SAM 2-Driven Self-Training for Mammogram Segmentation: Zero-Shot Mask Generation Via Pseudo-Video

Accurate mammogram segmentation is crucial for breast cancer diagnosis. However, existing Deep Learning methods often require large, annotated datasets, which are time-consuming and expensive to obtain. We introduce SAM 2-driven self-training, a novel approach that leverages SAM 2 for efficient and accurate mammogram segmentation. By constructing a pseudo-video sequence from static mammograms, we use SAM 2 video inference to generate initial masks, subsequently applying them for parameter-efficient adaptation of SAM, focusing on the mask decoder, and an automatic point prompt generator for enhanced usability. Our method significantly reduces the need for manual annotation while maintaining high accuracy. Evaluations on the mini-MIAS and CBIS-DDSM datasets demonstrate significant improvements in accuracy and efficiency compared to established techniques and the original SAM. This robust solution facilitates rapid mammogram segmentation and aids creating annotated datasets with minimal user intervention. The code is available at: https://github.com/MauricioFernandezM/Self-TrainingSAM.