Last Updated:
15th May 2023
qXR is a CE class IIb certified AI tool for automated chest X-ray interpretation. It detects over 30 findings, including tuberculosis, lung malignancies, COVID-19, COPD, and heart failure. qXR is WHO evaluated, customizable for TB screening, and can be used offline with qBox/laptop or online on a HIPAA-compliant cloud service. It generates reports and insights, supports various deployment modes, and works on desktop and mobile devices.
qXR integrates with qTrack, an app for case and program management, allowing multiple stakeholders to securely connect, comment, access patient information and dashboards to support a variety of program workflows.
A collaborative threshold optimization exercise can be conducted to accurately support program objectives.
Certification
CE MDR Class IIb, Kenya (Ministry of Health Kenya), India (CDSCO (Central Drugs Standard Control Organization)), Thailand (Thai FDA), Indonesia - Kementerian Kesehatan Republik Indonesia, Malaysia (Medical Device Authority Malaysia)
Development Stage
On the Market
Deployment
Online & Offline
Intended Age Group
3+ years
Target Setting
qXR can be deployed in government primary health centres and hospitals, teleradiology companies, National TB programmes, private diagnostic centers & hospitals and in immigration screening settings. Apart from active case finding at sites, qXR has also been deployed in level 2 and level 3 hospitals in a surveillance mode to scan all CXR to aid in additional case detection.
Current Market
Global, qXR is being used in over 80+ countries
Input
Can be used to read images from any kind of chest X-ray machine (vendor neutral)
Chest X-ray image format: DICOM for digital chest X-rays, PNG and JPEG formats using qTrack for acquiring pictures of analog chest X-ray films
Chest X-ray type: posterior-anterior chest X-ray, anterior-posterior chest X-ray
Other requirements: none
Output
Outputs include: Visual outputs – secondary capture, coloured heatmaps, Text outputs – structured report, tabulated pdf report.
Structured report including:
Probability score as well as output indicating whether each abnormality is present or absent
Probability score for TB as well as output indicating whether TB is likely present or likely absent
Contours indicating the location of the abnormalities with labels
Abnormalities detected by the product for which a separate abnormality score is given include: Abnormal, TB, opacities (atelectasis, cavities, calcification, consolidation, fibrosis, nodules, reticulonodular pattern), emphysema/hyperinflation, pleural effusion, blunted costophrenic angle, pneumothorax, cardiomegaly, tracheal shift, degenerative spine changes, scoliosis, hilar prominence, rib fractures, COVID-19, pneumoperitoneum, mediastinal widening, elevated hemidiaphragm, abnormal diaphragm shape, lines and tubes (4 types) and lung nodule malignancy risk for nodules.
Multilingual support for outputs in Portuguese, Spanish, Vietnamese, French & Russian . Provision to support more languages is available.
Hardware
For on-premise settings, qXR can either be deployed on a small footprint portable computer called qBox or laptops. Please contact partner@qure.ai for more information.
Server
qXR can be deployed on cloud servers built by cloud hosting partners with the highest standards for privacy and data security. We also deploy at in-country or on-premise servers that meet required specifications. Please contact partner@qure.ai for information.
Hardware
For on-premise settings, qXR can either be deployed on a small footprint portable computer called qBox or laptops. Please contact partner@qure.ai for more information.
Integration with X-ray Systems
Integration with PACS and Legacy Systems
qXR can generalise to any X-ray manufacturer (CR/DR/ ultraportable) and has been tested with over 20 leading x-ray manufacturers globally like Fujifilm, MinXray, Siemens, Mylab, Allengers etc. X-ray files are transmitted to qXR using DICOM protocols.
It is possible to integrate qXR with the client’s legacy PACS. The CAD outputs can be sent to the X-ray device console, PACS viewer or RIS or any other EMR systems.
Software
Ubuntu 18.04 is preferred
Processing Time
Less than 40 secs for TB findings
Data Sharing & Privacy
Data is protected under the Health Insurance Portability and Accountability (HIPAA) act 1996, ensuring confidentiality, integrity and availability of ePHI. Also, the Information Security Management System, as per ISO 27001:2013, considers the possible risks and vulnerabilities of the data involved across all business operations. ePHI is protected by the standards HIPAA and ISO 27001. All data is anonymized before analysis by qXR.
