Analysis of the MICCAI Brain Tumor Segmentation -- Metastases (BraTS-METS) 2025 Lighthouse Challenge: Brain Metastasis Segmentation on Pre- and Post-treatment MRI

/ Authors

Nazanin Maleki, R. Amiruddin, A. Moawad, N. Yordanov, A. Gkampenis, P. Fehringer, F. Umeh, C. Chukwurah, F. Memon, Bojan Petrovic

and 232 more authors

Justin A. Cramer, M. Krycia, Elizabeth B. Shrickel, I. Ikuta, G. Thompson, L. Vidal, Vilma Kosovic, A. Goldman-Yassen, Virginia Hill, Tiffany So, S. Mhana, A. Alotaibi, N. Page, Prisha Bhatia, Yasaman Sharifi, M. Jakovljevic, Salma A. S. Abosabie, Sara A. Abosabie, Mohanad Ghonim, Mohamed Ghonim, Amirreza Manteghinejad, A. Janas, K. Krantchev, Maruf Adewole, Jake Albrecht, U. Anazodo, S. Aneja, S. M. Anwar, Timothy Bergquist, V. Chiang, Verena Chung, G. Conte, F. Dako, James A. Eddy, I. Ezhov, Nastaran Khalili, K. Farahani, J. E. Iglesias, Zhifan Jiang, Elaine Johanson, A. Kazerooni, F. Kofler, D. LaBella, K. V. Leemput, H. Li, M. Linguraru, Xinyang Liu, Zeke Meier, Bjoern H Menze, Harrison Moy, K. Osenberg, M. Piraud, Z. Reitman, Russell T. Shinohara, Chunhao Wang, B. Wiestler, Walter F. Wiggins, U. Shafique, Klara Willms, A. Avesta, K. Bousabarah, Satrajit Chakrabarty, Nicolo Gennaro, W. Holler, Manpreet Kaur, P. LaMontagne, Mingde Lin, J. Lost, Daniel S. Marcus, R. Maresca, S. Merkaj, Gabriel Cassinelli Pedersen, Marc von Reppert, A. Sotiras, O. Teytelboym, Niklas Tillmans, M. Westerhoff, Ayda Youssef, Devon Godfrey, Scott R Floyd, A. Rauschecker, J. Villanueva-Meyer, Irada Pfluger, Jaeyoung Cho, M. Bendszus, G. Brugnara, Gloria J. Guzman Perez-Carillo, Derek R. Johnson, Anthony W. Kam, B. Kwan, Lillian Lai, N.U. Lall, S. Patro, Lei Wu, Anu Bansal, F. Barkhof, Cristina H. Besada, Sammy Chu, J. Druzgal, Alexandru-Eugen Dusoi, Luciano Farage, Fabricio Feltrin, Amy Z. Fong, Steve H. Fung, R. Gray, Michael Iv, A. Postma, Amit Mahajan, David Joyner, C. Krumpelman, L. Létourneau-Guillon, Christie M Lincoln, M. Maros, Elka Miller, Fanny Mor'on, E. Nimchinsky, O. Ozsarlak, Uresh Patel, Saurabh Rohatgi, Atin Saha, A. Sayah, Eric D. Schwartz, Robert Shih, M. Shiroishi, Juan E. Small, Manoj Tanwar, Jewels Valerie, Brent D. Weinberg, Matthew L. White, R. Young, V. Zohrabian, Aynur Azizova, Melanie Brusseler, Abdullah Okar, Luca Pasquini, Gagandeep Singh, Nico Sollmann, Theodora Soumala, Mahsa Taherzadeh, Philipp Vollmuth, Martha Foltyn-Dumitru, A. Malhotra, Francesco Dellepiane, V'ictor M. P'erez-Garc'ia, H. Elhalawani, Maria Correia de Verdier, Sanaria Al Rubaiey, R. D. Armindo, Kholod Ashraf, M. M. Asla, Mohamed Badawy, Jeroen Bisschop, Nima Broomand Lomer, J. Bukatz, Jim Chen, P. Cimflova, Felix Corr, Alexis Crawley, Lisa Deptula, Tasneem Elakhdar, Islam H. Shawali, S. Faghani, Alexandra Frick, Vaibhav Gulati, M. A. Haider, F´atima Hierro, R. Dahl, S. Jacobs, K. Hsieh, S. Kandemirli, Katharina Kersting, Laura Kida, S. Kollia, Ioannis Koukoulithras, Xiao Li, A. Abouelatta, Aya Mansour, Ruxandra-Catrinel Maria-Zamfirescu, M. Marsiglia, Y. Mateo-Camacho, Mark McArthur, Olivia McDonnel, Maire McHugh, Mana Moassefi, S. Morsi, Alexander Munteanu, Khanak K. Nandolia, Syed A. R. Naqvi, Yalda Nikanpour, Mostafa Alnoury, A. Nouh, Francesca Pappafava, Markand D. Patel, Samantha Petrucci, Eric Rawie, S. Raymond, Borna Roohani, Sadeq Sabouhi, L. Garcia, Z. Shaked, P. Suthar, Talissa A Altes, Edvin Isufi, Yaseen Dhemesh, Jaime Gass, Jonathan Thacker, A. Tarabishy, Benjamin Turner, S. Vacca, G. Vilanilam, Daniel Warren, D. Weiss, F. Worede, S. Yousry, W. Lerebo, Alejandro Aristizabal, Alexandros Karargyris, Hasan Kassem, Sarthak Pati, Micah J. Sheller, K. E. Link, Evan Calabrese, N. Tahon, A. Nada, J. Rudie, Janet Reid, K. Darge, A. Abayazeed, P. Lohmann, Y. Velichko, S. Bakas, M. Aboian

/ Abstract

Despite continuous advancements in cancer treatment, brain metastatic disease remains a significant complication of primary cancer and is associated with an unfavorable prognosis. One approach for improving diagnosis, management, and outcomes is to implement algorithms based on artificial intelligence for the automated segmentation of both pre- and post-treatment MRI brain images. Such algorithms rely on volumetric criteria for lesion identification and treatment response assessment, which are still not available in clinical practice. Therefore, it is critical to establish tools for rapid volumetric segmentations methods that can be translated to clinical practice and that are trained on high quality annotated data. The BraTS-METS 2025 Lighthouse Challenge aims to address this critical need by establishing inter-rater and intra-rater variability in dataset annotation by generating high quality annotated datasets from four individual instances of segmentation by neuroradiologists while being recorded on video (two instances doing"from scratch"and two instances after AI pre-segmentation). This high-quality annotated dataset will be used for testing phase in 2025 Lighthouse challenge and will be publicly released at the completion of the challenge. The 2025 Lighthouse challenge will also release the 2023 and 2024 segmented datasets that were annotated using an established pipeline of pre-segmentation, student annotation, two neuroradiologists checking, and one neuroradiologist finalizing the process. It builds upon its previous edition by including post-treatment cases in the dataset. Using these high-quality annotated datasets, the 2025 Lighthouse challenge plans to test benchmark algorithms for automated segmentation of pre-and post-treatment brain metastases (BM), trained on diverse and multi-institutional datasets of MRI images obtained from patients with brain metastases.