Journal Article

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

Miller, Michael I., Liu, Chin-Fu, Hsu, Johnny, Hillis, Argye E., Faria, Andreia V., Xu, Xin, Wang, Victor, Ramachandran, Sandhya

2021

Overview

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. Plain language summary Determining the volume and location of lesions caused by acute ischemic strokes - in which blood flow is restricted to part of the brain - is crucial to guide treatment and patient prognosis. However, this process is time-consuming and labor-intensive for clinicians. Here, using brain imaging datasets from patients with ischemic strokes, we create an artificial intelligence-based tool to quickly and accurately determine the volume and location of stroke lesions. Our tool outperforms some similar existing approaches, it is fast, publicly available, accessible to non-experts, and it runs on normal computers with minimal computational requirements. As such, it may be useful both for clinicians treating patients and researchers studying ischemic stroke. Liu et al. develop a deep learning-based tool to detect and segment diffusion abnormalities seen on magnetic resonance imaging (MRI) in acute ischemic stroke. The tool is tested in two clinical MRI datasets and outperforms existing algorithms in the detection of small lesions, potentially allowing clinicians and clinical researchers to more quickly and accurately diagnose and assess ischemic strokes.

• Publisher: Nature Publishing Group UK,Springer Nature B.V,Nature Portfolio
• Subject: 692/699/375/534 / 692/700/1421/65 / Brain research / Datasets / Deep learning / Demographics / Medicine / Medicine & Public Health / Neural networks / Population / Stroke