DGRNet: Disagreement-Guided Refinement for Uncertainty-Aware Brain Tumor Segmentation

TL;DR

DGRNet is a novel brain tumor segmentation framework that combines multi-view disagreement-based uncertainty estimation with report-guided refinement, improving accuracy and providing reliable uncertainty measures for clinical use.

Contribution

It introduces a multi-view disagreement-based uncertainty estimation method and a text-conditioned refinement strategy for brain tumor segmentation.

Findings

Improves Dice score by 2.4% over state-of-the-art

Reduces HD95 by 11%

Provides meaningful uncertainty estimates

Abstract

Accurate brain tumor segmentation from MRI scans is critical for diagnosis and treatment planning. Despite the strong performance of recent deep learning approaches, two fundamental limitations remain: (1) the lack of reliable uncertainty quantification in single-model predictions, which is essential for clinical deployment because the level of uncertainty may impact treatment decision-making, and (2) the under-utilization of rich information in radiology reports that can guide segmentation in ambiguous regions. In this paper, we propose the Disagreement-Guided Refinement Network (DGRNet), a novel framework that addresses both limitations through multi-view disagreement-based uncertainty estimation and text-conditioned refinement. DGRNet generates diverse predictions via four lightweight view-specific adapters attached to a shared encoder-decoder, enabling efficient uncertainty quantification within a single forward pass. Afterward, we build disagreement maps to identify regions of high segmentation uncertainty, which are then selectively refined according to clinical reports. Moreover, we introduce a diversity-preserving training strategy that combines pairwise similarity penalties and gradient isolation to prevent view collapse. The experimental results on the TextBraTS dataset show that DGRNet favorably improves state-of-the-art segmentation accuracy by 2.4% and 11% in main metrics Dice and HD95, respectively, while providing meaningful uncertainty estimates.