Medical Image Segmentation with SAM-generated Annotations
This work tackles the critical problem of data scarcity in medical image segmentation for researchers and practitioners, offering a method to train effective models without extensive manual annotation.
This paper addresses the scarcity of annotated medical image datasets by using the Segment Anything Model (SAM) to generate pseudo-labels for the Medical Segmentation Decathlon (MSD) CT tasks. A UNet model trained with these SAM-generated pseudo-labels, specifically using bounding box prompts, achieved performance comparable to a fully supervised model.
The field of medical image segmentation is hindered by the scarcity of large, publicly available annotated datasets. Not all datasets are made public for privacy reasons, and creating annotations for a large dataset is time-consuming and expensive, as it requires specialized expertise to accurately identify regions of interest (ROIs) within the images. To address these challenges, we evaluate the performance of the Segment Anything Model (SAM) as an annotation tool for medical data by using it to produce so-called "pseudo labels" on the Medical Segmentation Decathlon (MSD) computed tomography (CT) tasks. The pseudo labels are then used in place of ground truth labels to train a UNet model in a weakly-supervised manner. We experiment with different prompt types on SAM and find that the bounding box prompt is a simple yet effective method for generating pseudo labels. This method allows us to develop a weakly-supervised model that performs comparably to a fully supervised model.