基于3D卷积网络的结肠癌CT图像分类研究

Study of Colorectal Cancer CT Image Classification Based on 3D Convolutional Network

结直肠肿瘤是全世界排名前三的肿瘤之一,目前在CT图像中筛查出结肠肿瘤仍需要放射科医生手工完成,这是一项费时费力的重复性劳动,文中研究了用3D卷积网络在腹部CT图像上提取3D特征,判断CT图像中是否有结肠癌病灶的方法。文中采集了一个有348例样本的结肠癌CT图像数据集,设计了3种不同结构的3D卷积网络,对采集的腹部CT图像进行了正常/非正常二分类实验,文中性能最好的模型C是一个带有3个改进的残差模块的3D卷积网络,正常/非正常二分类实验的平均准确率为96.2%,AUC为0.989,分别比基准模型提高了2.2%、2.9%。实验结果表明,3D卷积网络在结肠癌CT的正常/非正常二分类任务上准确率高,泛化能力好,且只需要CT级弱标定数据集,具有潜在的临床应用价值。

Colorectal cancer(CRC) is among the top three tumors in the world. At present, screening CRC in CT images still needs to be done manually by radiologists, which is a time-consuming and laborious repetitive work. This paper investigated a method which extracted 3 D features on abdominal CT images based on 3 D convolutional network, then estimated whether there were CRC lesions through CT images. This paper collected a colorectal cancer CT image dataset with 348 samples and designed three 3 D convolution networks with different structures, and performed a normal/abnormal binary classification experiments on the acquired abdominal CT images. The best performance model in this paper was a 3 D convolution networks with three improved residual modules. The average accuracy of normal/abnormal binary classification experiment was 96.2%, and the AUC was 0.989, which was 2.2% and 2.9% higher than the baseline model. The experiment results showed that the 3 D convolutional networks with have outstanding performance in the CRC normal/abnormal classification task, it also has good generalization ability and only under CT-level weak-labeled data, it is helpful to clinical application.