AI Assessment of Heterogeneous Histopathologic Brain Tumor Sub-regions: the RANO MICCAI BraTS-Path 2024 Challenge.
BACKGROUND: Automated classification of glioblastoma (IDH-wt, WHO CNS Gr.4) histopathologic sub-regions in whole slide images (WSI) is essential for quantitative tumor characterization, but faces substantial challenges from intra-tumoral heterogeneity and inter-observer annotation variability. The AI-RANO & RANO-Pathology working groups organized BraTS-Path 2024, representing the first international benchmarking environment and publicly available spatially annotated dataset, towards promoting the development and fair evaluation of Artificial Intelligence (AI) models to classify specific sub-regions: cellular tumor, pseudopalisading necrosis (PN), microvascular proliferation, geographic necrosis, infiltration into the cortex, and white matter penetration (WM). METHODS: Multi-institutional H&E-stained WSIs had reference standard samples generated by eight expert neuropathologists, following a rigorous peer review protocol, resulting in 309,118 data samples (training/validation/hold-out testing: 96,485/62,387/150,246). Quantitative performance evaluation of six AI approaches was conducted based on multiple metrics, including Accuracy and Matthew's correlation coefficient (MCC). A robust statistically-aware ranking strategy offered statistical significance of the final rankings. RESULTS: Top-performing approaches employed common strategies, including large pre-trained models, ensembling, and extensive data augmentation, reporting Accuracy=0.69 and MCC=0.58. Key challenges included severe class imbalance, hampering minority class performance, and inter-annotator variability, especially for ambiguous sub-regions such as PN or WM. CONCLUSIONS: BraTS-Path represents a valuable public resource for glioblastoma histopathologic sub-region assessment. Our findings indicate the specific task remaining an open research problem, highlighting the influence of rare sub-regions, the absence of a consistent "gold standard" annotation protocol, and the potential of foundation models to improve generalization, guiding future research toward developing more reliable AI tools for quantitative neuropathology.
Authors
- Bjoern H. Menze (ORCID: https://orcid.org/0000-0003-4136-5690)
- Susan Chang (ORCID: https://orcid.org/0009-0001-2084-3959)
- Maria A. Gubbiotti (ORCID: https://orcid.org/0000-0003-2246-7958)
- Shahriar Faghani (ORCID: https://orcid.org/0000-0003-3275-2971)
- Bhakti Baheti (ORCID: https://orcid.org/0000-0001-5475-3903)
- Sylwia Malec (ORCID: https://orcid.org/0000-0002-3603-9930)
- Shubham Innani (ORCID: https://orcid.org/0000-0003-3616-0308)
- Martin J. van den Bent (ORCID: https://orcid.org/0000-0001-5710-5127)
- Matthew W. Pease (ORCID: https://orcid.org/0000-0001-6125-9858)
- David Becerra (ORCID: https://orcid.org/0000-0002-6944-916X)
- Marek Wodziński (ORCID: https://orcid.org/0000-0002-8076-6246)
- Giselle Yvette Lopez (ORCID: https://orcid.org/0000-0001-5435-6668)
- Dominic LaBella (ORCID: https://orcid.org/0000-0003-1713-9538)
- Jason T. Huse (ORCID: https://orcid.org/0000-0003-4514-0640)
- Mana Moassefi (ORCID: https://orcid.org/0000-0002-0111-7791)
- Akis Linardos (ORCID: https://orcid.org/0000-0002-5470-1908)
- Ujjwal Baid (ORCID: https://orcid.org/0000-0001-5246-2088)
- Jeffrey J. Helgager
- Lee Cooper (ORCID: https://orcid.org/0000-0002-3504-4965)
- M. L. Miller (ORCID: https://orcid.org/0000-0002-6350-5706)
- Benedikt Wiestler (ORCID: https://orcid.org/0000-0002-2963-7772)
- Verena Chung (ORCID: https://orcid.org/0000-0002-5622-7998)
