The Trials and Tribulations of Assembling Large Medical Imaging Datasets for Machine Learning Applications.

Journal Article (Journal Article)

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.

Full Text

Duke Authors

Cited Authors

  • Magudia, K; Bridge, CP; Andriole, KP; Rosenthal, MH

Published Date

  • December 2021

Published In

Volume / Issue

  • 34 / 6

Start / End Page

  • 1424 - 1429

PubMed ID

  • 34608591

Pubmed Central ID

  • PMC8669054

Electronic International Standard Serial Number (EISSN)

  • 1618-727X

Digital Object Identifier (DOI)

  • 10.1007/s10278-021-00505-7

Language

  • eng

Conference Location

  • United States