Deep learning-based detection and segmentation of diffusion abnormalities in acute ischemic stroke
Authors:
- Victor WangVWVictor Wang
- Andreia V. FariaAFAndreia V. Faria
- The STIR and VISTA Imaging investigatorsTIThe STIR and VISTA Imaging investigators
- Max WintermarkMWMax Wintermark
- Steven J. WarachSWSteven J. Warach
- Gregory W. AlbersGAGregory W. Albers
Top Cited Papers
Open Access
- 16 December 2021
- journal article
- research article
- Published by Springer Nature in Communications Medicine
- Vol. 1 (1) , 1-18
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.Keywords
All Related Versions
Funding Information
- U.S. Department of Health & Human Services | NIH | National Institute of Biomedical Imaging and Bioengineering (P41 EB031771)
- U.S. Department of Health & Human Services | NIH | National Institute on Deafness and Other Communication Disorders (R01 DC05375, R01 DC015466, P50 DC014664)
- U.S. Department of Health & Human Services | NIH | National Institute on Deafness and Other Communication Disorders
- U.S. Department of Health & Human Services | NIH | National Institute on Deafness and Other Communication Disorders
This publication has 43 references indexed in Scilit:
- Does stroke location predict walk speed response to gait rehabilitation?Human Brain Mapping, 2015
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Automated lesion detection on MRI scans using combined unsupervised and supervised methodsBMC Medical Imaging, 2015
- Automatic tumor lesion detection and segmentation using modified winnow algorithm2015
- Solitaire™ with the Intention for Thrombectomy as Primary Endovascular Treatment for Acute Ischemic Stroke (SWIFT PRIME) Trial: Protocol for a Randomized, Controlled, Multicenter Study Comparing the Solitaire Revascularization Device with IV tPA with IV tPA Alone in Acute Ischemic StrokeInternational Journal of Stroke, 2015
- Validation of digit-length ratio (2D:4D) assessments on the basis of DXA-derived hand scansBMC Medical Imaging, 2015
- scikit-image: image processing in PythonPeerJ, 2014
- Dipy, a library for the analysis of diffusion MRI dataFrontiers in Neuroinformatics, 2014
- Lesion Load of the Corticospinal Tract Predicts Motor Impairment in Chronic StrokeStroke, 2010
- Time to treatment with intravenous alteplase and outcome in stroke: an updated pooled analysis of ECASS, ATLANTIS, NINDS, and EPITHET trialsThe Lancet, 2010