Efficient two-step liver and tumour segmentation on abdominal CT via deep learning and a conditional random field. (November 2022)

• Record Type: Journal Article
• Authors: Chen, Ying; Zheng, Cheng; Hu, Fei; Zhou, Taohui; Feng, Longfeng; Xu, Guohui; Yi, Zhen; Zhang, Xiang
• Is Part Of: Computers in biology and medicine. Volume 150(2022)
• Publication Date: 2022-11
• Subjects: Liver tumour segmentation -- Improved residual blocks -- Fractal residual blocks -- Fully connected CRF -- Deep learning; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2022.106076
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Segmentation of the liver and tumours from computed tomography (CT) scans is an important task in hepatic surgical planning. Manual segmentation of the liver and tumours is a time-consuming and labour-intensive task; therefore, a fully automated method for performing this segmentation is particularly desired. An automatic two-step liver and tumour segmentation method is presented in this paper. A cascade framework is used during the segmentation process, and a fully connected conditional random field (CRF) method is used to refine the tumour segmentation result. First, the proposed fractal residual U-Net (FRA-UNet) is used to locate and initially segment the liver. Then, FRA-UNet is further used to predict liver tumours from the liver region of interest (ROI). Finally, a three-dimensional (3D) CRF is used to refine the tumour segmentation results. The improved fractal residual (FR) structure effectively retains more effective features for improving the segmentation performance of deeper networks, the improved deep residual block can utilise the feature information more effectively, and the 3D CRF method smooths the contours and avoids the tumour oversegmentation problem. FRA-UNet is tested on the Liver Tumour Segmentation challenge dataset (LiTS) and the 3D Image Reconstruction for Comparison of Algorithm Database dataset (3DIRCADb), achieving 97.13% and 97.18% Dice similarity coefficients (DSCs) for liver segmentation and 71.78% and 68.97% DSCs for tumour segmentation, respectively, outperforming most state-of-the-art networks. Highlights: A two-step mechanism for liver and tumour segmentation is proposed. The mechanism relies on a cascade framework and improved traditional method. The combination of fractal structure and residual structure can solve the contour blurring problem to some extent.