- Alexandros Karargyris (ORCID: https://orcid.org/0000-0002-1930-3410)
- Pallavi Tiwari (ORCID: https://orcid.org/0000-0001-9477-4856)
- Spyridon Bakas (ORCID: https://orcid.org/0000-0001-8734-6482)
- Siddhesh Pravin Thakur (ORCID: https://orcid.org/0000-0003-4807-2495)
- MacLean P. Nasrallah (ORCID: https://orcid.org/0000-0003-4861-0898)
- Patrick Y Wen (ORCID: https://orcid.org/0000-0002-2452-0540)
- Valeria Barresi (ORCID: https://orcid.org/0000-0001-7086-1920)
- Syed Rameem Zahra (ORCID: https://orcid.org/0000-0002-6416-2143)
- Timothy Francis Cloughesy (ORCID: https://orcid.org/0000-0002-8656-7483)
- Hasan Kassem (ORCID: https://orcid.org/0000-0001-5830-8890)
- Sarthak Pati (ORCID: https://orcid.org/0000-0003-2243-8487)
- Zhifan Jiang (ORCID: https://orcid.org/0000-0001-5713-1675)
- Olivia K. Krebs
- Marius George Linguraru (ORCID: https://orcid.org/0000-0001-6175-8665)
- Jared T. Ahrendsen (ORCID: https://orcid.org/0000-0002-9309-6544)
- Nelly Jazmín Sandino (ORCID: https://orcid.org/0000-0001-9696-8339)
- Ankur Gupta (ORCID: https://orcid.org/0000-0002-6515-2596)
- Ying Weng (ORCID: https://orcid.org/0000-0003-4338-713X)
- Sanyukta Adap (ORCID: https://orcid.org/0009-0006-3639-0911)
- Michael A. Vogelbaum
- Jeff Rudie
- Twinkle Dhingra (ORCID: https://orcid.org/0009-0002-5157-0014)
- Raymond Huang
- Rithik Kumar (ORCID: https://orcid.org/0009-0001-3339-200X)
- Vansh Kakkar (ORCID: https://orcid.org/0009-0003-0717-1873)
- Madhav Arora (ORCID: https://orcid.org/0009-0001-4940-9531)
- Calixto-Hope G. Lucas (ORCID: https://orcid.org/0000-0002-8347-9592)
- Maria Correia de Verdier
- Alvaro A Sandino
- William R Bell
- Eduardo Romero
- Henning Müller
- Ke Chen
- Carla Pitarch-Abaigar
- Vinit
- Juexin Zhang
Institutions
- Northwestern University (US)
- University of Geneva (CH)
- Uppsala University (SE)
- Brigham and Women's Hospital (US)
- Sher-e-Kashmir University of Agricultural Sciences and Technology of Kashmir (IN)
- Georgia Institute of Technology (US)
- Sage Bionetworks (US)
- Mayo Clinic (US)
- Children's National (US)
- The University of Texas MD Anderson Cancer Center (US)
- University of Wisconsin–Madison (US)
- University of Nottingham Ningbo China (CN)
- Harvard University (US)
- Johns Hopkins University (US)
- Emory University (US)
- University of California, Los Angeles (US)
- Duke University (US)
- HES-SO University of Applied Sciences and Arts Western Switzerland (CH)
- University of California, San Francisco (US)
- George Washington University (US)
- University of Zurich (CH)
- Columbia University Irving Medical Center (US)
- Johns Hopkins Medicine (US)
- Erasmus MC (NL)
- The Wallace H. Coulter Department of Biomedical Engineering (US)
- Moffitt Cancer Center (US)
- Netaji Subhas University of Technology (IN)
- Universidad Nacional de Colombia (CO)
- University of California San Diego (US)
- Dana-Farber Cancer Institute (US)
- Duke Medical Center (US)
- HES-SO Valais-Wallis (CH)
- Fondazione IRCCS Istituto Neurologico Carlo Besta (IT)
- Indiana University Indianapolis (US)
- Indiana University Melvin and Bren Simon Comprehensive Cancer Center (US)
- Indiana University School of Medicine (US)
- Sheikh Zayed Institute for Pediatric Surgical Innovation (US)
- Case Western Reserve University (US)
- Technical University of Munich (DE)
- AGH University of Krakow (PL)
- University of Pennsylvania (US)
Publication Details
- Journal
- PubMed
- Published
- 2026-11-12
- DOI
- https://doi.org/10.1093/neuonc/noag283
- Primary Topic
- AI in cancer detection
- Type
- article
- Field-Weighted Citation Impact
- 0.00