Deep Learning-Based Automatic Classification of Ischemic Stroke Subtype Using Diffusion-Weighted Images

Authors

Wi-Sun Ryu
Dawid Schellingerhout
Hoyoun Lee
Keon-Joo Lee
Chi Kyung Kim
Beom Joon Kim
Jong-Won Chung
Jae-Sung Lim
Joon-Tae Kim
Dae-Hyun Kim
Jae-Kwan Cha
Leonard Sunwoo
Dongmin Kim
Sang-Il Suh
Oh Young Bang
Hee-Joon Bae
Dong-Eog Kim

Publication Date

5-1-2024

Journal

Journal of Stroke

DOI

10.5853/jos.2024.00535

PMID

38836277

PMCID

PMC11164582

PubMedCentral® Posted Date

5-30-2024

PubMedCentral® Full Text Version

Post-print

Abstract

Background and purpose: Accurate classification of ischemic stroke subtype is important for effective secondary prevention of stroke. We used diffusion-weighted image (DWI) and atrial fibrillation (AF) data to train a deep learning algorithm to classify stroke subtype.

Methods: Model development was done in 2,988 patients with ischemic stroke from three centers by using U-net for infarct segmentation and EfficientNetV2 for subtype classification. Experienced neurologists (n=5) determined subtypes for external test datasets, while establishing a consensus for clinical trial datasets. Automatically segmented infarcts were fed into the model (DWI-only algorithm). Subsequently, another model was trained, with AF included as a categorical variable (DWI+AF algorithm). These models were tested: (1) internally against the opinion of the labeling experts, (2) against fresh external DWI data, and (3) against clinical trial dataset.

Results: In the training-and-validation datasets, the mean (±standard deviation) age was 68.0±12.5 (61.1% male). In internal testing, compared with the experts, the DWI-only and the DWI+AF algorithms respectively achieved moderate (65.3%) and near-strong (79.1%) agreement. In external testing, both algorithms again showed good agreements (59.3%-60.7% and 73.7%-74.0%, respectively). In the clinical trial dataset, compared with the expert consensus, percentage agreements and Cohen's kappa were respectively 58.1% and 0.34 for the DWI-only vs. 72.9% and 0.57 for the DWI+AF algorithms. The corresponding values between experts were comparable (76.0% and 0.61) to the DWI+AF algorithm.

Conclusion: Our model trained on a large dataset of DWI (both with or without AF information) was able to classify ischemic stroke subtypes comparable to a consensus of stroke experts.

Keywords

Deep learning, Artificial intelligence, Diffusion magnetic resonance imaging, Atrial fibrillation, Ischemic stroke

Published Open-Access

yes

Recommended Citation

Ryu, Wi-Sun; Schellingerhout, Dawid; Lee, Hoyoun; et al., "Deep Learning-Based Automatic Classification of Ischemic Stroke Subtype Using Diffusion-Weighted Images" (2024). Faculty, Staff and Student Publications. 4985.
https://digitalcommons.library.tmc.edu/uthgsbs_docs/4985