A vendor-agnostic, PACS integrated, and DICOM-compatible software-server pipeline for testing segmentation algorithms within the clinical radiology workflow.
A vendor-agnostic, PACS integrated, and DICOM-compatible software-server pipeline for testing segmentation algorithms within the clinical radiology workflow.
复制标题
DOI：
10.3389/fmed.2023.1241570
复制
发表时间：
2023
影响因子：
3.9
通讯作者：
Dreizin, David
中科院分区：
文献类型：
--
作者：
Zhang, Lei;Labelle, Wayne;Unberath, Mathias;Chen, Haomin;Hu, Jiazhen;Li, Guang;Dreizin, David
关键词：
需要可重复的方法来使用于医学图像分析的 AI/ML 更接近床边。希望在新研究中实时影子测试横截面医学成像分割算法的研究人员将受益于将 PACS 与本地图像处理集成的简单工具，从而允许在放射学工作站上可视化兼容 DICOM 的分割结果和体积数据。在这项工作中，我们开发并发布了一个简单的容器化且易于部署的管道，用于临床工作流程中分割算法的影子测试。我们的端到端自动化管道有两个主要组件 - 1. 路由器/侦听器和匿名器以及 OHIF Web 查看器，由部署在我们安全医院内联网的虚拟基础设施中的 DCM4CHEE DICOM 查询/检索存档提供支持，以及 2. 用于 DICOM/NIfTI 转换步骤和图像处理的本地单 GPU 工作站主机。使用 DICOM SEG 和结构化报告 (SR) 元素在 OHIF 中可视化 DICOM 图像及其分割掩模和相关的体积测量（以 mL 为单位）。由于 nnU-net 已成为一种广泛使用的开箱即用方法，用于训练具有最先进性能的分割模型，因此我们的管道的可行性通过记录创伤性盆腔血肿 nnU-net 模型的时钟时间来证明。从用户发送 PACS 到完成传输到 DCM4CHEE 查询/检索存档的平均总时钟时间为 5 分钟 32 秒（± SD 为 1 分钟 26 秒）。这与全身 CT 检查的报告周转时间相比是有利的，全身 CT 检查的报告周转时间通常超过 30 分钟，并且说明了在报告签署之前预计会获得定量结果的临床环境中的可行性。推理时间占总时钟时间的大部分，范围从 2 分钟 41 秒到 8 分钟 27 秒。所有其他虚拟和本地主机步骤的总时间范围从最少 34 秒到最多 48 秒。该软件与现有的 PACS 无缝协作，可用于在放射学工作流程中部署 DL 模型，以便对新扫描的患者进行前瞻性测试。配置完成后，即可使用单个 shell 脚本通过一个命令执行管道。该代码通过“https://github.com/vastc/”上的开源许可证公开提供，并包含一个自述文件，提供主机名、系列过滤器、其他参数的管道配置说明以及本工作的引用说明。
Reproducible approaches are needed to bring AI/ML for medical image analysis closer to the bedside. Investigators wishing to shadow test cross-sectional medical imaging segmentation algorithms on new studies in real-time will benefit from simple tools that integrate PACS with on-premises image processing, allowing visualization of DICOM-compatible segmentation results and volumetric data at the radiology workstation. In this work, we develop and release a simple containerized and easily deployable pipeline for shadow testing of segmentation algorithms within the clinical workflow. Our end-to-end automated pipeline has two major components- 1. A router/listener and anonymizer and an OHIF web viewer backstopped by a DCM4CHEE DICOM query/retrieve archive deployed in the virtual infrastructure of our secure hospital intranet, and 2. An on-premises single GPU workstation host for DICOM/NIfTI conversion steps, and image processing. DICOM images are visualized in OHIF along with their segmentation masks and associated volumetry measurements (in mL) using DICOM SEG and structured report (SR) elements. Since nnU-net has emerged as a widely-used out-of-the-box method for training segmentation models with state-of-the-art performance, feasibility of our pipleine is demonstrated by recording clock times for a traumatic pelvic hematoma nnU-net model. Mean total clock time from PACS send by user to completion of transfer to the DCM4CHEE query/retrieve archive was 5 min 32 s (± SD of 1 min 26 s). This compares favorably to the report turnaround times for whole-body CT exams, which often exceed 30 min, and illustrates feasibility in the clinical setting where quantitative results would be expected prior to report sign-off. Inference times accounted for most of the total clock time, ranging from 2 min 41 s to 8 min 27 s. All other virtual and on-premises host steps combined ranged from a minimum of 34 s to a maximum of 48 s. The software worked seamlessly with an existing PACS and could be used for deployment of DL models within the radiology workflow for prospective testing on newly scanned patients. Once configured, the pipeline is executed through one command using a single shell script. The code is made publicly available through an open-source license at “https://github.com/vastc/,” and includes a readme file providing pipeline config instructions for host names, series filter, other parameters, and citation instructions for this work.
登录
查看更多内容
DOI：
10.1148/ryai.2019190021
发表时间：
2019-03-01
期刊：
RADIOLOGY-ARTIFICIAL INTELLIGENCE
影响因子：
--
作者：
Chokshi, Falgun H.;Flanders, Adam E.;Langlotz, Curtis P.
通讯作者：
Langlotz, Curtis P.
影响因子：
168.9
作者：
Huber-Wagner, Stefan;Lefering, Rolf;Kanz, Karl-Georg
通讯作者：
Kanz, Karl-Georg
影响因子：
19.7
作者：
Banaste, Nathan;Caurier, Berenice;Millet, Ingrid
通讯作者：
Millet, Ingrid
影响因子：
4.4
作者：
Blezek, Daniel J.;Olson-Williams, Lonny;Korfiatis, Pangiotis
通讯作者：
Korfiatis, Pangiotis
影响因子：
11.2
作者：
Herz, Christian;Fillion-Robin, Jean-Christophe;Fedorov, Andriy
通讯作者：
Fedorov, Andriy