BACKGROUND

Clinical decisions for stroke treatments, such as thrombolytic drugs for ischemic strokes or anticoagulants for hemorrhagic strokes, rely on accurate diagnosis and severity assessment. Our study uses diffusion-weighted magnetic resonance imaging and Convolutional Neural Networks (CNNs) to differentiate healthy and stroke samples, classify stroke types, and predict severity, aiding in decision-making for stroke management.

METHODS

We evaluated 143 patients: 85 with ischemic stroke and 58 with hemorrhagic stroke. For stroke diagnosis, we compared multimodal (apparent diffusion coefficient and diffusion-weighted imaging [DWI]) and single-modal (using separate images) preprocessing techniques. Our study introduced two models, Added CNN Layer-ResNet-50 (ACL-ResNet-50) and Added CNN Layer-MobileNetV1 (ACL-MobileNetV1), based on transfer learning (MobileNetV1 and ResNet-50), enhancing performance through reinforced layers. We compared our proposed models with a scenario in which only the final layer was replaced in ResNet-50 and MobileNetV1. Furthermore, we predicted National Institutes of Health Stroke Scale (NIHSS) scores in three ranges based on DWI images to gauge stroke severity. Evaluation criteria for the models included accuracy, sensitivity, specificity, and area under the curve (AUC).

RESULTS

In stroke classification (normal, ischemic, and hemorrhagic), ACL-MobileNetV1 outperformed other models, achieving 98% accuracy, 99% sensitivity, 98% specificity, and 99% AUC. For assessing ischemic stroke severity using NIHSS ranges, ACL-ResNet-50 showed the optimal performance with an accuracy of 0.92, sensitivity of 0.84, specificity of 0.92, and AUC of 0.95.

CONCLUSION

Our study's proposed method effectively classified stroke type and severity based on multimodal MR images, potentially as a practical decision support tool for stroke treatments.