BraTS-Path Challenge: Assessing Heterogeneous Histopathologic Brain Tumor Sub-regions

TL;DR

The BraTS-Path Challenge introduces a comprehensive dataset and benchmarking platform for deep learning models to identify histopathologic tumor sub-regions in glioblastoma, aiming to improve diagnosis and understanding of tumor heterogeneity.

Contribution

This work presents a new challenge with a curated dataset and evaluation framework for deep learning models targeting histopathologic sub-regions of glioblastoma.

Findings

Benchmarking results of various models on tumor sub-region identification

Insights into model performance across different histopathologic features

Establishment of a standardized evaluation protocol for histopathologic segmentation

Abstract

Glioblastoma is the most common primary adult brain tumor, with a grim prognosis - median survival of 12-18 months following treatment, and 4 months otherwise. Glioblastoma is widely infiltrative in the cerebral hemispheres and well-defined by heterogeneous molecular and micro-environmental histopathologic profiles, which pose a major obstacle in treatment. Correctly diagnosing these tumors and assessing their heterogeneity is crucial for choosing the precise treatment and potentially enhancing patient survival rates. In the gold-standard histopathology-based approach to tumor diagnosis, detecting various morpho-pathological features of distinct histology throughout digitized tissue sections is crucial. Such "features" include the presence of cellular tumor, geographic necrosis, pseudopalisading necrosis, areas abundant in microvascular proliferation, infiltration into the cortex, wide extension in subcortical white matter, leptomeningeal infiltration, regions dense with macrophages, and the presence of perivascular or scattered lymphocytes. With these features in mind and building upon the main aim of the BraTS Cluster of Challenges https://www.synapse.org/brats2024, the goal of the BraTS-Path challenge is to provide a systematically prepared comprehensive dataset and a benchmarking environment to develop and fairly compare deep-learning models capable of identifying tumor sub-regions of distinct histologic profile. These models aim to further our understanding of the disease and assist in the diagnosis and grading of conditions in a consistent manner.