将高性能脑卒中病灶分割模型转化为轻量级临床部署工具
Stroke Lesion Segmentation in Clinical Workflows: A Modular, Lightweight, and Deployment-Ready Tool
- 模块化设计分离预处理、推理与后处理流程
- 量化后模型体积减半，保持原有分割精度
- 支持图形界面和命令行，可直接用于临床工作流
深度学习框架如nnU-Net在脑病变分割上表现优异，但因依赖复杂且架构单一，难以临床部署。我们提出StrokeSeg，一个模块化、轻量化的框架，可将研究级脑卒中病灶分割模型转化为可部署应用。预处理基于Anima工具箱，输出符合BIDS标准；推理采用ONNX Runtime与Float16量化，模型大小减少约50%。StrokeSeg提供图形界面和命令行接口，以Python脚本及独立Windows可执行文件形式分发。在300例亚急性和慢性期卒中患者数据集上，分割性能与原PyTorch管道相当（Dice差异<10⁻³），证明高性能研究模型可成功转化为便携、临床可用的工具。
原文摘要 · Abstract (English)
Deep learning frameworks such as nnU-Net achieve state-of-the-art performance in brain lesion segmentation but remain difficult to deploy clinically due to heavy dependencies and monolithic design. We introduce \textit{StrokeSeg}, a modular and lightweight framework that translates research-grade stroke lesion segmentation models into deployable applications. Preprocessing, inference, and postprocessing are decoupled: preprocessing relies on the Anima toolbox with BIDS-compliant outputs, and inference uses ONNX Runtime with \texttt{Float16} quantisation, reducing model size by about 50\%. \textit{StrokeSeg} provides both graphical and command-line interfaces and is distributed as Python scripts and as a standalone Windows executable. On a held-out set of 300 sub-acute and chronic stroke subjects, segmentation performance was equivalent to the original PyTorch pipeline (Dice difference $<10^{-3}$), demonstrating that high-performing research pipelines can be transformed into portable, clinically usable tools.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。