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.

Artificial Intelligence -based Computer Aided Early Diagnosis for low dose CT scans

Principal Investigator

Name
Jolu Ninan

Degrees
Masters Student

Institution
Abu Dhabi University

Position Title
Graduate Researcher

Email
jolujjn@gmail.com

About this CDAS Project

Study
NLST (Learn more about this study)

Project ID
NLST-450

Initial CDAS Request Approval
Nov 19, 2018

Title
Artificial Intelligence -based Computer Aided Early Diagnosis for low dose CT scans

Summary
The aim of this project is to develop an AI-based computer aided early detection system to help diagnose lung cancer at its early stages. A deep neural net approach will be adopted to classify benign and malignant nodules. Semantic Segmentation will also be used to label anatomy and pathological ROI.

Aims

- Lung Nodule feature recognition-based analysis.
- Classification model to classify benign and malignant lung nodules and management of false positives.
- Risk and survival rate prediction model for lung cancer for the subject in the future.
- Deep Learning approach using neural nets for semantic segmentation of the chest CT of the subject

Collaborators

Jolu Jose Ninan (1039789@students.adu.ac.ae)