Weakly-Supervised 3D Medical Image Segmentation Using Geometric Prior and Contrastive Similarity.

• DOI: 10.48550/arxiv.2302.02125
• Publication Date: 2023-10-01
• Authors: Hao Du; Qihua Dong; Yan Xu; Jing Liao
• Keywords: FOS: Computer and information sciences; Computer Science - Machine Learning; 03 medical and health sciences; 0302 clinical medicine; Computer Vision and Pattern Recognition (cs.CV); Image and Video Processing (eess.IV); Computer Science - Computer Vision and Pattern Recognition; Image Processing, Computer-Assisted; FOS: Electrical engineering, electronic engineering, information engineering; Diagnosis, Computer-Assisted; Electrical Engineering and Systems Science - Image and Video Processing; Artifacts; Machine Learning (cs.LG)

Weakly-supervised Segmentation, Medical Image Segmentation, Contrastive Similarity, Geometric Prior, Point Cloud<br/>Medical image segmentation is almost the most important pre-processing procedure in computer-aided diagnosis but is also a very challenging task due to the complex shapes of segments and various artifacts caused by medical imaging, (i.e., low-contrast tissues, and non-homogenous textures). In this paper, we propose a simple yet effective segmentation framework that incorporates the geometric prior and contrastive similarity into the weakly-supervised segmentation framework in a loss-based fashion. The proposed geometric prior built on point cloud provides meticulous geometry to the weakly-supervised segmentation proposal, which serves as better supervision than the inherent property of the bounding-box annotation (i.e., height and width). Furthermore, we propose contrastive similarity to encourage organ pixels to gather around in the contrastive embedding space, which helps better distinguish low-contrast tissues. The proposed contrastive embedding space can make up for the poor representation of the conventionally-used gray space. Extensive experiments are conducted to verify the effectiveness and the robustness of the proposed weakly-supervised segmentation framework. The proposed framework is superior to state-of-the-art weakly-supervised methods on the following publicly accessible datasets: LiTS 2017 Challenge, KiTS 2021 Challenge, and LPBA40. We also dissect our method and evaluate the performance of each component.<br/>