Open access image repositories: high-quality data to enable machine learning research
Department of Radiation Oncology
Artificial Intelligence and Robotics | Bioinformatics | Databases and Information Systems | Health Information Technology | Neoplasms | Oncology | Radiation Medicine | Radiology
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.
quantitative image analysis, machine learning, image repositories, Cancer Imaging Archive
DOI of Published Version
Prior F, Almeida J, Kathiravelu P, Kurc T, Smith K, Fitzgerald TJ, Saltz J. Open access image repositories: high-quality data to enable machine learning research. Clin Radiol. 2020 Jan;75(1):7-12. doi: 10.1016/j.crad.2019.04.002. Epub 2019 Apr 28. PMID: 31040006; PMCID: PMC6815686. Link to article on publisher's site
Prior F, Almeida J, Kathiravelu P, Kurc T, Smith K, FitzGerald TJ, Saltz J. (2020). Open access image repositories: high-quality data to enable machine learning research. Radiation Oncology Publications. https://doi.org/10.1016/j.crad.2019.04.002. Retrieved from https://escholarship.umassmed.edu/radiationoncology_pubs/104