TCIA Updates Cancer Imaging Archive NCI Call January 2019
1. The Cancer Imaging Archive - Updates
NCI Imaging Community Call
January 7, 2019
Christina Vivelo
2. 2
TCIA – General Updates
• Text search feature in our data portal allows searching specific DICOM
metadata fields (e.g. "0018,0015:pancreas" would look only at the
BodyPartExamined field for the word “pancreas”)
• Filter collections on our home page by supporting data available for each
data set (image analyses, clinical, genomic, etc.)
• New “Imaging Proteogenomics” and “Imaging Clinical Trials” tabs on the
TCIA website under “Research Activities” menu
• Updated the “Submit your data” menu on TCIA homepage to clarify
submission protocol for novel imaging data sets and analyses of existing
TCIA datasets
3. 3
TCIA – Collections & Publications
• QIN-Prostate-Repeatability Limited Access Collection: On repeatability of
MRI based measurements in the prostate, plan to add additional MRI
series, parametric maps, potential corresponding clinical and pathology data
• Liu, Z., et al. Conventional MR-based Preopertaive Nomograms for
Prediction of IDH/1p19q Subtype in Low-Grade Glioma, Academic
Radiology (Nov 2018): used MRI data sets from TCIA and genetic data from
TCGA, developing a model to provide preoperative prediction of prognosis
and responsiveness to treatment for lower-grade glioma patients
• Li, Z., et al. Multiregional radiomics profiling from multiparametric MRI:
Identifying an imaging predictor of IDH1 mutation status in glioblastoma,
Cancer Med (Dec 2018): used TCIA MRI data sets, how different models,
using multiregional radiomics features, preoperatively predict IDH1 gene
mutation status in glioblastoma patients
4. 4
TCIA – Other Announcements
• NCI Imaging Data Commons – Promoted the RFP
• CPTAC Pathology Data hosted on TCIA – TCIA hosts a large collection of
pathology data, access through CPTAC Pathology Portal
• Test data from the 2018 BraTS competition is now available upon request
from TCIA helpdesk, reviewed in this Nature article: Bakas S., et al.
Advancing The Cancer Genome Atlas glioma MRI collections with expert
segmentation labels and radiomic features
• Follow TCIA on twitter: @TCIA_News, Facebook, and LinkedIn
Editor's Notes
Manage The Cancer Imaging Archive (TCIA)Increase public availability of high quality cancer imaging data sets for researchSupport NIH data sharing requirements for the cancer imaging communityEnable cancer imaging researchers to adhere to Findability, Accessibility, Interoperability, and Reusability (FAIR) Principles Create a culture of open data sharing and collaboration among cancer imaging researchers
Enable the development of new technologies and methodologies forclinical imaging data de-identification and curationintegrative, multi-disciplinary data analysis (e.g. radiogenomics)deep learningradiomics
Provide leadership and subject matter expertise to NIH data collection activities such as
Manage The Cancer Imaging Archive (TCIA)Increase public availability of high quality cancer imaging data sets for researchSupport NIH data sharing requirements for the cancer imaging communityEnable cancer imaging researchers to adhere to Findability, Accessibility, Interoperability, and Reusability (FAIR) Principles Create a culture of open data sharing and collaboration among cancer imaging researchers
Enable the development of new technologies and methodologies forclinical imaging data de-identification and curationintegrative, multi-disciplinary data analysis (e.g. radiogenomics)deep learningradiomics
Provide leadership and subject matter expertise to NIH data collection activities such as
Manage The Cancer Imaging Archive (TCIA)Increase public availability of high quality cancer imaging data sets for researchSupport NIH data sharing requirements for the cancer imaging communityEnable cancer imaging researchers to adhere to Findability, Accessibility, Interoperability, and Reusability (FAIR) Principles Create a culture of open data sharing and collaboration among cancer imaging researchers
Enable the development of new technologies and methodologies forclinical imaging data de-identification and curationintegrative, multi-disciplinary data analysis (e.g. radiogenomics)deep learningradiomics
Provide leadership and subject matter expertise to NIH data collection activities such as