Abstract
With vast interest in machine learning applications, more investigators are proposing to assemble large datasets for machine learning applications. We aim to delineate multiple possible roadblocks to exam retrieval that may present themselves and lead to significant time delays. This HIPAA-compliant, institutional review board–approved, retrospective clinical study required identification and retrieval of all outpatient and emergency patients undergoing abdominal and pelvic computed tomography (CT) at three affiliated hospitals in the year 2012. If a patient had multiple abdominal CT exams, the first exam was selected for retrieval (n=23,186). Our experience in attempting to retrieve 23,186 abdominal CT exams yielded 22,852 valid CT abdomen/pelvis exams and identified four major categories of challenges when retrieving large datasets: cohort selection and processing, retrieving DICOM exam files from PACS, data storage, and non-recoverable failures. The retrieval took 3 months of project time and at minimum 300 person-hours of time between the primary investigator (a radiologist), a data scientist, and a software engineer. Exam selection and retrieval may take significantly longer than planned. We share our experience so that other investigators can anticipate and plan for these challenges. We also hope to help institutions better understand the demands that may be placed on their infrastructure by large-scale medical imaging machine learning projects.
Highlights
Machine learning is a field focusing on how computers can learn from data and sits at the intersection between statistics and computer science
An initial attempt to retrieve our cohort revealed that a number of studies that we had identified for retrieval were mislabeled musculoskeletal and interventional computed tomography (CT) exams
Another major initial challenge for exam retrieval was inconsistent formatting of medical record numbers (MRNs) and accession numbers (ACCs) across different hospitals
Summary
Machine learning is a field focusing on how computers can learn from data and sits at the intersection between statistics and computer science. An increasingly popular approach to machine learning is to use deep neural networks, inspired by the structure and function of the human brain to process complex image data [1]. A major bottleneck to the potential progress of machine learning in radiology is the assembly of imaging datasets to use for model training [3]. Performance of these models generally improves with more data so maximal dataset size is desired [1]. Increasing numbers of investigators are proposing to assemble their own datasets for training,
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
