Analysis of the BraTS 2023 Intracranial Meningioma Segmentation Challenge

We describe the design and results from the BraTS 2023 Intracranial Meningioma Segmentation Challenge. The BraTS Meningioma Challenge differed from prior BraTS Glioma challenges in that it focused on meningiomas, which are typically benign extra-axial tumors with diverse radiologic and anatomical presentation and a propensity for multiplicity. Nine participating teams each developed deep-learning automated segmentation models using image data from the largest multi-institutional systematically expert annotated multilabel multi-sequence meningioma MRI dataset to date, which included 1000 training set cases, 141 validation set cases, and 283 hidden test set cases. Each case included T2, FLAIR, T1, and T1Gd brain MRI sequences with associated tumor compartment labels delineating enhancing tumor, non-enhancing tumor, and surrounding non-enhancing FLAIR hyperintensity. Participant automated segmentation models were evaluated and ranked based on a scoring system evaluating lesion-wise metrics including dice similarity coefficient (DSC) and 95% Hausdorff Distance. The top ranked team had a lesion-wise median dice similarity coefficient (DSC) of 0.976, 0.976, and 0.964 for enhancing tumor, tumor core, and whole tumor, respectively and a corresponding average DSC of 0.899, 0.904, and 0.871, respectively. These results serve as state-of-the-art benchmarks for future pre-operative meningioma automated segmentation algorithms. Additionally, we found that 1286 of 1424 cases (90.3%) had at least 1 compartment voxel abutting the edge of the skull-stripped image edge, which requires further investigation into optimal pre-processing face anonymization steps.

Authors

Institutions

Publication Details

Journal
The Journal of Machine Learning for Biomedical Imaging
Published
2025-03-07
DOI
https://doi.org/10.59275/j.melba.2025-bea1
Citations
5
Primary Topic
Meningioma and schwannoma management
Type
article
Field-Weighted Citation Impact
6.77
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Analysis of the BraTS 2023 Intracranial Meningioma Segmentation Challenge

Anahita Fathi Kazerooni, Tanvir Rizvi, Nico Sollmann, Bjoern Menze et al.
5 citations
The Journal of Machine Learning for Biomedical Imaging
Meningioma and schwannoma management
6.77
article

Analysis of the BraTS 2023 Intracranial Meningioma Segmentation Challenge

Anahita Fathi Kazerooni, Tanvir Rizvi, Nico Sollmann, Bjoern Menze, Shahriar Faghani, Marie Piraud, Scott Floyd, Jake Albrecht, Udunna Anazodo, Michel Bilello, Chunhao Wang, Nastaran Khalili, Mahsa Taherzadeh, Muhammad Ammar Haider, Talissa A. Altes, Dominic LaBella, Fathi Hilal, John Freymann, Michelle Alonso‐Basanta, Yulia Bronstein, Elaine Johanson, Walter F. Wiggins, Khanak Nandolia, Adam E. Flanders, Farouk Dako, Devon Godfrey, Ujjwal Baid, Andreas M. Rauschecker, Keyvan Farahani, Evan G. Stein, Christos A. Davatzikos, Mana Moassefi, Ali Hussain, Arif Rashid, Daniel Warren, Aoife Haughey, Nazanin Maleki, Ivan Ezhov, Benedikt Wiestler, Zachary J. Reitman, Evan Calabrese, Verena Chung, Marco C. Pinho, Ahmed W. Moawad, Alexandros Karargyris, Spyridon Bakas, Koen Van Leemput, Rachit Saluja, Ayman Nada, Kevin Leu, Rong Chai, Javier Villanueva-Meyer, John Mongan, Luca Saba, Juan Eugenio Iglesias, Micah Sheller, Collin Kent, Pranav Warman, Aly Abayazeed, Raymond Y. Huang, Yury Velichko, Priscila Crivellaro, Hasan Kassem, András Jakab, Marinos S. Kontzialis, Sarthak Pati, Zhifan Jiang, Melanie Brüßeler, Pierre Nedelec, Syed Muhammad Anwar, Christopher Paul Hess, Shan McBurney-Lin, Alejandro Aristizábal, Roula Hourani, Jeffrey D. Rudie, Joel M. Stein, Yasaman Sharifi, Shehbaz Mohd Salim Ansari, Maruf Adewole, Nourel Hoda Tahon, Anastasia Janas, Marius George Linguraru, Gennaro D’Anna, Mariam Aboian, Timothy Bergquist, John P. Kirkpatrick, J. Mark Eddy, Ryan McLean, Aria Mahtabfar, Philipp Lohmann, Zeke Meier, Maxence Pajot, Rachel Akinola, Klara Willms, Lisa Deptula, Mohammed Yahya Moshebah, David Diffley, Athanasios Gkampenis, Islam H. Shawali, Abdullah Okar, Yaseen Dhemesh, Nikolay Yordanov, Ahmed Magdy Abouelatta, Dominic Kite, Maria Correia de Verdier, Phillipp Vollmuth, Pascal Fehringer, Hongwei Li, Eduardo Portela de Oliveira, Xinyang Liu, Ahmed Taha, Benjamin Turner, Omaditya Khanna, Florian Kofler, Russell Takeshi Shinohara, Radhika Bhalerao, Matthew W. Pease, Gian-Marco Conte, Aya Mansour, Dann C. Martin, David Maximilian Weiss, Sully Francis Chen
article en
5 citations

