Skip to Main Content
An official website of the United States government
Login Change: CDAS is now using the NIH Researcher Auth Service (RAS) to manage our existing login options. When logging into CDAS, you will be taken to RAS, where you can select your preferred login provider to access CDAS.

Cloud-based Liquid-biopsy and Radiomics Platform for the Cancer Research Data Commons

Principal Investigator

Name
Chun-Chi Liu

Degrees
Ph.D.

Institution
EarlyDiagnostics

Position Title
Chief Computing Officer

Email
jim.liu@earlydx.com

About this CDAS Project

Study
NLST (Learn more about this study)

Project ID
NLST-1323

Initial CDAS Request Approval
Sep 19, 2024

Title
Cloud-based Liquid-biopsy and Radiomics Platform for the Cancer Research Data Commons

Summary
Radiomics or imaging data analysis, as a counterpart to multi-omics data analysis, provide structural and functional details of tumors in parallel with the molecular features extracted from multi-omics data. Integrative analyses of multimodal data can uncover complex mechanisms of cancer and provide more reliable predictions. We will implement functions for radiomics analysis of the chest/lung CT scans data analysis. CT scan data are the most common type of non-invasive lung cancer diagnosis/prognosis data. We will implement analysis tools to gain insights from the imaging data, help uncover the underlying mechanisms of disease conditions and facilitate better decision-making.

Aims

We will conduct the following aims:
(1) Implement tools to access, query, and visualize imaging data through web-based interfaces. We will implement tools to: i) access and share image information from user-specified collections, cases, studies, or series; ii) query images and annotations by their attributes. The querying can be performed in a user-friendly interface or with SQL language; iii) visualize CT images and annotations.

(2) Implement image processing module to support image normalization and segmentation for machine learning. The module will consist of the following automated processing steps: i) Image normalization; ii) Lung segmentation; and iii) Nodule detection and segmentation.

Collaborators

William Hsu, UCLA