Multi-Dimensional Cascaded Net with Uncertain Probability Reduction for Abdominal Multi-Organ Segmentation in CT Sequences. (June 2022)

• Record Type: Journal Article
• Authors: Li, Chengkang; Mao, Yishen; Guo, Yi; Li, Ji; Wang, Yuanyuan
• Is Part Of: Computer methods and programs in biomedicine. Volume 221(2022)
• Publication Date: 2022-06
• Subjects: multi-organ segmentation -- shallow-layer-enhanced 3D location net -- probability anatomical prior -- uncertain probability -- circular inference module -- high-resolution multi-view 2.5D net; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2022.106887
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: We propose a multi-dimensional cascaded net (MDCNet), which cascades and takes full advantage of two networks with different dimensions to segment eight organs in 3D CT images automatically. MDCNet can extract the complete semantic features while preserving the high-resolution detail information of a large volume CT image, thus maintaining the segmentations integrity while achieving smooth and accurate edges. We propose a circular inference strategy to reduce the uncertain probability of the segmented boundaries. The experiments on the two multi-center public datasets both obtained the best performance, particularly a higher Dice on small gallbladders and irregular duodenums. Due to the advanced network structure, the memory consumption of MDCNet is 27 times less than that of other methods. Abstract: Background and Objective: Deep learning abdominal multi-organ segmentation provides preoperative guidance for abdominal surgery. However, due to the large volume of 3D CT sequences, the existing methods cannot balance complete semantic features and high-resolution detail information, which leads to uncertain, rough, and inaccurate segmentation, especially in small and irregular organs. In this paper, we propose a two-stage algorithm named multi-dimensional cascaded net (MDCNet) to solve the above problems and segment multi-organs in CT images, including the spleen, kidney, gallbladder, esophagus, liver, stomach, pancreas, and duodenum. Methods: MDCNet combines the powerful semantic encoder ability of a 3D net and the rich high-resolution information of a 2.5D net. In stage1, a prior-guided shallow-layer-enhanced 3D location net extracts entire semantic features from a downsampled CT volume to perform rough segmentation. Additionally, we use circular inference and parameter Dice loss to alleviate uncertain boundary. The inputs of stage2 are high-resolution slices, which are obtained by the original image and coarse segmentation of stage1. Stage2 offsets the details lost during downsampling, resulting in smooth and accurate refined contours. The 2.5D net from the axial, coronal, and sagittal views also compensates for the missing spatial information of a single view. Results: The experiments on the two datasets both obtained the best performance, particularly a higher Dice on small gallbladders and irregular duodenums, which reached 0.85±0.12 and 0.77±0.07 respectively, increasing by 0.02 and 0.03 compared to the state-of-the-art method. Conclusion: Our method can extract all semantic and high-resolution detail information from a large-volume CT image. It reduces the boundary uncertainty while yielding smoother segmentation edges, indicating good clinical application prospects.