AUTHOR=Winzeck Stefan , Hakim Arsany , McKinley Richard , Pinto José A. A. D. S. R. , Alves Victor , Silva Carlos , Pisov Maxim , Krivov Egor , Belyaev Mikhail , Monteiro Miguel , Oliveira Arlindo , Choi Youngwon , Paik Myunghee Cho , Kwon Yongchan , Lee Hanbyul , Kim Beom Joon , Won Joong-Ho , Islam Mobarakol , Ren Hongliang , Robben David , Suetens Paul , Gong Enhao , Niu Yilin , Xu Junshen , Pauly John M. , Lucas Christian , Heinrich Mattias P. , Rivera Luis C. , Castillo Laura S. , Daza Laura A. , Beers Andrew L. , Arbelaezs Pablo , Maier Oskar , Chang Ken , Brown James M. , Kalpathy-Cramer Jayashree , Zaharchuk Greg , Wiest Roland , Reyes Mauricio TITLE=ISLES 2016 and 2017-Benchmarking Ischemic Stroke Lesion Outcome Prediction Based on Multispectral MRI JOURNAL=Frontiers in Neurology VOLUME=9 YEAR=2018 URL=https://www.frontiersin.org/journals/neurology/articles/10.3389/fneur.2018.00679 DOI=10.3389/fneur.2018.00679 ISSN=1664-2295 ABSTRACT=

Performance of models highly depend not only on the used algorithm but also the data set it was applied to. This makes the comparison of newly developed tools to previously published approaches difficult. Either researchers need to implement others' algorithms first, to establish an adequate benchmark on their data, or a direct comparison of new and old techniques is infeasible. The Ischemic Stroke Lesion Segmentation (ISLES) challenge, which has ran now consecutively for 3 years, aims to address this problem of comparability. ISLES 2016 and 2017 focused on lesion outcome prediction after ischemic stroke: By providing a uniformly pre-processed data set, researchers from all over the world could apply their algorithm directly. A total of nine teams participated in ISLES 2015, and 15 teams participated in ISLES 2016. Their performance was evaluated in a fair and transparent way to identify the state-of-the-art among all submissions. Top ranked teams almost always employed deep learning tools, which were predominately convolutional neural networks (CNNs). Despite the great efforts, lesion outcome prediction persists challenging. The annotated data set remains publicly available and new approaches can be compared directly via the online evaluation system, serving as a continuing benchmark (www.isles-challenge.org).