A vendor-agnostic, PACS integrated, and DICOM-compatible software-server pipeline for testing segmentation algorithms within the clinical radiology workflow

Frontiers in Medicine

Medicine

Haomin Chen¹  Jiazhen Hu¹  Mathias Unberath¹  Lei Zhang²  Wayne LaBelle²  David Dreizin²  Guang Li² 

[1] Department of Computer Science, Whiting School of Engineering, Johns Hopkins University, Baltimore, MD, United States;School of Medicine, University of Maryland, Baltimore, MD, United States;

关键词: artificial intelligence;    deep learning;    nnU-net;    PACS;    DICOM;    OHIF;    quantitative visualization;    computed tomography;   

DOI  :  10.3389/fmed.2023.1241570

 received in 2023-06-20, accepted in 2023-10-09,  发布年份 2023

来源: Frontiers

【 摘 要 】

BackgroundReproducible 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.PurposeIn this work, we develop and release a simple containerized and easily deployable pipeline for shadow testing of segmentation algorithms within the clinical workflow.MethodsOur 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.ResultsMean 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.ConclusionThe 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.

【 授权许可】

Unknown   
Copyright © 2023 Zhang, LaBelle, Unberath, Chen, Hu, Li and Dreizin.