Automated detection of new cerebral infarctions and prognostic implications using deep learning on serial MRI.
Authors
Affiliations (12)
Affiliations (12)
- Department of Electronics Engineering, Incheon National University, Incheon, South Korea.
- Department of Neurology, Inje University Haeundae Paik Hospital, Busan, South Korea.
- Department of Neurology, Chung-Ang University Gwangmyeong Hospital, Gwangmyeong, South Korea.
- Department of Neurology, Uijeongbu Eulji Medical Center, Eulji University School of Medicine, Uijeongbu, South Korea.
- Department of Neurology, Ulsan Hospital, Ulsan, South Korea.
- Department of Neurology, Busan Paik Hospital, Inje University College of Medicine, Busan, South Korea.
- Department of Neurology, Dong-A University College of Medicine, Busan, South Korea.
- Department of Neurology and Stroke Center, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, South Korea.
- Department of Neurology, Korea University Ansan Hospital, Ansan, South Korea.
- Department of Electrical and Computer Engineering, Sungkyunkwan University, Suwon, South Korea.
- Center for Neuroscience Imaging Research, Institute for Basic Science, Suwon, South Korea.
- Department of Neurology, Hanyang University Guri Hospital, College of Medicine, Hanyang University, Guri, South Korea. [email protected].
Abstract
We developed and externally validated a deep learning model to automatically detect new ischemic lesions on serial FLAIR MRI scans in patients with stroke. Manual interpretation of follow-up imaging is labor-intensive and variable, and silent brain infarctions (SBIs) are frequently missed despite their prognostic importance. Using 25,451 paired slices from 1055 patients across two hospitals, we trained a convolutional neural network with supervised contrastive learning to classify new lesion occurrence. The model achieved an area under the receiver operating characteristic curve of 0.89 in both internal and external validation cohorts. To evaluate clinical relevance, we further analyzed an independent asymptomatic cohort of 307 patients with a median follow-up of two years. Patients classified as SBI-positive by the model showed a significantly higher risk of subsequent symptomatic stroke than those without SBI. In multivariable Cox regression adjusted for age and major vascular risk factors, model-positive patients had a 3.8-fold increased risk of stroke recurrence. These findings indicate that AI can identify clinically meaningful SBIs that are under-recognized in routine practice and independently associated with stroke recurrence. Automated lesion detection may provide a reproducible imaging biomarker for risk stratification, supporting standardized interpretation of follow-up MRI and informing secondary stroke prevention strategies.