Skip to Main Content
An official website of the United States government
Upcoming Login Change: On or about August 24, CDAS will begin 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.

Image retrieval and automatic preliminary diagnosis of chest X-ray radiographs

Principal Investigator

Name
Jogundas Armaitis

Degrees
Ph. D.

Institution
Oxipit, UAB

Position Title
COO

Email
jogundas@oxipit.ai

About this CDAS Project

Study
PLCO (Learn more about this study)

Project ID
PLCO-360

Initial CDAS Request Approval
Apr 13, 2018

Title
Image retrieval and automatic preliminary diagnosis of chest X-ray radiographs

Summary
In this project, we will develop, improve, and validate/test Deep Learning models using the chest X-ray dataset. These models will be used to create/improve novel radiological tools, intended to assist radiologists and make their chest X-ray workflow more efficient in two ways: (i) enable image retrieval from large datasets by allowing pixel-data-based search, and (ii) offer a preliminary diagnosis, covering most of the pathologies present in a chest X-ray.

Aims

* Develop new Deep Learning models and improve existing Deep Learning models
* Validate and test Deep Learning models

Collaborators

Oxipit, UAB