Self-supervised learning for stroke lesion segmentation on CT: a new pretext task for neuroimaging

With the advancement of technology, the availability of medical data has increased, enabling the training of deep learning models for automatic analysis of medical images. However, annotating this data can be costly. To address this challenge, self-supervised learning has emerged, allowing models to be pre-trained on unannotated data using pretext tasks before fine-tuning them. In this study, we propose a novel pretext task specifically designed for neuroimaging applications and demonstrate its effectiveness in a use case involving stroke lesion segmentation on CT scans. The task leverages the stroke ASPECTS score by first training the model to segment the ten regions defined by this score using an initial dataset, followed by fine-tuning on the target data. Unlike conventional pretext tasks originally developed for natural images, our approach is specifically adapted to the unique challenges of neuroimaging, achieving improved segmentation performance and stability, showing that this pretext task, specifically tailored for stroke lesion segmentation is more efficient than generic tasks for self-supervised learning.Clinical relevance- Stroke lesion segmentation on CT is vital for diagnosis and treatment, as CT is commonly used despite its lower contrast compared to MRI. However, segmentation is challenging due to limited labeled data and CT's low contrast. Our self-supervised learning pretext task, tailored for neuroimaging and applied here to stroke lesions, improves accuracy and reliability, supporting its use in real-world clinical workflows.