Abstract
The Cancer Imaging Archive (TCIA) is the U.S. National Cancer Institute’s repository for cancer imaging and related information. TCIA contains 30.9 million radiology images representing data collected from approximately 37,568 subjects. This data is organized into collections by tumor-type with many collections also including analytic results or clinical data. TCIA staff carefully de-identify and curate all incoming collections prior to making the information available via web browser or programmatic interfaces. Each published collection within TCIA is assigned a Digital Object Identifier that references the collection. Additionally, researchers who use TCIA data may publish the subset of information used in their analysis by requesting a TCIA generated Digital Object Identifier. This data descriptor is a review of a selected subset of existing publicly available TCIA collections. It outlines the curation and publication methods employed by TCIA and makes available 15 collections of cancer imaging data.
Highlights
Background & SummaryThe Cancer Imaging Archive is a web-accessible information resource designed to promote research reproducibility and encourage reuse of data
The primary data managed by The Cancer Imaging Archive (TCIA) are radiology images of cancer, e.g., Computed Tomography (CT), Magnetic Resonance Imaging (MRI), and Positron Emission Tomography (PET) imaging studies
Data Digital Object Identifiers (DOIs) created by TCIA fall into two categories: ‘Primary Data’ which include radiology and pathology images together with supporting data; and ‘Analysis Results’ that are derived from TCIA Primary Data
Summary
The Cancer Imaging Archive is a web-accessible information resource designed to promote research reproducibility and encourage reuse of data. TCIA encourages and supports cancer-related open science communities by hosting and managing image collections and providing searchable metadata repositories to facilitate collaborative research[1]. The primary data managed by TCIA are radiology images of cancer, e.g., Computed Tomography (CT), Magnetic Resonance Imaging (MRI), and Positron Emission Tomography (PET) imaging studies. These may have come from clinical trials, investigator initiated research, or clinical repositories and may have been collected under a single collection protocol or multiple protocols representing current clinical practice. Data DOIs created by TCIA fall into two categories: ‘Primary Data’ which include radiology and pathology images together with supporting data (e.g. demographics, clinical outcomes, treatment information); and ‘Analysis Results’ (e.g. tumor segmentations, radiomics features, derived image maps, radiologist assessments) that are derived from TCIA Primary Data. An analysis DOI may reference a subset of a TCIA collection or superset, which spans multiple collections
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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 call
