Weakly Supervised Intracranial Hemorrhage Segmentation with YOLO and an Uncertainty Rectified Segment Anything Model

TL;DR

This paper introduces a weakly supervised method for intracranial hemorrhage segmentation using YOLO and an uncertainty-rectified Segment Anything Model, achieving high accuracy without extensive annotated datasets.

Contribution

The paper presents a novel weakly supervised segmentation approach combining YOLO and SAM with a point prompt generator, reducing reliance on detailed annotations.

Findings

Achieved 0.933 accuracy in ICH detection

Obtained 0.629 mean Dice score for segmentation

Outperformed existing weakly and supervised methods

Abstract

Intracranial hemorrhage (ICH) is a life-threatening condition that requires rapid and accurate diagnosis to improve treatment outcomes and patient survival rates. Recent advancements in supervised deep learning have greatly improved the analysis of medical images, but often rely on extensive datasets with high-quality annotations, which are costly, time-consuming, and require medical expertise to prepare. To mitigate the need for large amounts of expert-prepared segmentation data, we have developed a novel weakly supervised ICH segmentation method that utilizes the YOLO object detection model and an uncertainty-rectified Segment Anything Model (SAM). In addition, we have proposed a novel point prompt generator for this model to further improve segmentation results with YOLO-predicted bounding box prompts. Our approach achieved a high accuracy of 0.933 and an AUC of 0.796 in ICH detection, along with a mean Dice score of 0.629 for ICH segmentation, outperforming existing weakly supervised and popular supervised (UNet and Swin-UNETR) approaches. Overall, the proposed method provides a robust and accurate alternative to the more commonly used supervised techniques for ICH quantification without requiring refined segmentation ground truths during model training.