Abstract

We describe the design and results from the BraTS 2023 Intracranial Meningioma Segmentation Challenge. The BraTS Meningioma Challenge differed from prior BraTS Glioma challenges in that it focused on meningiomas, which are typically benign extra-axial tumors with diverse radiologic and anatomical presentation and a propensity for multiplicity. Nine participating teams each developed deep-learning automated segmentation models using image data from the largest multi-institutional systematically expert annotated multilabel multi-sequence meningioma MRI dataset to date, which included 1000 training set cases, 141 validation set cases, and 283 hidden test set cases. Each case included T2, FLAIR, T1, and T1Gd brain MRI sequences with associated tumor compartment labels delineating enhancing tumor, non-enhancing tumor, and surrounding non-enhancing FLAIR hyperintensity. Participant automated segmentation models were evaluated and ranked based on a scoring system evaluating lesion-wise metrics including dice similarity coefficient (DSC) and 95% Hausdorff Distance. The top ranked team had a lesion-wise median dice similarity coefficient (DSC) of 0.976, 0.976, and 0.964 for enhancing tumor, tumor core, and whole tumor, respectively and a corresponding average DSC of 0.899, 0.904, and 0.871, respectively. These results serve as state-of-the-art benchmarks for future pre-operative meningioma automated segmentation algorithms. Additionally, we found that 1286 of 1424 cases (90.3%) had at least 1 compartment voxel abutting the edge of the skull-stripped image edge, which requires further investigation into optimal pre-processing face anonymization steps.

The Journal of Machine Learning for Biomedical ImagingVol. 3(March 2025)
Northwestern University (US), Leidos (United States) (US), Uppsala University (SE), Brigham and Women's Hospital (US), Rush University Medical Center (US), Montreal Neurological Institute and Hospital (CA), Leeds General Infirmary (GB), National Institutes of Health (US), Catholic Medical Center (US), United States Food and Drug Administration (US), Booz Allen Hamilton (United States) (US), Sage Bionetworks (US), Children's Hospital of Philadelphia (US), Children's National (US), Harvard University (US), Cairo University (EG), Thomas Jefferson University (US), University of Ottawa (CA), Universität Hamburg (DE), University of San Diego (US), Iran University of Medical Sciences (IR), Forschungszentrum Jülich (DE), German Cancer Research Center (DE), University of California, San Francisco (US), University of Toronto (CA), George Washington University (US), University of Zurich (CH), Washington University in St. Louis (US), Cornell University (US), Heidelberg University (DE), CMH Lahore Medical College and Institute of Dentistry (PK), University Hospital Bonn (DE), University Hospitals Bristol NHS Foundation Trust (GB), Lagos University Teaching Hospital (NG), King Fahd Medical City (SA), TUM Klinikum (DE), University of California System (US), University of Rochester Medical Center (US), Medical University of Sofia (BG), Yale University (US), Massachusetts General Hospital (US), American University of Beirut Medical Center (LB), Mercy Catholic Medical Center (US), Helmholtz Institute Mainz (DE), Radiology Associates (US), Essen University Hospital (DE), Ross University School of Medicine (BB), Azienda Ospedaliero-Universitaria Cagliari (IT), Mayo Clinic in Arizona (US), Duke Medical Center (US), Athinoula A. Martinos Center for Biomedical Imaging (US), Penn Center for AIDS Research (US), Center for Global Health (US), Frederick National Laboratory for Cancer Research (US), Jena University Hospital (DE), Stanford Medicine (US), National Cancer Institute (US), University Hospital of Ioannina (GR), Mayo Clinic in Florida (US), Duke University Hospital (US), University Hospital Ulm (DE), Neurological Surgery (US), Intel (United Kingdom) (GB), Fort Worth Library (US), All India Institute of Medical Sciences Rishikesh (IN), University Hospitals Bristol and Weston NHS Foundation Trust (GB), Indiana University School of Medicine, Aziende Socio Sanitarie Territoriale Ovest Milanese, University College London (GB), University of Manitoba (CA), McGill University (CA), University of Virginia (US), Indiana University – Purdue University Indianapolis (US), New York University (US), Technical University of Munich (DE), Massachusetts Institute of Technology (US), Friedrich Schiller University Jena (DE), University of Missouri (US), University of Pennsylvania (US), Ludwig-Maximilians-Universität München (DE), The University of Texas Southwestern Medical Center (US), RWTH Aachen University (DE), Vanderbilt University Medical Center (US), Philadelphia University (US), Technical University of Denmark (DK)
Openalex Percentile: Top 3%
Meningioma and schwannoma management
6.77
DOISourceOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.