VoxTell: Free-Text Promptable Universal 3D Medical Image Segmentation
Rokuss, Maximilian, Langenberg, Moritz, Kirchhoff, Yannick, Isensee, Fabian, Hamm, Benjamin, Ulrich, Constantin, Regnery, Sebastian, Bauer, Lukas 等 11 位作者
原文摘要
We introduce VoxTell, a vision-language model for text-prompted volumetric medical image segmentation. It maps free-form descriptions, from single words to full clinical sentences, to 3D masks. Trained on 62K+ CT, MRI, and PET volumes spanning 1K+ anatomical and pathological classes, VoxTell uses multi-stage vision-language fusion across decoder layers to align textual and visual features at multiple scales. It achieves state-of-the-art zero-shot performance across modalities on unseen datasets, excelling on familiar concepts while generalizing to related unseen classes. Extensive experiments further demonstrate strong cross-modality transfer, robustness to linguistic variations and clinical language, as well as accurate instance-specific segmentation from real-world text. Code is available at: https://github.com/MIC-DKFZ/VoxTell
cs.CV · cs.CL
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表