Skip to Main Content

An official website of the United States government

Government Funding Lapse

Because of a lapse in government funding, the information on this website may not be up to date, transactions submitted via the website may not be processed, and the agency may not be able to respond to inquiries until appropriations are enacted. The NIH Clinical Center (the research hospital of NIH) is open. For more details about its operating status, please visit  cc.nih.gov. Updates regarding government operating status and resumption of normal operations can be found at OPM.gov.

Clinical Decision Support System (CDSS) and self-learning tool for radiologists for Lung CT using Content Based Image Retrieval (CBIR).

Principal Investigator
Name
Sudipta Mukhopadhyay
Degrees
Ph.D.
Institution
Indian Institute of Technology Kharagpur, India
Position Title
Associate Professor
Email
About this CDAS Project
Study
NLST (Learn more about this study)
Project ID
NLST-255
Initial CDAS Request Approval
Nov 10, 2016
Title
Clinical Decision Support System (CDSS) and self-learning tool for radiologists for Lung CT using Content Based Image Retrieval (CBIR).
Summary
We aim to design an automated system to detect and classify lung nodules in thoracic CT images with an objective to create a Clinical Decision Support System (CDSS) that could help radiologists in diagnosing lung nodules faster and with better accuracy. Also, this system can act as a self-learning tool for budding radiologist.

Pulmonary nodules are a potential manifestation of lung cancer, and its early detection can significantly enhance the survival rate of patients. Hundreds of images in thoracic CT scan makes nodule detection a very tiring process for the radiologists. Therefore, a CDSS system can be used to assist radiologists in detecting and diagnosing the lung nodules.

On getting an image, the system will try to detect a nodule and classify it according to the confidence index generated on the basis of similar nodule cases retrieved using Content Based Image Retrieval (CBIR).
Aims

1) To develop algorithms based on both shallow and deep learning techniques to accurately detect and classify thoracic nodules.
2) To develop a technique to automatically segment nodules in real-time.
3) To develop a Content Based Image Retrieval (CBIR) mechanism in order to classify nodules on the bases of past cases.

Collaborators

Prof. Niranjan Khandelwal, PGIMER Chandigarh, India.
Dr. Naveen Kalra, PGIMER Chandigarh, India.
Dr. Mandeep Garg, PGIMER Chandigarh, India.