← 研踪 PaperTrailCVF · CVPR 2026:cvf:2dfbec1c08f09a0c10b3076b9f8048ed · 记录 #1
VoxTell: Free-Text Promptable Universal 3D Medical Image Segmentation
Rokuss, MaximilianLangenberg, MoritzKirchhoff, YannickIsensee, FabianHamm, BenjaminUlrich, ConstantinRegnery, SebastianBauer, LukasKatsigiannopulos, EfthimiosNorajitra, TobiasMaier-Hein, Klaus 来源日期（仅到年份） 2026
来源记录日期 2026
雷达观测 2026-11-01 23:20
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
论文发现出处
这些页面提供论文线索，不代表同行评审或质量认证。
观测到的版本
平台记录号代表本站观测到的元数据变化，不是作者修订号。来源日期仅到月份或年份时，按该月或该年首日存档。
记录 #1 · 2026 · 最新观测版本
VoxTell: Free-Text Promptable Universal 3D Medical Image Segmentation
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
查看此版本解读 →查看此版本原文 ↗