top of page



Version 0.1

Company HQ: 

Bulawayo, Zimbabwe


Last Updated:

14 April 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 analysing a chest X-ray image, Dr CADx provides a likelihood score (between 0 to 100%) for the presence of TB and also generates a heat map.


Pending. South African certification and CE mark anticipated in 2021

Development Stage



Online only

Intended Age Group

16+ years

Target Setting

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

Current Market

Currently not on the market


»» 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


The Dr CADx results consist of: 

»» Heat map 

»» A probability score for TB



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


No validation required for the X-ray machine


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




The current version of Dr CADx cannot be integrated with client's legacy picture archiving and communication system (PACS).


Any web browser

Processing Time

Less than a minute

Data Sharing & Privacy

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

»» Data are shared with the developer. DICOM images including DICOM metadata are sent to the server. Dicom meta data are 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


»» 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 or private pricing

»» Sales contact: Gift Gana at

Software Updates

»» Annual software updates

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

Product Development Method

Supervised deep learning (CNN, RNN)


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


Peer-reviewed publications are not yet available.

Does this page require updates? Send us a message:

This website works best with browsers other than Internet Explorer.

bottom of page