This website works best with browsers other than Internet Explorer.

Product:

Version 0.1

Dr CADx

Company HQ: 

Bulawayo, Zimbabwe

Last Updated:

April 14th, 2020

Dr CADx is a computer aided reading system that can interpret medical images and distinguish the chest X-rays of healthy people from those with tuberculosis (TB) or lung cancer. On analyzing a chest X-ray image DrCADx provides a likelihood score (between 0 to 100%) for the presence of TB and also generates a heatmap.

Certification

Pending. South African certification and CE mark anticipated in 2021

Development Stage

Validation

Deployment

Online only

Intended Age Group

16+ years

Target Setting

Primary health centers, general hospital (above primary level), government/public sector, e.g. national TB program, private sector

Current Market

Currently not on the market

Input

»» Can be used to read images from any kind of chest X-ray machine (vendor neutral)

»» Chest X-ray image format: JPEG, PNG, DICOM

»» Chest X-ray type: posterior-anterior chest X-ray, anterior-posterior chest X-ray

»» Other requirements: none

Output

The Dr CADx results consists of: 

»» Heat map 

»» A probability score for TB

Server

None

Integration

With the current version it is not possible to integrate with client's legacy picture archiving and communication system (PACS).

Software

Any web browser

Processing Time

Less than a minute

Hardware

Computer interfaced to the X-ray machine and connected to the internet

Validation

No validation required for the X-ray machine

Data Sharing & Privacy

»» Server is located in the USA. Local or national server options not currently available

»» Data is shared with the developer. DICOM images including DICOM meta data are sent to the server. Dicom meta data is not being used by the manufacturer

»» No option to de-identify input at the moment. This feature is being developed for the next version of the product

Software Updates

»» Annual software updates

»» Updates are included in usage fees. No cost difference between private and public sector

Price

»» Online solution: US$ 1 per chest X-ray; no upfront costs

»» Offline solution: US$ 1 per chest X-ray; there will be installation costs of US$ 500 per machine and users will be charged for travel and lodging with actual amount based on location

»» No difference in public private pricing

»» Sales contact: Gift Gana at info@drcadx.com

Product Development Method

Supervised deep learning (CNN, RNN)

Training

The product was trained on thousands of chest X-rays from the USA, China, and Belarus

Reference Standard

Mixture of human reader, culture, sputum smear microscopy and GeneXpert results

Publications

»» Peer-reviewed publications are not yet available.

Does this page require updates? Send us a message:

Designed by Tasneem Naheyan

© 2020 Stop TB Partnership