AUTHOR=Zhang Lei , LaBelle Wayne , Unberath Mathias , Chen Haomin , Hu Jiazhen , Li Guang , Dreizin David 

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

JOURNAL=Frontiers in Medicine

VOLUME=Volume 10 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/medicine/articles/10.3389/fmed.2023.1241570

DOI=10.3389/fmed.2023.1241570

ISSN=2296-858X

ABSTRACT=Background: Reproducible approaches are needed to bring automated medical image analysis closer to the bedside. Investigators wishing to shadow test cross-sectional imaging segmentation algorithms 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. 

Purpose: In this work, we develop and release a simple containerized pipeline for shadow testing segmentation algorithms within the clinical workflow. 

Methods: Our automated pipeline has two major components- 1. a router/listener and anonymizer and an OHIF web viewer backstopped by a DCM4CHEE archive deployed in the virtual infrastructure of our secure hospital intranet, and 2. An on-premises single GPU workstation host for DICOM/NIfTI conversion, 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 method for training segmentation models with state-of-the-art performance for challenging tasks, feasibility of our pipeline is demonstrated by recording clock times for a traumatic pelvic hematoma nnU-net model. 

Results: Mean total clock time from PACS send by user to DCM4CHEE query/retrieve archive transfer completion was 5 minutes 32 seconds (+/- SD of 1 min 26 sec). This compares favorably to report turnaround times for whole-body CT exams (often exceeding 30 minutes), and illustrates feasibility in the clinical setting where quantitative results are needed prior to report sign-off. Inference times accounted for most of the total clock time, ranging from 2 minutes 41 seconds to 8 minutes 27 seconds. All other virtual and on-premises host steps combined ranged from a minimum of 34 seconds to a maximum of 48 seconds. 

Conclusion: The software worked seamlessly with an existing PACS and could be used for deployment of DL models within the radiology workflow for prospective testing. Once configured, the pipeline is executed through one command using a single shell script. The code is publicly available through an open-source license at “https://github.com/vastc/”, and includes a readme file providing config instructions for host names, series filter, other parameters, and citation instructions.