An Open-Source, Vender Agnostic Hardware and Software Pipeline for Integration of Artificial Intelligence in Radiology W
- PDF / 1,163,928 Bytes
- 6 Pages / 595.276 x 790.866 pts Page_size
- 27 Downloads / 166 Views
METHODS PAPER
An Open-Source, Vender Agnostic Hardware and Software Pipeline for Integration of Artificial Intelligence in Radiology Workflow Jae Ho Sohn 1 & Yeshwant Reddy Chillakuru 1,2 & Stanley Lee 1 & Amie Y Lee 1 & Tatiana Kelil 1 & Christopher Paul Hess 1 & Youngho Seo 1 & Thienkhai Vu 1 & Bonnie N Joe 1
# Society for Imaging Informatics in Medicine 2020
Abstract Although machine learning (ML) has made significant improvements in radiology, few algorithms have been integrated into clinical radiology workflow. Complex radiology IT environments and Picture Archiving and Communication System (PACS) pose unique challenges in creating a practical ML schema. However, clinical integration and testing are critical to ensuring the safety and accuracy of ML algorithms. This study aims to propose, develop, and demonstrate a simple, efficient, and understandable hardware and software system for integrating ML models into the standard radiology workflow and PACS that can serve as a framework for testing ML algorithms. A Digital Imaging and Communications in Medicine/Graphics Processing Unit (DICOM/GPU) server and software pipeline was established at a metropolitan county hospital intranet to demonstrate clinical integration of ML algorithms in radiology. A clinical ML integration schema, agnostic to the hospital IT system and specific ML models/frameworks, was implemented and tested with a breast density classification algorithm and prospectively evaluated for time delays using 100 digital 2D mammograms. An open-source clinical ML integration schema was successfully implemented and demonstrated. This schema allows for simple uploading of custom ML models. With the proposed setup, the ML pipeline took an average of 26.52 s per second to process a batch of 100 studies. The most significant processing time delays were noted in model load and study stability times. The code is made available at “http://bit.ly/2Z121hX”. We demonstrated the feasibility to deploy and utilize ML models in radiology without disrupting existing radiology workflow. Keywords Artificial intelligence . Machine learning . PACS . Informatics . Quality improvement
Background Machine learning (ML) has made significant advances in radiology, especially with the applications of artificial neural networks to various medical imaging modalities. However, very few of these algorithms have been integrated into the clinical radiology Jae Ho Sohn and Yeshwant Reddy Chillakuru contributed equally to this work. * Jae Ho Sohn [email protected] 1
Radiology and Biomedical Imaging, University of California San Francisco (UCSF), 505 Parnassus Ave, San Francisco, CA 94143, USA
2
School of Medicine and Health Sciences, The George Washington University, Washington, DC 20037, USA
workflow [1]. ML algorithms have demonstrated promising performance on a variety of tasks, such as Alzheimer’s prediction, mammographic risk scoring, tomographic segmentation, and arthritic joint and muscle tissue segmentation [2–6]. Given a twofold increase in workload seen by radiologists f
Data Loading...
