Addressing data annotation scarcity in Brain Tumor Segmentation on 3D MRI scan Using a Semi-Supervised Teacher-Student Framework

TL;DR

This paper introduces a semi-supervised teacher-student framework for brain tumor segmentation on 3D MRI scans, effectively addressing data annotation scarcity and heterogeneity, and demonstrating significant improvements in segmentation accuracy with limited labeled data.

Contribution

It proposes a novel confidence-based curriculum and agreement refinement in a semi-supervised setting, enhancing pseudo-label quality and segmentation performance.

Findings

Validation DSC increased from 0.393 to 0.872 with more data.

Student outperformed teacher on tumor subregions.

Effective segmentation achieved with limited labeled data.

Abstract

Accurate brain tumor segmentation from MRI is limited by expensive annotations and data heterogeneity across scanners and sites. We propose a semi-supervised teacher-student framework that combines an uncertainty-aware pseudo-labeling teacher with a progressive, confidence-based curriculum for the student. The teacher produces probabilistic masks and per-pixel uncertainty; unlabeled scans are ranked by image-level confidence and introduced in stages, while a dual-loss objective trains the student to learn from high-confidence regions and unlearn low-confidence ones. Agreement-based refinement further improves pseudo-label quality. On BraTS 2021, validation DSC increased from 0.393 (10% data) to 0.872 (100%), with the largest gains in early stages, demonstrating data efficiency. The teacher reached a validation DSC of 0.922, and the student surpassed the teacher on tumor subregions (e.g., NCR/NET 0.797 and Edema 0.980); notably, the student recovered the Enhancing class (DSC 0.620) where the teacher failed. These results show that confidence-driven curricula and selective unlearning provide robust segmentation under limited supervision and noisy pseudo-labels.