JF CXR-1 is a screening and triaging tool to help clinicians identify abnormalities on chest X-rays. JF CXR-1 can also be used as a prioritization tool for radiologists and teleradiology companies.

Certification

Pending, China NMPA tier-3 approval expected in mid-2021

Development Stage

China NMPA tier-2

Deployment

Online & offline

Intended Age Group

15+ years

Target Setting

Primary health centers, teleradiology companies, government/public sector, e.g. national tuberculosis (TB) program, private sector

Current Market

Indonesia, Malaysia, Viet Nam, mainland China, South-East Asia

Input

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

»» Chest X-ray image format: DICOM

»» Chest X-ray type: posterior-anterior CXR

»» Other requirements: none

Output

Output in the form of: 

»» Heat map, 

»» Probability score for TB and dichotomized outcome for TB, 

»» Probability score for any abnormality, pneumonia, nodule, 

»» Pop-up alert message when TB score exceeds cut-off and a line list of all examination records which allows sorting, searching, exporting and statistical analysis.

Server

Online: one cloud instance with 8 CPU with 32 GB memory and at least one GPU with 8 GB or more GPU memory, 1 TB disk space for storing the DICOM files.
Offline: none

Integration

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

Software

A proprietary software that supports File Transfer Protocol (FTP)-style DICOM uploading

Processing Time

Online deployment: it takes around 1 second for the AI algorithm to process the image and generate the result, but the uploading time of the DICOM file may vary depending on the local internet environment.
Offline deployment: it takes around 5 seconds for the AI algorithm to process the image and generate the result.

Hardware

Online: basic desktop without GPU to upload the DICOM files to the server. Recommended specs: Intel Xeon E5-2650, 8 GB memory, 500 GB disk space
Offline: Intel Xeon E5-2650, 16 GB memory, 1 TB disk space

Validation

X-ray machine validation is not needed.

Data Sharing & Privacy

»» Server Location: the server is currently located on AliCloud in China. It can be deployed locally and offline

»» Upon consent, the pixel_array from the DICOM file is shared when the DICOM is generated and uploaded to the company's cloud platform

»» The shared data is used for troubleshooting, monitoring product usage, training or improvement of software. JF Healthcare has their own radiologist team that confirms the AI results. Customers are also notified of any emergent abnormalities e.g. pneumothorax/pneumoperitoneum not related to TB

»» There is an option to de-identify data

Software Updates

»» Quarterly to yearly software updates

»» For improving existing functions, the updates usually do not include additional fees. If new functions are added, the customer can choose whether to pay for additional functions or not. Currently, there are no cost differences between the private and public sector

»» Extra costs: none for minor updates

Price

»» Volume-based pricing models are available

»» Please contact company for quote: Yi Li at

Hardware

Online: basic desktop without GPU to upload the DICOM files to the server. Recommended specs: Intel Xeon E5-2650, 8 GB memory, 500 GB disk space
Offline: Intel Xeon E5-2650, 16 GB memory, 1 TB disk space

Product Development Method

Supervised deep learning (CNN, RNN)

Training

The product was trained on over 120 000 chest X-rays from China

Reference Standard

Human reader

Publications

»» Peer-reviewed publications are not yet available.