A Foundation Model for General Moving Object Segmentation in Medical Images

TL;DR

This paper introduces iMOS, a foundation model for moving object segmentation in medical images, which achieves effective segmentation with minimal annotations, potentially accelerating medical image annotation and model development.

Contribution

The paper presents the first foundation model for medical moving object segmentation, enabling accurate segmentation with limited annotations and improving annotation efficiency.

Findings

iMOS achieves satisfactory segmentation with minimal annotations.

The model effectively tracks moving objects in medical image sequences.

Experiments validate the model's robustness across multi-modal datasets.

Abstract

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.