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

Abstract

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.

arXiv commentWeakly-supervised Segmentation, Medical Image Segmentation, Contrastive Similarity, Geometric Prior, Point Cloud

References in corpus (13)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Automated Design of Deep Learning Methods for Biomedical Image Segmentation
• Categorical Reparameterization with Gumbel-Softmax
• The Liver Tumor Segmentation Benchmark (LiTS)
• Open3D: A Modern Library for 3D Data Processing
• Anatomically Constrained Neural Networks (ACNN): Application to Cardiac Image Enhancement and Segmentation
• Constrained-CNN losses for weakly supervised segmentation
• Constrained Deep Weak Supervision for Histopathology Image Segmentation
• Weakly Supervised Deep Nuclei Segmentation Using Partial Points Annotation in Histopathology Images
• Anatomical Priors in Convolutional Networks for Unsupervised Biomedical Segmentation
• Inter Extreme Points Geodesics for End-to-End Weakly Supervised Image Segmentation
• Boosting Semi-supervised Image Segmentation with Global and Local Mutual Information Regularization
• Self-Ensembling Contrastive Learning for Semi-Supervised Medical Image Segmentation