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=Volume 9 - 2018

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 newly suggested tools difficult to compare, and often requires researchers
to implement a previously published algorithm first to have an adequate benchmark on their
data set. The Ischemic Stroke Lesion Segmentation (ISLES) challenge, ran now consecutively
for three years, aims to address this problem of comparability. ISLES 2016 & 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 and 15 research teams participated for ISLES 2016 and ISLES 2017, respectively. Their
performance was then evaluated in a fair and transparent way to identify the state-of-the-art
amongst all submissions. Top ranked teams almost always employed deep learning tools, which
were predominately constitutional neural networks (CNNs). Despite the great efforts, lesion
outcome prediction remains a great challenge. The annotated data sets stays publicly available
and new approaches can be compared directly via the online evaluation system, serving as a
continuing benchmark (www.isles-challenge.org)