IMVS：具有测试时自适应的交互式医学体积分割——一种用于放射学数据集标注的新方法

中文摘要 AI 辅助

标注大型放射学数据集受到在3D体积中逐切片勾画结构所需手动工作的瓶颈限制。交互式方法减少了这一工作量，但交互效率仍然不高：逐切片方法（包括许多基础模型）忽略了切片间的连续性，而3D和基于视频的方法使用一个固定的传播器来传播提示，该传播器从不适应目标体积，因此在低对比度或病理结构上会漂移，必须重新提示。我们提出了IMVS，一个人在环路中的标注框架，它将三个组件组合成一个闭环，而不是一个新的分割原语：一个轻量级的2D切片掩膜适配器（SMA），从用户涂鸦在线微调；一个冻结的体积掩膜跟踪器（VMT），在相邻切片间传播校正后的掩膜；以及一个软教师-学生对齐，以限制遗忘。SMA与骨干网络无关（UNet++、DeepLabV3、TransUNet）。在8个公开的CT/MRI数据集上，IMVS在质量上与强大的交互式基线相当，同时大幅削减了标注工作量：比熟练的基于复制的手动工作流快14.4倍（比朴素手动快22.3倍），比逐切片方法快4.6倍，比3D交互式方法快1.9倍。MedSAM2和ScribblePrompt在轮廓清晰的器官上保持竞争力或更强；IMVS的优势在具有挑战性的目标和交互效率上最大。源代码和演示视频：此https URL。

英文摘要

Annotating large radiology datasets is bottlenecked by the manual effort of delineating structures slice-by-slice in 3D volumes. Interactive methods reduce this effort but stay interaction-inefficient: slice-wise methods (including many foundation models) ignore inter-slice continuity, while 3D and video-based methods propagate a prompt with a \emph{fixed} propagator that never adapts to the target volume, so it drifts on low-contrast or pathological structures and must be re-prompted. We present IMVS, a human-in-the-loop annotation framework that composes three components into a closed loop rather than a new segmentation primitive: a lightweight 2D Slice Mask Adapter (SMA) fine-tuned online from user scribbles, a frozen Volume Mask Tracker (VMT) that propagates corrected masks across adjacent slices, and a soft teacher--student alignment that limits forgetting. The SMA is backbone-agnostic (UNet++, DeepLabV3, TransUNet). Across 8 public CT/MRI datasets, IMVS matches strong interactive baselines in quality while sharply cutting annotation effort: $14.4\times$ faster than a proficient copy-based manual workflow ($22.3\times$ over naive manual), $4.6\times$ over slice-wise and $1.9\times$ over 3D interactive methods. MedSAM2 and ScribblePrompt stay competitive or stronger on well-delineated organs; IMVS's advantage is largest on challenging targets and on interaction efficiency. Source code and Demo Video: https://github.com/AbhilakshSinghReen/imvs.

发表机构

• California State University（加州州立大学）

机构由 AI 辅助整理，请以论文原文为准。