Semantic Segmentation Refiner for Ultrasound Applications with Zero-Shot Foundation Models
This work addresses the problem of segmentation performance degradation for medical imaging applications, particularly in ultrasound, where labeled data is scarce, though it appears incremental as it builds on existing foundation models.
The paper tackles the challenge of medical image segmentation in low-data regimes by proposing a prompt-less method that uses coarse masks and a zero-shot foundation model to improve performance, demonstrating gains on a small-scale musculoskeletal ultrasound dataset with larger improvements as training data decreases.
Despite the remarkable success of deep learning in medical imaging analysis, medical image segmentation remains challenging due to the scarcity of high-quality labeled images for supervision. Further, the significant domain gap between natural and medical images in general and ultrasound images in particular hinders fine-tuning models trained on natural images to the task at hand. In this work, we address the performance degradation of segmentation models in low-data regimes and propose a prompt-less segmentation method harnessing the ability of segmentation foundation models to segment abstract shapes. We do that via our novel prompt point generation algorithm which uses coarse semantic segmentation masks as input and a zero-shot prompt-able foundation model as an optimization target. We demonstrate our method on a segmentation findings task (pathologic anomalies) in ultrasound images. Our method's advantages are brought to light in varying degrees of low-data regime experiments on a small-scale musculoskeletal ultrasound images dataset, yielding a larger performance gain as the training set size decreases.