top of page


InferRead DR Chest


Company HQ: 

Beijing, China


Last Updated:

15th May 2023

InferRead DR Chest is a screening tool that analyses chest radiograph DICOM images from medical imaging storage devices and automatically evaluates the probability of an abnormality suggestive of tuberculosis (TB). It shows the abnormal cases in a study list. InferRead DR Chest is used to assist doctors in the diagnostic process, but should not be used as a confirmatory diagnostic tool on its own. The InferRead DR Chest product offers different deployment configurations that adapt to different use cases.


CE-marked Class IIb

Development Stage

On the Market


Online & Offline

Intended Age Group

12+ years

Target Setting

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

Current Market

As of Apr 2023, Infervision has expanded its global strategic layout to Europe, Africa, East Asia, Africa, Asia-Pacific and North and South Americas, with the InferRead DR Chest solution deployed in multiple countries such as Moldova, Uzbekistan, South Africa, Pakistan etc.


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


Structured report including: 

Heat map 

Detection box output indicating the presence or absence of the following abnormalities: Pulmonary Nodule, Fracture, Pneumothorax, Tuberculosis, Pleural Effusion, Pulmonary Infection, Aorta Calcification, Cardiomegaly, Aorta Tortuous, Hilar Shadow, Costophrenic Angle, Hemidiaphragm, Atelectasis, Aorta Protrusion, Increased Lung Markings, Pleura Thickening

Probability score for TB

Probability score for each abnormality 

Location of each abnormality


To view the AI result from another client computer, the client computer should meet the following requirements:
CPU: 4-core or above


Requirements for server hardware:
CPU: 4-core (8-vcore) or above
RAM: 16GB or above
Hard drive: 250 GB or above SSD. To store images, an additional high-speed HDD > 1TB is recommended.
GPU: Optional. If present, the processing speed will largely increase (3 – 5 seconds per X-ray image). Applicable GPU models include: Nvidia GTX 1080, RTX 2070, RTX 3070, Tesla T4, Tesla P4, Tesla V100, Tesla M50, Tesla A4000.
Network card must be present. (Ethernet or WIFI)



To view the AI result from another client computer, the client computer should meet the following requirements:
CPU: 4-core or above

Integration with X-ray Systems

Integration with PACS and Legacy Systems

It is possible to integrate the product with the client’s legacy picture archiving and communication system (PACS).


Software requirements for client computer:
OS: Windows XP or above
Browser: Google Chrome 49.0 or above
Software requirements for server:
OS: Ubuntu 18.04 LTS or above
Docker: 20.10 or above

Processing Time

With GPU, it takes around 3 – 5 seconds per X-ray image. Without GPU, it takes around 15 – 30 seconds per X-ray image.

Data Sharing & Privacy

Offline (onsite) installation is available. The developer can install the AI software in a laptop (or console of an X-ray machine), which will be shipped onsite for installation. In this case, all data will remain onsite, and no data will go into cloud.
Optional cloud server is available upon request. Location: flexible location within the country. A local cloud server (on AWS, Google Cloud, or local server) can be arranged if requested.
Data are not shared with the developer
De-identification option can be provided if required by customer


Flexible pricing models are available
Perpetual license for InferRead software and related accessories and services are available on the Stop TB Partnership’s Global Drug Facility (GDF) catalogue. Please see the Diagnostics Catalogue of GDF for more details.
Please contact the company for quote (

Software Updates

Please contact the company for this information (

Product Development Method

Supervised deep learning (CNN, RNN)


Please contact the company for this information (

Reference Standard

Culture, sputum smear microscopy, and human reader


Qin, Z.Z., Ahmed, S., Sarker, M.S. et al. Tuberculosis detection from chest x-rays for triaging in a high tuberculosis-burden setting: an evaluation of five artificial intelligence algorithms. Lancet Digital Health. 2021;3:e543–5437: 2113–31.

Does this page require updates? Send us a message:

This website works best with browsers other than Internet Explorer.

bottom of page