NCI Imaging Data Commons September 2022 release is out!
Data
Along with the addition to 9 new collections, the main highlight for this release is the availability of clinical data collections, which until now have only been available in spreadhseets that followed collection-specific organization. With this release we ingested clinical data for most of the collections into BigQuery tables, so that you can search both the names of the columns available in the source spreadsheets and the values assigned to those columns. Each clinical data table contains the patient identifier matching DICOM PatientID to simplify linking with imaging data. The recommended way to get started with understanding clinical data in IDC is this new notebook.
Training
This month we conducted IDC tutorial at the annual meeting of the NCI Informatics Technology for Cancer Research (ITCR). You can see the agenda and pointers to the notebooks used in the tutorial here. The newly released “getting started” notebook will hopefully serve as a gentle introduction into the organization of data in IDC and its main features.
Pictures
A sample from the newly released HCC-TACE-Seg collection, which includes segmentations of lliver, mass and blood vessels.
Reminders
- Please drop by IDC Office Hours to ask any questions about IDC: every Tuesday 16:30 – 17:30 (New York) and Wednesday 10:30-11:30 (New York) via Google Meet at https://meet.google.com/xyt-vody-tvb .
- Free cloud credits are available for those who want to explore features of Google Cloud not included in the free tier (e.g., Cloud Compute Engine, Vertex AI, using Healthcare API for your data): apply here
Summary
The IDC DataStudio dashboard was updated to include summary of the available annotations and clinical data.
Note the snapshot of the dashboard above captures only the publicly available IDC collections.
(as always, the live dashboard for the screenshot above is available here)
