跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.24443 · v1

NativeSeg: Native Vision Language Segmentation of 3D Computed Tomography via Spatial Visual Tokens and Verified Local Zoom

首次提交 2026-11-18 21:56
版本更新 2026-11-18 21:56
雷达观测 2026-11-19 15:04
arXiv ↗PDF ↗

摘要

Text prompted 3D computed tomography (CT) segmentation requires both full slice context and fine boundary precision across volumes where over 80%80\% of organ prompted slices lack the queried target. Existing medical vision language models (VLMs) are largely non native segmenters: they delegate pixel delineation outside the VLM by compressing reasoning into a 1D [SEG] vector for an external Segment Anything Model (SAM) decoder, quantizing masks into lossy discrete codebooks, or issuing box prompts to stateless external SAM tools without empty slice screening or spatial state memory. We introduce NativeSeg, a native vision language segmentation framework on Low Rank Adaptation (LoRA) adapted Qwen3.8-27B that performs dense mask decoding, volumetric triage, spatial error self diagnosis, and multiround local zoom directly over the VLM's 2D spatial visual tokens without external SAM decoders. NativeSeg decodes confidence maps from upper layer 2D spatial tokens fused with a five slice U-Net pathway, halts at zero zooms on >91%>91\% of standalone evaluations via a native presence gate (<pres>), localizes uncertain boundaries via a 20 cell multiscale error gate (<err>), and accepts zoomed updates only when predicted error decreases. Trained solely on adult CT, NativeSeg improves Round 00 DSC by +19.81+19.81 and +7.04+7.04 points over discrete codebook and 1D [SEG] readouts on the identical backbone, reaches 86.81%86.81\% adult and 87.04%87.04\% zero shot pediatric DSC, and safely refines 2D nnU-Net (89.52%89.52\% adult; 86.86%86.86\% pediatric), 3D SegVol (86.81%86.81\%), and 3D VoxTell (89.85%89.85\%).

作者备注:13 pages, 5 figures, 4 tables. Code: https://github.com/step-out/NativeSeg ; Weights: https://huggingface.co/ChengqianMa/NativeSeg

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-18 21:56 · 最新观测版本

NativeSeg: Native Vision Language Segmentation of 3D Computed Tomography via Spatial Visual Tokens and Verified Local Zoom

Text prompted 3D computed tomography (CT) segmentation requires both full slice context and fine boundary precision across volumes where over 80%80\% of organ prompted slices lack the queried target. Existing medical vision language models (VLMs) are largely non native segmenters: they delegate pixel delineation outside the VLM by compressing reasoning into a 1D [SEG] vector for an external Segment Anything Model (SAM) decoder, quantizing masks into lossy discrete codebooks, or issuing box prompts to stateless external SAM tools without empty slice screening or spatial state memory. We introduce NativeSeg, a native vision language segmentation framework on Low Rank Adaptation (LoRA) adapted Qwen3.8-27B that performs dense mask decoding, volumetric triage, spatial error self diagnosis, and multiround local zoom directly over the VLM's 2D spatial visual tokens without external SAM decoders. NativeSeg decodes confidence maps from upper layer 2D spatial tokens fused with a five slice U-Net pathway, halts at zero zooms on >91%>91\% of standalone evaluations via a native presence gate (<pres>), localizes uncertain boundaries via a 20 cell multiscale error gate (<err>), and accepts zoomed updates only when predicted error decreases. Trained solely on adult CT, NativeSeg improves Round 00 DSC by +19.81+19.81 and +7.04+7.04 points over discrete codebook and 1D [SEG] readouts on the identical backbone, reaches 86.81%86.81\% adult and 87.04%87.04\% zero shot pediatric DSC, and safely refines 2D nnU-Net (89.52%89.52\% adult; 86.86%86.86\% pediatric), 3D SegVol (86.81%86.81\%), and 3D VoxTell (89.85%89.85\%).

查看此版本解读 →查看此版本原文 ↗