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