A Foundation Model for General Moving Object Segmentation in Medical Images
This work addresses the annotation bottleneck for medical experts, potentially accelerating annotation speed and boosting medical foundation models, though it appears incremental as it adapts an existing task from natural images to the medical domain.
The paper tackles the problem of cumbersome and time-consuming annotation for medical image segmentation by proposing iMOS, the first foundation model for Moving Object Segmentation in medical images, which achieves satisfactory tracking and segmentation performance with minimal annotations.
Medical image segmentation aims to delineate the anatomical or pathological structures of interest, playing a crucial role in clinical diagnosis. A substantial amount of high-quality annotated data is crucial for constructing high-precision deep segmentation models. However, medical annotation is highly cumbersome and time-consuming, especially for medical videos or 3D volumes, due to the huge labeling space and poor inter-frame consistency. Recently, a fundamental task named Moving Object Segmentation (MOS) has made significant advancements in natural images. Its objective is to delineate moving objects from the background within image sequences, requiring only minimal annotations. In this paper, we propose the first foundation model, named iMOS, for MOS in medical images. Extensive experiments on a large multi-modal medical dataset validate the effectiveness of the proposed iMOS. Specifically, with the annotation of only a small number of images in the sequence, iMOS can achieve satisfactory tracking and segmentation performance of moving objects throughout the entire sequence in bi-directions. We hope that the proposed iMOS can help accelerate the annotation speed of experts, and boost the development of medical foundation models.