GLI-AL: A Multi-Modal Glioma MRI Label Resource with Unified Anatomy-Lesion Labels

2026-07-24

AI Summary

This study addresses a critical limitation in the existing BraTS-GLI dataset, which annotates only tumor subregions while ignoring co-occurring abnormalities such as white matter hyperintensities (WMH), leading to mislabeling of pathological tissues as normal and introducing label noise in joint segmentation tasks. To overcome this, the authors construct the first unified anatomical–lesion multi-sequence MRI labeling resource based on the BraTS 2023-GLI training cohort, encompassing 1,251 cases with eight distinct labels—including healthy tissue and multiple coexisting pathologies—and partitioned into curated and extended subsets to enable reproducible evaluation. Leveraging expert-level multimodal annotations (e.g., T1, FLAIR), image curation, and standardized metadata management, this resource uniquely integrates healthy brain structures with diverse lesion types in glioma MRI. Experiments demonstrate that WMH-aware supervision significantly enhances sensitivity to coexisting abnormalities while preserving healthy tissue segmentation performance, outperforming models trained with the original noisy labels.

Abstract

Existing BraTS-GLI datasets provide a widely used benchmark for adult glioma MRI segmentation, but their task definition focuses on tumor subregions and does not systematically represent coexisting white matter hyperintensities (WMH). In joint segmentation settings, such unlabeled abnormalities introduce task-specific label noise by treating pathological regions as normal tissue. To address this limitation, we introduce BraTS-GLI Anatomy-Lesion, a controlled-access, labels-only derived resource built from the BraTS 2023-GLI training cohort. The resource provides 1,251 unified eight-class anatomy-lesion label sets aligned with the original four-modal MRI cases, including image-repair labels for 116 cases requiring repaired imaging inputs. The cohort is organized into a 394-case purified subset and an 857-case extended subset, with case-level metadata covering label source, image-repair requirements, quality-control status, access conditions, checksums, and release boundaries. Compared with the original BraTS-GLI annotations, the resource substantially expands foreground supervision by incorporating healthy brain tissues and previously unlabeled coexisting abnormalities within a unified label space. A validation study using MedNeXt and T1/FLAIR inputs suggests that WMH-aware supervision preserves healthy-tissue segmentation performance across both in-domain GLI and external WMH datasets, while improving sensitivity to coexisting lesions relative to noisy-control training. The resource is intended for scientific research and supports joint anatomy-lesion supervision, label-noise analysis, and reproducible evaluation. Data are available at https://www.synapse.org/Synapse:syn75210889/wiki/, and code is available at https://github.com/xyx200/brats-gli-anatomy-lesion-code. The data resource DOI is https://doi.org/10.7303/SYN75210889.

Problem

• glioma
• white matter hyperintensities
• label noise
• MRI segmentation
• coexisting lesions

Innovation

• multi-modal MRI
• unified anatomy-lesion labeling
• white matter hyperintensities
• label noise mitigation
• joint segmentation