The Brain Tumor Segmentation (BraTS-METS) Challenge 2023: Brain Metastasis Segmentation on Pre-treatment MRI

The translation of AI-generated brain metastases (BM) segmentation into clinical practice relies heavily on diverse, high-quality annotated medical imaging datasets. The BraTS-METS 2023 challenge has gained momentum for testing and benchmarking algorithms using rigorously annotated internationally c...

Full description

Saved in:

Bibliographic Details
Main Authors:	Moawad, Ahmed W, Janas, Anastasia, Baid, Ujjwal, Ramakrishnan, Divya, Saluja, Rachit, Ashraf, Nader, Amiruddin, Raisa, Anwar, Syed Muhammad, Chiang, Veronica, Chung, Verena, Conte, Gian Marco Marco, Eddy, James, Ezhov, Ivan, Iglesias, Juan Eugenio, Jiang, Zhifan, Kazerooni, Anahita Fathi, Kofler, Florian, Krantchev, Kiril, LaBella, Dominic, Van Leemput, Koen, Linguraru, Marius George, Liu, Xinyang, Menze, Bjoern H, Piraud, Marie, Shinohara, Russel Takeshi, Nada, Ayman, Wang, Chunhao, Willms, Klara, Avesta, Arman, Bousabarah, Khaled, Chakrabarty, Satrajit, Gennaro, Nicolo, LaMontagne, Pamela, Maresca, Ryan, Teytelboym, Oleg, Westerhoff, Malte, Villanueva-Meyer, Javier, Brugnara, Gianluca, Kam, Anthony, Kwan, Benjamin Yin Ming, Lall, Neil U, Thompson, Gerard, Wu, Lei, Bansal, Anu, Besada, Cristina, Dusoi, Alexandru, Farage, Luciano, Fong, Amy, Gray, R. Ian, Ikuta, Ichiro, Joyner, David, Krumpelman, Chase, Lincoln, Christie M, Morón, Fanny, Ozsarlak, Ozkan, Rohatgi, Saurabh, Saha, Atin, Schwartz, Eric D, Tanwar, Manoj, Valerie, Jewels, Fehringer, Pascal, Ghonim, Mohamed, Gkampenis, Athanasios, Singh, Gagandeep, Soumala, Theodora, Taherzadeh, Mahsa, Vollmuth, Philipp, Abayazeed, Aly H, Dellepiane, Francesco, Lohmann, Philipp, Al-Rubaiey, Sanaria, Armindo, Rui Duarte, Asla, Moamen M, Bisschop, Jeroen, Lomer, Nima Broomand, Chen, Jim, Crawley, Alexis, Faghani, Shahriar, Gulati, Vaibhav, Hierro, Fátima, Dahl, Rasmus Holmboe, Jacobs, Sarah Maria, Kandemirli, Sedat G, Li, Xiao, Marsiglia, Marcela, Morsi, Samah Mostafa, Nandolia, Khanak K, Naqvi, Syed Raza, Nikanpour, Yalda, Alnoury, Mostafa, Patel, Markand D, Rawie, Eric, Sanchez-Garcia, Laura M, Isufi, Edvin, Vilanilam, George K, Yousry, Sara, Kassem, Hasan, Pati, Sarthak, Rudie, Jeffrey D, Aboian, Mariam
Format:	Journal Article
Language:	English
Published:	01-06-2023
Subjects:	Quantitative Biology - Other
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	The translation of AI-generated brain metastases (BM) segmentation into clinical practice relies heavily on diverse, high-quality annotated medical imaging datasets. The BraTS-METS 2023 challenge has gained momentum for testing and benchmarking algorithms using rigorously annotated internationally compiled real-world datasets. This study presents the results of the segmentation challenge and characterizes the challenging cases that impacted the performance of the winning algorithms. Untreated brain metastases on standard anatomic MRI sequences (T1, T2, FLAIR, T1PG) from eight contributed international datasets were annotated in stepwise method: published UNET algorithms, student, neuroradiologist, final approver neuroradiologist. Segmentations were ranked based on lesion-wise Dice and Hausdorff distance (HD95) scores. False positives (FP) and false negatives (FN) were rigorously penalized, receiving a score of 0 for Dice and a fixed penalty of 374 for HD95. Eight datasets comprising 1303 studies were annotated, with 402 studies (3076 lesions) released on Synapse as publicly available datasets to challenge competitors. Additionally, 31 studies (139 lesions) were held out for validation, and 59 studies (218 lesions) were used for testing. Segmentation accuracy was measured as rank across subjects, with the winning team achieving a LesionWise mean score of 7.9. Common errors among the leading teams included false negatives for small lesions and misregistration of masks in space.The BraTS-METS 2023 challenge successfully curated well-annotated, diverse datasets and identified common errors, facilitating the translation of BM segmentation across varied clinical environments and providing personalized volumetric reports to patients undergoing BM treatment.
DOI:	10.48550/arxiv.2306.00838