A DICOM Framework for Machine Learning Pipelines against Real-Time Radiology Images
This addresses the problem of limited computing resources and data transfer inefficiencies for researchers in clinical radiology, though it is incremental as it builds on existing DICOM protocols.
The paper tackles the challenge of executing machine learning pipelines on radiology images in real-time by proposing Niffler, a framework that efficiently queries and retrieves images from hospital systems, enabling stable operation for over 19 months and supporting projects like IVC filter detection.
Executing machine learning (ML) pipelines in real-time on radiology images is hard due to the limited computing resources in clinical environments and the lack of efficient data transfer capabilities to run them on research clusters. We propose Niffler, an integrated framework that enables the execution of ML pipelines at research clusters by efficiently querying and retrieving radiology images from the Picture Archiving and Communication Systems (PACS) of the hospitals. Niffler uses the Digital Imaging and Communications in Medicine (DICOM) protocol to fetch and store imaging data and provides metadata extraction capabilities and Application programming interfaces (APIs) to apply filters on the images. Niffler further enables the sharing of the outcomes from the ML pipelines in a de-identified manner. Niffler has been running stable for more than 19 months and has supported several research projects at the department. In this paper, we present its architecture and three of its use cases: an inferior vena cava (IVC) filter detection from the images in real-time, identification of scanner utilization, and scanner clock calibration. Evaluations on the Niffler prototype highlight its feasibility and efficiency in facilitating the ML pipelines on the images and metadata in real-time and retrospectively.