Deep learning-based detection and segmentation of diffusion abnormalities in acute ischemic stroke

Liu, C.-F. et al. (2021) Deep learning-based detection and segmentation of diffusion abnormalities in acute ischemic stroke. Communications Medicine, 1, 61. (doi: 10.1038/s43856-021-00062-8)

Abstract

Background: Accessible tools to efficiently detect and segment diffusion abnormalities in acute strokes are highly anticipated by the clinical and research communities. Methods: We developed a tool with deep learning networks trained and tested on a large dataset of 2,348 clinical diffusion weighted MRIs of patients with acute and sub-acute ischemic strokes, and further tested for generalization on 280 MRIs of an external dataset (STIR). Results: Our proposed model outperforms generic networks and DeepMedic, particularly in small lesions, with lower false positive rate, balanced precision and sensitivity, and robustness to data perturbs (e.g., artefacts, low resolution, technical heterogeneity). The agreement with human delineation rivals the inter-evaluator agreement; the automated lesion quantification of volume and contrast has virtually total agreement with human quantification. Conclusion: Our tool is fast, public, accessible to non-experts, with minimal computational requirements, to detect and segment lesions via a single command line. Therefore, it fulfills the conditions to perform large scale, reliable and reproducible clinical and translational research.

• Item Type: Articles
• Additional Information: This research was supported in part by the National Institute of Deaf and Communication Disorders, NIDCD, through R01 DC05375, R01 DC015466, P50 DC014664 (A.H., A.V.F.), the National Institute of Biomedical Imaging and Bioengineering, NIBIB, through P41 EB031771 (M.I.M., A.V.F.), and the Department of Neurology, University of Texas at Austin, the National Institute of Neurological Disorders and Stroke, NINDS, National Institutes of Health, NIH (STIR/Vista Imaging Investigators).
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Lees, Professor Kennedy
• Authors: Liu, C.-F., Hsu, J., Xu, X., Ramachandran, S., Wang, V., Miller, M. I., Hillis, A. E., Faria, A. V., Wintermark, M., Warach, S. J., Albers, G. W., Davis, S. M., Grotta, J. C., Hacke, W., Kang, D.-W., Kidwell, C., Koroshetz, W. J., Lees, K. R., Lev, M. H., Liebeskind, D. S., Sorensen, A. G., Thijs, V. N., Thomalla, G., Wardlaw, J. M., and Luby, M.
• College/School: College of Medical Veterinary and Life Sciences > School of Medicine, Dentistry & Nursing
• Journal Name: Communications Medicine
• Publisher: Nature Research
• ISSN: 2730-664X
• ISSN (Online): 2730-664X
• Copyright Holders: Copyright © 2021 The Authors
• First Published: First published in Communications Medicine 1: 61
• Publisher Policy: Reproduced under a Creative Commons License