Open access image repositories: high-quality data to enable machine learning research. Issue 1 (January 2020)

• Record Type: Journal Article
• Authors: Prior, F.; Almeida, J.; Kathiravelu, P.; Kurc, T.; Smith, K.; Fitzgerald, T.J.; Saltz, J.
• Is Part Of: Clinical radiology. Volume 75:Issue 1(2020)
• Page Start: 7
• Page End: 12
• Publication Date: 2020-01
• Subjects: Medical radiology -- Periodicals; Radiotherapy -- Periodicals; Radiotherapy -- Periodicals; Radiology -- Periodicals; Societies, Medical -- Periodicals; Medical radiology; Radiotherapy; Electronic journals; Periodicals; 616.0757
• DOI: 10.1016/j.crad.2019.04.002
• Languages: English
• ISSNs: 0009-9260

Abstract

Abstract : Originally motivated by the need for research reproducibility and data reuse, large-scale, open access information repositories have become key resources for training and testing of advanced machine learning applications in biomedical and clinical research. To be of value, such repositories must provide large, high-quality data sets, where quality is defined as minimising variance due to data collection protocols and data misrepresentations. Curation is the key to quality. We have constructed a large public access image repository, The Cancer Imaging Archive, dedicated to the promotion of open science to advance the global effort to diagnose and treat cancer. Drawing on this experience and our experience in applying machine learning techniques to the analysis of radiology and pathology image data, we will review the requirements placed on such information repositories by state-of-the-art machine learning applications and how these requirements can be met. Highlights: Machine learning algorithms have shown promising results but the number of clinically successful AI products is limited. Access to appropriate data for training, testing and evaluation is a key limitation to the field. Open access repositories are a vital source of quality data needed for training and testing machine learning algorithms.