99, AUC of T3 stage was 0.96, and AUC of T4 stage was 1.00.
Faster R-CNN AI might be an effective and objective method to build the platform for predicting rectal cancer T-staging.
chictr.org.cn: ChiCTR1900023575; http://www.chictr.org.cn/showproj.aspx?proj=39665.
结直肠癌对患者的生命有害。患者的治疗取决于准确的术前分期。磁共振成像（MRI）在直肠癌患者的术前检查中发挥了重要作用，而人工智能（AI）在图像学习方面近年来取得了重大进展。将 AI 引入 MRI 识别，可以在短时间内建立一个稳定的图像识别和判断平台。本研究旨在通过深度神经网络建立自动诊断平台，预测直肠癌术前 T 分期。
回顾性收集 183 例直肠癌患者的数据作为研究对象。使用快速区域卷积神经网络（Faster R-CNN）构建平台，并通过受试者工作特征（ROC）曲线评估平台。
通过对 MRI 的研究，建立了一种直肠癌 T 分期的自动诊断平台。ROC 曲线下面积（AUC）在水平平面为 0.99，矢状面为 0.97，冠状面为 0.98。在水平平面上，T1 期的 AUC 为 1，T2 期的 AUC 为 1，T3 期的 AUC 为 1，T4 期的 AUC 为 1。在冠状面，T1 期的 AUC 为 0.96，T2 期的 AUC 为 0.97，T3 期的 AUC 为 0.97，T4 期的 AUC 为 0.97。在矢状面，T1 期的 AUC 为 0.95，T2 期的 AUC 为 0.99，T3 期的 AUC 为 0.96，T4 期的 AUC 为 1.00。
Faster R-CNN AI 可能是建立预测直肠癌 T 分期平台的一种有效、客观的方法。
chictr.org.cn：ChiCTR1900023575；http://www.chictr.org.cn/showproj.aspx？proj=39665。
Zotero 插件
