MedSAM Segment Anything in Medical Images Universal medical image segmentation.

MedSAM, a deep learning-powered foundation model designed for the segmentation of a wide array of anatomical structures and lesions across diverse medical imaging modalities. MedSAM is trained on a meticulously assembled large-scale dataset comprised of over one million medical image-mask pairs. Its promptable configuration strikes an optimal balance between automation and customization, rendering MedSAM a versatile tool for universal medical image segmentation.

If you like such content please subscribe to the channel here:

[wasfianazzal]

That is really amazing thank you. Can you do the medSAM 2d and the medSAM3d?

[scotthwang]

To segment out the other lesions in the colab example, do you need to do anything else besides move the bounding box? I moved it to be around the lesion at the upper edge of the liver. It didn't work. Sometimes it would show some yellow pixels but they were outside of the bounding box.