FAIR‐compliant clinical, radiomics and DICOM metadata of RIDER, interobserver, Lung1 and head‐Neck1 TCIA collections

Abstract

Purpose One of the most frequently cited radiomics investigations showed that features automatically extracted from routine clinical images could be used in prognostic modeling. These images have been made publicly accessible via The Cancer Imaging Archive (TCIA). There have been numerous requests for additional explanatory metadata on the following datasets — RIDER, Interobserver, Lung1, and Head–Neck1. To support repeatability, reproducibility, generalizability, and transparency in radiomics research, we publish the subjects’ clinical data, extracted radiomics features, and digital imaging and communications in medicine (DICOM) headers of these four datasets with descriptive metadata, in order to be more compliant with findable, accessible, interoperable, and reusable (FAIR) data management principles. Acquisition and validation methods Overall survival time intervals were updated using a national citizens registry after internal ethics board approval. Spatial offsets of the primary gross tumor volume (GTV) regions of interest (ROIs) associated with the Lung1 CT series were improved on the TCIA. GTV radiomics features were extracted using the open‐source Ontology‐Guided Radiomics Analysis Workflow (O‐RAW). We reshaped the output of O‐RAW to map features and extraction settings to the latest version of Radiomics Ontology, so as to be consistent with the Image Biomarker Standardization Initiative (IBSI). Digital imaging and communications in medicine metadata was extracted using a research version of Semantic DICOM (SOHARD, GmbH, Fuerth; Germany). Subjects’ clinical data were described with metadata using the Radiation Oncology Ontology. All of the above were published in Resource Descriptor Format (RDF), that is, triples. Example SPARQL queries are shared with the reader to use on the online triples archive, which are intended to illustrate how to exploit this data submission. Data format The accumulated RDF data are publicly accessible through a SPARQL endpoint where the triples are archived. The endpoint is remotely queried through a graph database web application at http://sparql.cancerdata.org. SPARQL queries are intrinsically federated, such that we can efficiently cross‐reference clinical, DICOM, and radiomics data within a single query, while being agnostic to the original data format and coding system. The federated queries work in the same way even if the RDF data were partitioned across multiple servers and dispersed physical locations. Potential applications The public availability of these data resources is intended to support radiomics features replication, repeatability, and reproducibility studies by the academic community. The example SPARQL queries may be freely used and modified by readers depending on their research question. Data interoperability and reusability are supported by referencing existing public ontologies. The RDF data are readily findable and accessible through the aforementioned link. Scripts used to create the RDF are made available at a code repository linked to this submissio...

Radiomics integration into a picture archiving and communication system

“…Open data from the Maastro LUNG1 cohort [10] , [11] was used to develop and test the software. These data included CT scans with manual delineations stored in the RTSTRUCT format.…”

A review in radiomics: Making personalized medicine a reality via routine imaging

“…Reproducibility and replicability in radiomics are, however, not possible if researchers do not disclose all the details of the analysis performed. Each radiomics model must be accompanied by the of imaging protocol used for image collection, selected scans for analysis with exclusion and inclusion criteria, segmentations of VOIs, detailed accounts of how features were extracted (including the preprocessing and feature reduction, and of the modeling methodology used (ideally, the code) 87 …”

Unpaired cross-modality educed distillation (CMEDL) for medical image segmentation

“…Eighty one T2w turbo spin echo MRI images sourced from 28 NSCLC patients treated with definitive intensity modulated radiation therapy at our institution and imaged every week upto 6 weeks during treatment, as described in our prior work [50] was used. Finally, we also evaluated the robustness of the approach with respect to five radiation oncologists using twenty additional cases from the open-source dataset [51].…”

“…The best performing CMEDL method, CMEDL-MRRN was used to compare against manual segmentations, by five radiation oncologists, sourced from an external institution dataset [51] consisting patients with NSCLC imaged prior to conventionally fractionated radiation treatment and imaged at a single institution. We measured the accuracy (DSC and HD95) with respect to the five raters as well as the coefficient of variation (CV = σ µ ), where σ is the 0.75±0.17…”