ConDSeg, a general framework that handles medical image segmentation across multiple modalities through contrast-driven feature enhancement, has had its implementation published on GitHub. It is the official implementation of the AAAI 2025 paper "ConDSeg: A General Medical Image Segmentation Framework via Contrast-Driven Feature Enhancement" (arXiv:2412.08345, by Mengqi Lei, Haochen Wu, Xinhua Lv and Xin Wang). The GitHub repository is PyTorch-based and is free for research and educational use, while commercial use requires permission.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.