Knowledge-prompted intracranial hemorrhage segmentation on brain computed tomography

Intracranial hemorrhage poses a critical threat to patient survival, necessitating rapid intervention to prevent devastating outcomes. Traditional segmentation methods in computer-aided diagnosis face significant challenges due to the inherent variability of hemorrhage regions. Recent advancements in segmentation, powered by foundation models and innovative utilization of prior knowledge, have shown promise; however, existing methods predominantly rely on point or bounding box prompts, which often fail to account for the intricate variability inherent in hemorrhage presentations. To tackle this challenge, we propose a knowledge-prompted segment anything model (KP-SAM) that integrates the specialized knowledge of neurologists into the segmentation process. By collaborating with expert neurologist, our method captures the nuanced characteristics of hemorrhage regions, effectively augmenting the limitations of using only points or bounding boxes. Furthermore, we developed a diagnostic support system for intracranial hemorrhage at the Affiliated Hospital of Qingdao University. Leveraging concise semantic information provided by radiologists, our system facilitates rapid and accurate diagnostic support for clinicians. Experimental results demonstrate that our method achieves state-of-the-art performance in real-world segmentation tasks and significantly enhances diagnostic accuracy for neurologists. This advancement not only enhances diagnostic precision but also highlights the transformative potential of integrating diverse data modalities in medical applications.