跳到正文
arXiv cs.AI· Vincenzo Marcian\`o, Xiaoming Zhang, Michela Antonelli, Sebastien Ourselin, Maria A Zuluaga·· 23 小时前AI 评分31

GRACE:检索增强的通用医学图像分割校正模型

Retrieval-Augmented Correction for Generalist Medical Image Segmentation

AI 导读

GRACE 是一个检索增强的掩码精修器,基于已验证病例的共享知识库对输入分割掩码进行校正,只需在多器官语料上训练一次,无需为每个解剖结构单独训练校正模型。在 18 个公开数据集(CT、MRI、超声)上,弱分割器输入 DSC 为 0.386 时 GRACE 最多提升 +0.35 DSC;强分割器输入 DSC 0.932 时平均变化较小。

正文 · 原文

View PDF HTML (experimental)

Abstract:Automated segmentation is routinely used as the first step in quantitative image-based clinical workflows, where predicted masks are subsequently reviewed and corrected by human operators. Automated correction of the residual structural errors is currently addressed one anatomy at a time, so the number of trained correctors scales with the number of segmentation targets. We present GRACE, a retrieval-augmented refiner that edits an input mask under context drawn from a shared knowledge base of verified prior cases. The refiner is trained once on a multi-organ corpus spanning compact organs, cavities, branching vessels, and tumour lesions. In the held-out dataset-transfer evaluation, three held-out datasets query a fixed knowledge base built from training data only. A separate leave-one-anatomy-out experiment tests parameter-free index extension: verified cases of an unseen solid organ enter the knowledge base, and the refiner stays frozen. A light shape-aware projection head on a frozen multimodal encoder maps embedding similarity to the shape agreement of the masks, so the knowledge base returns cases that the refiner can use as a shape prior. We evaluate GRACE on 18 public datasets spanning CT, MRI and ultrasound, using nine refinement configurations and seven upstream segmentors that span weak, mid, and strong operating regimes. We report each change with the DSC of its input mask. On the weak tier, the input DSC is 0.386 and GRACE adds up to +0.35 DSC. On a strong segmentor, the input DSC is 0.932 and the mean change is small. Transfer to an imaging modality that is absent from training and from the index is partial and depends on the anatomy, and remains an open research direction. Our results suggest retrieval-conditioned refinement is a practical alternative to anatomy-specific correction models. Code: this https URL
Comments: Accepted in Transactions on Machine Learning Research (10/2026). Reviewed on OpenReview: this https URL
Subjects: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
Cite as: arXiv:2611.23189 [cs.CV]
  (or arXiv:2611.23189v1 [cs.CV] for this version)
  https://doi.org/10.48550/arXiv.2611.23189

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Vincenzo Marcianò [view email]
[v1] Tue, 17 Nov 2026 18:33:42 UTC (1,940 KB)

来源:arXiv cs.AI · arxiv.org