Yuan Zixu, Xu Tingyang, Cai Jian, Zhao Yebiao, Cao Wuteng, Fichera Alessandro, Liu Xiaoxia, Yao Jianhua, Wang Hui
Department of Colorectal Surgery, Guangdong Institute of Gastroenterology, Guangdong Provincial Key Laboratory of Colorectal and Pelvic Floor Diseases, Department of Radiology, The Sixth Affiliated Hospital of Sun Yat-Sen University, Guangzhou, Guangdong, China.
Tencent AI lab, Shenzhen, Guangdong, China.
Ann Surg. 2022 Apr 1;275(4):e645-e651. doi: 10.1097/SLA.0000000000004229.
The aim of this study was to build a SVM classifier using ResNet-3D algorithm by artificial intelligence for prediction of synchronous PC.
Adequate detection and staging of PC from CRC remain difficult.
The primary tumors in synchronous PC were delineated on preoperative contrast-enhanced computed tomography (CT) images. The features of adjacent peritoneum were extracted to build a ResNet3D + SVM classifier. The performance of ResNet3D + SVM classifier was evaluated in the test set and was compared to routine CT which was evaluated by radiologists.
The training set consisted of 19,814 images from 54 patients with PC and 76 patients without PC. The test set consisted of 7837 images from 40 test patients. The ResNet-3D spent only 34 seconds to analyze the test images. To increase the accuracy of PC detection, we have built a SVM classifier by integrating ResNet-3D features with twelve PC-specific features (P < 0.05). The ResNet3D + SVM classifier showed accuracy of 94.11% with AUC of 0.922 (0.912-0.944), sensitivity of 93.75%, specificity of 94.44%, positive predictive value (PPV) of 93.75%, and negative predictive value (NPV) of 94.44% in the test set. The performance was superior to routine contrast-enhanced CT (AUC: 0.791).
The ResNet3D + SVM classifier based on deep learning algorithm using ResNet-3D framework has shown great potential in prediction of synchronous PC in CRC.
本研究旨在利用人工智能的ResNet-3D算法构建支持向量机（SVM）分类器，以预测同步性腹膜转移（PC）。
结直肠癌（CRC）中PC的充分检测和分期仍然困难。
在术前对比增强计算机断层扫描（CT）图像上勾勒出同步性PC中的原发性肿瘤。提取相邻腹膜的特征以构建ResNet3D + SVM分类器。在测试集中评估ResNet3D + SVM分类器的性能，并与放射科医生评估的常规CT进行比较。
训练集包括来自54例PC患者和76例无PC患者的19814张图像。测试集包括来自40例测试患者的7837张图像。ResNet-3D仅花费34秒来分析测试图像。为了提高PC检测的准确性，我们通过将ResNet-3D特征与十二个PC特异性特征相结合构建了一个SVM分类器（P <0.05）。在测试集中，ResNet3D + SVM分类器的准确率为94.11％，曲线下面积（AUC）为0.922（0.912 - 0.944），灵敏度为93.75％，特异性为94.44％，阳性预测值（PPV）为93.75％，阴性预测值（NPV）为94.44％。其性能优于常规对比增强CT（AUC：0.791）。
基于使用ResNet-3D框架的深度学习算法的ResNet3D + SVM分类器在预测CRC中的同步性PC方面显示出巨大潜力。
