BASIC: Semi-supervised Multi-organ Segmentation with Balanced Subclass Regularization and Semantic-conflict Penalty

TL;DR

This paper introduces BASIC, a semi-supervised multi-organ segmentation method that uses balanced subclass regularization and a semantic-conflict penalty to address class imbalance and improve segmentation accuracy.

Contribution

The paper proposes a novel semi-supervised network with balanced subclass regularization and semantic-conflict penalty, enhancing unbiased learning in multi-organ segmentation.

Findings

Outperforms state-of-the-art methods on WORD and MICCAI FLARE 2022 datasets.

Effectively alleviates class imbalance in multi-organ segmentation.

Improves segmentation accuracy through multi-task learning and semantic conflict penalties.

Abstract

Semi-supervised learning (SSL) has shown notable potential in relieving the heavy demand of dense prediction tasks on large-scale well-annotated datasets, especially for the challenging multi-organ segmentation (MoS). However, the prevailing class-imbalance problem in MoS caused by the substantial variations in organ size exacerbates the learning difficulty of the SSL network. To address this issue, in this paper, we propose an innovative semi-supervised network with BAlanced Subclass regularIzation and semantic-Conflict penalty mechanism (BASIC) to effectively learn the unbiased knowledge for semi-supervised MoS. Concretely, we construct a novel auxiliary subclass segmentation (SCS) task based on priorly generated balanced subclasses, thus deeply excavating the unbiased information for the main MoS task with the fashion of multi-task learning. Additionally, based on a mean teacher framework, we elaborately design a balanced subclass regularization to utilize the teacher predictions of SCS task to supervise the student predictions of MoS task, thus effectively transferring unbiased knowledge to the MoS subnetwork and alleviating the influence of the class-imbalance problem. Considering the similar semantic information inside the subclasses and their corresponding original classes (i.e., parent classes), we devise a semantic-conflict penalty mechanism to give heavier punishments to the conflicting SCS predictions with wrong parent classes and provide a more accurate constraint to the MoS predictions. Extensive experiments conducted on two publicly available datasets, i.e., the WORD dataset and the MICCAI FLARE 2022 dataset, have verified the superior performance of our proposed BASIC compared to other state-of-the-art methods.