LSSED: A robust segmentation network for inflamed appendix from CT images
Wing W.Y. Ng (South China University of Technology); Peixin Zheng (South China University of Technology); Ting Wang (South China University of Technology); Jianjun Zhang (South China University of Technology); Hui Zhou (The Sixth Affiliated Hospital of Guangzhou Medical University, Qingyuan People’s Hospital); GuangMing Li (The Sixth Affiliated Hospital of Guangzhou Medical University, Qingyuan People’s Hospital); Dan Liang (Guangzhou First People’s Hospital/The Second Affiliated Hospital, South China University of Technology); Yinhao Liang (South China University of Technology); Xinhua Wei (Department of Radiology, Guangzhou First People's Hospital, South China University of Technology)
-
Members: FreeSPS
IEEE Members: $11.00
Non-members: $15.00
06 Jun 2023
Acute appendicitis (AA) is one of the most prevalent surgical acute abdominal condition diseases. The treatment management of AA is highly dependent on the CT image diagnosis. However, the inflamed appendix exhibits blurred boundaries with nearby tissue, varying shapes, and sizes. These properties require high robustness and generalization capability of inflamed appendix segmentation networks. In this paper, we propose a CNN-Transformer-based encoder-decoder segmentation network (LSSED) equipped with localized stochastic sensitivity (LSS) loss function and residual dilated paths (RD-Paths) to solve above problems. The proposed method effectively learns robust features of the input data by reducing the LSS of unseen samples. In addition, the RD-Paths capture multi-scale feature information and reduce the semantic gap between the encoder and decoder, which improves the accuracy of the segmentation. Empirical studies on a real-world AA dataset show that our method yields the best performance in terms of average Dice similarity coefficient (DSC) and Hausdorff Distance of 95% (HD95) compared to several state-of-the-art segmentation networks.
