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

2026-02-09

AI Summary

This study addresses the challenges of brain tumor segmentation, particularly the scarcity of labeled MRI data due to high annotation costs and heterogeneity across multi-center datasets. To this end, the authors propose an uncertainty-aware semi-supervised teacher-student framework that integrates confidence-driven progressive curriculum learning with a selective forgetting mechanism. The approach leverages dual loss objectives and consistency optimization to enhance model robustness and generalization under limited annotation. Evaluated on the BraTS 2021 dataset using only 10% of the labeled data, the student model achieves a validation Dice Similarity Coefficient (DSC) of 0.872 and outperforms the teacher model across multiple tumor sub-regions, notably recovering the enhancing tumor class with a DSC of 0.620.

Technology Category

• Machine Learning: Semi-Supervised Learning
• Computer Vision: Segmentation
• Search and Optimization: Learning to Search

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

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.

Problem

• brain tumor segmentation
• data annotation scarcity
• 3D MRI
• semi-supervised learning
• data heterogeneity

Innovation

• semi-supervised learning
• teacher-student framework
• uncertainty-aware pseudo-labeling
• confidence-based curriculum
• brain tumor segmentation