Lung Segmentation

In this paper, we exploit ways to fine-tune SAM and adapt it for lung segmentation in chest X-ray images provided by the Shenzhen and Montgomery datasets. In this study, various strategies to fine-tuning SAM were investigated, including the use of different prompts, such as bounding boxes, points selected from the average image, and a combination of both.

Do you want to know more about fine-tuning SAM for lung segmentation in chest X-ray images? Check our paper “Exploiting the Segment Anything Model (SAM) for Lung Segmentation in Chest X-ray Images”, just accepted for publication in the Iberoamerican Congress on Pattern Recognition.