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

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

Nature Communications 2025;16.

DOI PMID

Abstract

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.