There are 2 modes of deployment: A cloud-based model and an on-premise one:
1. For the cloud-based product, the server can be set up in any location (preferably Amazon Web Services but can also be deployed with the help of other cloud providers). An environment set-up for a server, be it local or national, can be facilitated. The cloud-based deployment can be done using a recommended cloud service in-country or with a Qure.ai preferred partner.
2. Offline/On-premise deployment can be done using a small footprint, portable computer or a laptop with the data secure within the premises.
Software Updates
Routine product upgrades for improvements and periodic updates for improved accuracy (annual). V4.0 has improvements to processing times, non-TB findings, pediatric models and processing of low quality images. This new version is available to be deployed on request on specific hardware, while V3.2 will continue to be available & supported.
Product Development Method
Deep learning to analyse chest X-ray scans. To find out more about the product's algorithm development, contact partner@qure.ai.
Training
The current commercial version of qXR V4.0 has been trained and tested on 5 million chest X-rays acquired globally.
Reference Standard
Human readers, culture, sputum smear microscopy, and GeneXpert results
Publications
Tavaziva, G., Harris, M., Abidi, S.K. et al. Chest X-ray analysis with deep learning-based software as a triage test for pulmonary tuberculosis: an individual patient data meta-analysis of diagnostic accuracy. Clin Infect Dis. 2021:ciab639. https://doi.org/10.1093/cid/ciab639
Ebrahimian, S., Homayounieh, F., Rockenbach, M.A.B.C. et al. Artificial intelligence matches subjective severity assessment of pneumonia for prediction of patient outcome and need for mechanical ventilation: a cohort study. Sci Rep. 2021;11(1):858. https://doi.org/10.1038/s41598-020-79470-0
Khan, F.A., Majidulla, A., Tavaziva, G. et al. Chest x-ray analysis with deep learning-based software as a triage test for pulmonary tuberculosis: a prospective study of diagnostic accuracy for culture-confirmed disease. Lancet Digit Health. 2020;2(11):e573-e581. https://doi.org/10.1016/S2589-7500(20)30221-1
Mushtaq, J., Pennella, R., Lavalle, S. et al. Initial chest radiographs and artificial intelligence (AI) predict clinical outcomes in COVID-19 patients: analysis of 697 Italian patients. Eur Radiol. 2021;31(3):1770-1779. https://doi.org/10.1007/s00330-020-07269-8
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. https://doi.org/10.1016/S2589-7500(21)00116-3
Engle, E., Gabrielian, A., Long, A., Hurt, D.E., Rosenthal, A. Performance of Qure.ai automatic classifiers against a large annotated database of patients with diverse forms of tuberculosis. PLoS One. 2020;15(1):e0224445. https://doi.org/10.1371/journal.pone.0224445
Nash, M., Kadavigere, R., Andrade, J. et al. Deep learning, computer-aided radiography reading for tuberculosis: a diagnostic accuracy study from a tertiary hospital in India. Sci Rep. 2020;10(1):210. https://doi.org/10.1038/s41598-019-56589-3
Qin, Z.Z., Sander, M.S., Rai, B. et al. Using artificial intelligence to read chest radiographs for tuberculosis detection: A multi-site evaluation of the diagnostic accuracy of three deep learning systems. Sci Rep. 2019;9(1):15000. https://doi.org/10.1038/s41598-019-51503-3
Putha, P., Tadepalli, M., Reddy, B. Can Artificial Intelligence Reliably Report Chest X-Rays?: Radiologist Validation of an Algorithm trained on 2.3 Million X-Rays. Available from: https://arxiv.org/abs/1807.07455
Singh, R., Kalra, M.K., Nitiwarangkul, C et al. Deep learning in chest radiography: Detection of findings and presence of change. PLoS One. 2018;13(10):e0204155. https://doi.org/10.1371/journal.pone.0204155
This website works best with browsers other than Internet Explorer.