A prior-based method for colorectal lymph node region classification via deep neural network

Yueyao Huang, Shuo Huang, Han Wang, Mingtian Wei, Jingling Wang, Haixian Zhang, Ziqiang Wang, Zhang Yi

Abstract: Colorectal cancer (CRC) is a common malignant tumor disease appeared in colon or rectum walls. CRC metastasis often appears with lymph nodes, and the CRC lymph nodes region classification is essential for CRC diagnosis, generally classified as lateral lymph nodes (LLN) and non-lateral lymph nodes (NLLN). Previous CRC diagnosis relied heavily on the physician’s clinical experience, which is a manual and time-consuming process. An automated method based on prior is proposed to CRC lymph node region classification using Convolutional neural networks (CNNs). Two novel priors are proposed, including spatial prior and shape prior. The spatial prior is based on medical domain knowledge to relieve the difficulty of extracting useful features from the complex semantic information of CT images. And the shape prior is proposed through carefully analyzing the dataset, which aims to find an optimal size that can preserve features in the origin CT images and be adaptive to neural network input. Experimental results demonstrate that the proposed method achieves impressive classification performance, in terms of an accuracy of 96.66% and an AUC of 0.9941. Additionally, we apply the proposed method in other medical classification works and it also achieves satisfying results.