PuSH - Publication Server of Helmholtz Zentrum München: DeepISLES: A clinically validated ischemic stroke segmentation model from the ISLES'22 challenge.

Navigation

Home

Deutsch

Research

Advanced Search

Browse by ...

... Journal

... Publication Type

... Research Data

... Publication Year

Publication overview

Support & Contact

Contact persons

Help

Data protection

de la Rosa, E.* ; Reyes, M.* ; Liew, S.L.* ; Hutton, A.* ; Wiest, R.* ; Kaesmacher, J.* ; Hanning, U.* ; Hakim, A.J.* ; Zubal, R.* ; Valenzuela, W.* ; Robben, D.* ; Sima, D.M.* ; Anania, V.* ; Brys, A.* ; Meakin, J.A.* ; Mickan, A.* ; Broocks, G.* ; Heitkamp, C.* ; Gao, S.* ; Liang, K.W.* ; Zhang, Z.* ; Rahman Siddiquee, M.M.* ; Myronenko, A.* ; Ashtari, P.* ; Van Huffel, S.* ; Jeong, H.* ; Yoon, C.* ; Kim, C.* ; Huo, J.* ; Ourselin, S.* ; Sparks, R.* ; Clèrigues, A.* ; Oliver, A.J.* ; Lladó, X.* ; Chalcroft, L.* ; Pappas, I.* ; Bertels, J.* ; Heylen, E.* ; Moreau, J.* ; Hatami, N.* ; Frindel, C.* ; Qayyum, A.* ; Mazher, M.* ; Puig, D.* ; Lin, S.C.* ; Juan, C.J.* ; Hu, T.* ; Boone, L.* ; Goubran, M.* ; Liu, Y.J.* ; Wegener, S.* ; Kofler, F. ; Ezhov, I.* ; Shit, S.* ; Hernandez Petzsche, M.R.* ; Müller, M.* ; Menze, B.* ; Kirschke, J.S.* ; Wiestler, B.*

DeepISLES: A clinically validated ischemic stroke segmentation model from the ISLES'22 challenge.

Nat. Commun. 16:7357 (2025)

Publ. Version/Full Text

Research data

DOI

PMC

	Open Access Gold

Abstract
Metrics
Extra information

Diffusion-weighted MRI is critical for diagnosing and managing ischemic stroke, but variability in images and disease presentation limits the generalizability of AI algorithms. We present DeepISLES, a robust ensemble algorithm developed from top submissions to the 2022 Ischemic Stroke Lesion Segmentation challenge we organized. By combining the strengths of best-performing methods from leading research groups, DeepISLES achieves superior accuracy in detecting and segmenting ischemic lesions, generalizing well across diverse axes. Validation on a large external dataset (N = 1685) confirms its robustness, outperforming previous state-of-the-art models by 7.4% in Dice score and 12.6% in F1 score. It also excels at extracting clinical biomarkers and correlates strongly with clinical stroke scores, closely matching expert performance. Neuroradiologists prefer DeepISLES' segmentations over manual annotations in a Turing-like test. Our work demonstrates DeepISLES' clinical relevance and highlights the value of biomedical challenges in developing real-world, generalizable AI tools. DeepISLES is freely available at https://github.com/ezequieldlrosa/DeepIsles .

Altmetric

Additional Metrics?

[➜Log in]

Edit extra informations Login

Publication type Article: Journal article

Document type Scientific Article

Keywords Lesion Segmentation; Computed-tomography; Benchmark; Association; Images; Core

ISSN (print) / ISBN 2041-1723

e-ISSN 2041-1723

Journal Nature Communications

Quellenangaben Volume: 16, Issue: 1, Article Number: 7357

Publisher Nature Publishing Group

Publishing Place London

Reviewing status Peer reviewed

Institute(s) Helmholtz Artifical Intelligence Cooperation Unit (HAICU)

Grants Korea Evaluation Institute of Industrial Technology (KEIT) - Korea government (MOTIE)
Artificial Intelligence Graduate School Program (POSTECH)
Institute of Information & communications Technology Planning & Evaluation (IITP) - Korea government (MSIT)
Basic Science Research Program through the National Research Foundation of Korea (NRF) - Ministry of Education
Swiss Heart Foundation
Swiss National Science Foundation
National Institutes of Health, National Institutes of Neurological Disorders and Stroke (NIH NINDS)
Flemish Government (AI Research Program)
Helmut Horten Foundation