SAMMed-VR: Integrated Segment Anything Model in Virtual Reality for Supervised Brain Tumour Segmentation

Brain tumours differ significantly in shape, size, location, and contrast imperfections. Reliable segmentation is crucial for accurate identification and effective treatment. Recent advances in AI-based 3D medical image segmentation, such as SAM-Med3D, have improved automation; however, expert supervision remains vital for brain imaging. We present a virtual reality probe that integrates an expert-in-the-loop approach with SAM-Med3D, allowing users to iteratively enhance brain tumour segmentation by selecting points for AI refinement.

Recommended citation: Pooryousef, V., Peiris, H., Liang, H., Li, A., Chen, Z., Dwyer, T., & Liu, J., (2025 Oct) SAMMed-VR: Integrated Segment Anything Model in Virtual Reality for Supervised Brain Tumour Segmentation. IEEE VIS Poster
Download Paper