[论文] Retrieval-Augmented Correction for Generalist Medical Image Segmentati...

研究领域: CV 作者: Vincenzo Marcianò, Xiaoming Zhang, Michela Antonelli, Sebastien Ourselin, Maria A Zuluaga 发布时间: 2026-11-17 arXiv: 2611.23189

目录
  1. 论文概要
  2. 中文摘要
  3. 原文摘要

论文概要

研究领域: CV 作者: Vincenzo Marcianò, Xiaoming Zhang, Michela Antonelli, Sebastien Ourselin, Maria A Zuluaga 发布时间: 2026-11-17 arXiv: 2611.23189

中文摘要

自动化分割是定量图像临床工作流常规首步,预测掩码由人工审查修正。残差结构误差自动校正目前逐解剖部位处理,可校正模型数与分割目标数成正比。我们提出 GRACE——检索增强修正器,从共享验证案例知识库抽取上下文编辑输入掩码。修正器在多器官语料训练一次,涵盖紧凑器官、腔体、分支血管和肿瘤病变。冻结多模态编码器上的轻量形状感知投影头将嵌入相似性映射到掩码形状一致性,使知识库返回可用作形状先验的案例。18 个公共数据集(CT/MRI/超声)上:弱层级输入 DSC 0.386,GRACE 最高增 +0.35;强分割器输入 DSC 0.932,平均变化微小。

原文摘要

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-ana...


*自动采集于 2026-11-19*

#论文 #arXiv #CV #小凯

暂无表态

想参与讨论或点赞?登录后使用完整功能

讨论回复(0)

暂无回复,登录后可参与讨论

本文标签

合作

智谱 GLM-5 已上线

在智谱开放平台 BigModel.cn 打造 AI 应用。新一代旗舰模型 GLM-5 在推理、代码、智能体综合能力达到开源模型 SOTA。

领取 2000万 Tokens