ISLES 2015-A public evaluation benchmark for ischemic stroke lesion segmentation from multispectral MRI
Journal article, 2017

Ischemic stroke is the most common cerebrovascular disease, and its diagnosis, treatment, and study relies on non-invasive imaging. Algorithms for stroke lesion segmentation from magnetic resonance imaging (MRI) volumes are intensely researched, but the reported results are largely incomparable due to different datasets and evaluation schemes. We approached this urgent problem of comparability with the Ischemic Stroke Lesion Segmentation (ISLES) challenge organized in conjunction with the MICCAI 2015 conference. In this paper we propose a common evaluation framework, describe the publicly available datasets, and present the results of the two sub-challenges: Sub-Acute Stroke Lesion Segmentation (SISS) and Stroke Perfusion Estimation (SPES). A total of 16 research groups participated with a wide range of state-of-the-art automatic segmentation algorithms. A thorough analysis of the obtained data enables a critical evaluation of the current state-of-the-art, recommendations for further developments, and the identification of remaining challenges. The segmentation of acute perfusion lesions addressed in SPES was found to be feasible. However, algorithms applied to sub-acute lesion segmentation in SISS still lack accuracy. Overall, no algorithmic characteristic of any method was found to perform superior to the others. Instead, the characteristics of stroke lesion appearances, their evolution, and the observed challenges should be studied in detail. The annotated ISLES image datasets continue to be publicly available through an online evaluation system to serve as an ongoing benchmarking resource (www.isles-challenge.org).

Comparison

MRI

Ischemic stroke

Benchmark

Segmentation

Challenge

Author

O. Maier

Universitaet Zu Lübeck

Bjoern H. Menze

Technical University of Munich

J. von der Gablentz

Universitaet Zu Lübeck

L. Hani

University of Bern

Mattias Heinrich

Universitaet Zu Lübeck

M. Liebrand

Universitaet Zu Lübeck

S. Winzeck

Technical University of Munich

A. Basit

Pakistan Institute of Nuclear Science and Technology

P. Bentley

Imperial College London

L. Chen

Imperial College London

D. Christiaens

KU Leuven– University Hospital Leuven

KU Leuven

F. Dutil

Université de Sherbrooke

K. Egger

Universitats Klinikum Freiburg und Medizinische Fakultat

C. L. Feng

Northeastern University China

B. Glocker

Imperial College London

M. Gotz

German Cancer Research Center (DKFZ)

T. Haeck

KU Leuven

KU Leuven– University Hospital Leuven

H. L. Halme

University of Helsinki

Aalto University

M. Havaei

Université de Sherbrooke

K. M. Iftekharuddin

Old Dominion University

P. M. Jodoin

Université de Sherbrooke

K. Kamnitsas

Imperial College London

E. Kellner

Universitats Klinikum Freiburg und Medizinische Fakultat

A. Korvenoja

University of Helsinki

H. Larochelle

Université de Sherbrooke

C. Ledig

Imperial College London

J. H. Lee

National Taiwan University of Science and Technology

F. Maes

KU Leuven– University Hospital Leuven

KU Leuven

Mahmood Qaiser

Chalmers, Signals and Systems, Signal Processing and Biomedical Engineering

K. H. Maier-Hein

German Cancer Research Center (DKFZ)

R. McKinley

UniversitatsSpital Bern

J. Muschelli

Johns Hopkins University

C. Pal

École Polytechnique de Montréal

L. M. Pei

Old Dominion University

J. R. Rangarajan

KU Leuven

KU Leuven– University Hospital Leuven

S. M. S. Reza

Old Dominion University

D. Robben

KU Leuven– University Hospital Leuven

KU Leuven

D. Rueckert

Imperial College London

E. Salli

University of Helsinki

P. Suetens

KU Leuven– University Hospital Leuven

KU Leuven

C. W. Wang

National Taiwan University of Science and Technology

M. Wilms

Universitaet Zu Lübeck

J. S. Kirschke

Klinikum rechts der Isar

U. M. Kramer

Universitaet Zu Lübeck

T. F. Munte

Universitaet Zu Lübeck

P. Schramme

University Medical Center Lübeck

R. Wiest

UniversitatsSpital Bern

H. Handels

Universitaet Zu Lübeck

M. Reyes

University of Bern

Medical Image Analysis

1361-8415 (ISSN) 13618423 (eISSN)

Vol. 35 250-269

Subject Categories

Computer Vision and Robotics (Autonomous Systems)

DOI

10.1016/j.media.2016.07.009

PubMed

27475911

More information

Latest update

9/18/2018