Multimodal MRI Report Findings Supervised Brain Lesion Segmentation with Substructures

TL;DR

This paper introduces MS-RSuper, a novel report-supervised learning framework for brain lesion segmentation that effectively utilizes hierarchical and uncertain radiology report cues to improve accuracy on multi-parametric MRI data.

Contribution

The paper proposes a unified, uncertainty-aware report supervision method that aligns qualitative and quantitative findings with brain substructures, addressing report incompleteness and cohort variability.

Findings

MS-RSuper outperforms baseline methods on BraTS-MET/MEN datasets.

Effectively utilizes hierarchical and uncertain report cues.

Improves lesion segmentation accuracy in multi-parametric MRI.

Abstract

Report-supervised (RSuper) learning seeks to alleviate the need for dense tumor voxel labels with constraints derived from radiology reports (e.g., volumes, counts, sizes, locations). In MRI studies of brain tumors, however, we often involve multi-parametric scans and substructures. Here, fine-grained modality/parameter-wise reports are usually provided along with global findings and are correlated with different substructures. Moreover, the reports often describe only the largest lesion and provide qualitative or uncertain cues (``mild,'' ``possible''). Classical RSuper losses (e.g., sum volume consistency) can over-constrain or hallucinate unreported findings under such incompleteness, and are unable to utilize these hierarchical findings or exploit the priors of varied lesion types in a merged dataset. We explicitly parse the global quantitative and modality-wise qualitative findings and introduce a unified, one-sided, uncertainty-aware formulation (MS-RSuper) that: (i) aligns modality-specific qualitative cues (e.g., T1c enhancement, FLAIR edema) with their corresponding substructures using existence and absence losses; (ii) enforces one-sided lower-bounds for partial quantitative cues (e.g., largest lesion size, minimal multiplicity); and (iii) adds extra- vs. intra-axial anatomical priors to respect cohort differences. Certainty tokens scale penalties; missing cues are down-weighted. On 1238 report-labeled BraTS-MET/MEN scans, our MS-RSuper largely outperforms both a sparsely-supervised baseline and a naive RSuper method.