Last Updated:
25th January 2025

qXR by Qure.ai is an AI-powered solution for automated chest X-ray (CXR) interpretation, capable of detecting and localizing over 30 abnormalities, including tuberculosis (TB), lung cancer, silicosis, heart failure, and pleural effusion. Trained on 9 million scans, microbiologically confirmed TB X-rays, clinical ground truths, and radiologists reports, qXR uses pixel-level annotations for enhanced diagnostic precision. The TB and lung cancer risk scores with AI-generated visual contours on CXRs aids in clinical decision making, and can be visualized on the end to end disease management platform called qTrack, accessible on phone/laptop. Automated, downloadable annotated reports offer clear insights for healthcare professionals. qXR+qTrack is versatile, supporting active case finding, community outreach, X-ray reading for less skilled staff, prisons and facility-based screening, surveillance, and migrant/ visa health checks, and capturing data for climate-resilient health systems.
Certification
CE Class IIb MDR-qXR v4.1 (v4.2 expected soon)
US FDA Breakthrough Device Designation-qSpot-TB (qXR v4 TB)
Thai FDA-v4.0
Class B CDSCO India-v3
Kementerian Kesehatan Republik Indonesia-v2.1
Malaysia (Medical Device Authority)-v3.2
Philippines FDA-v3.2
Kenya MOH-v4
ANVISA Brazil-v3.2
HealthCanada-v4
Development Stage
On the Market
Deployment
Online & Offline
Intended Age Group
3 years and above (CE MDR Approved)
Target Setting
qXR can be deployed in active case finding and facility based screening settings. It has been deployed in government primary health centers and hospitals, teleradiology companies, National TB programmes, private diagnostic centers & hospitals and in immigration/ prison screening/conflict settings.
Current Market
90+ countries globally
Input
Can be used to read images from any chest X-ray machine and model
Chest X-ray image format: DICOM, JPG, PNG
Chest X-ray type: Posterior-anterior chest X-ray, Anterior-posterior chest X-ray
Output
Output includes:
Heatmap
Dichotomous output indicating whether TB is likely present or absent
Dichotomous output indicating whether each abnormality is likely present or absent
Probability score for TB
Probability score for each abnormality
Location of each abnormality
Contours indicating the location of the abnormalities with labels
0.5 is the default threshold. The threshold can be customized based on requirements.
A structured report is provided that mimics a typical radiology report for a CXR, detailing each abnormality's presence or absence, and providing a TB probability score to indicate the likelihood of TB.
TB Score is generated using deep learning pattern recognition trained using millions of CXRs with microbiological test reports and radiologist reports as reference standard.
Additional findings reported by the product: Atelectasis, Calcification, Cavity, Consolidation, Fibrosis, Hyperinflation, Lymphadenopathy, Mass, Nodule, Opacity, Pleural effusion, Prominance in hilar region, Pneumothorax, Tracheal shift, Lung nodule malignancy risk, Silicosis, Heart failure, Cardiomegaly, Degenerative spine changes, Scoliosis, Rib fractures, Pneuomoperitoneum, Mediastinal widening, Elevated hemidiaphragm, Lines/tubes, and Normal/Abnormal.



Hardware
For on cloud deployments, the gateway is deployed in a local system with minimum specifications and reliable internet to ensure smooth uploading of CXRs occur from X-ray machine to the cloud. For on-premise settings, qXR can be deployed on laptops. Please contact partner@qure.ai for more information.
Server
qXR can be deployed on cloud servers built by cloud hosting partners, following strict data security measures that includes encryption, cloud infrastructure (HIPAA, ISO 27001), data segmentation, and access control. We also deploy at in-country or on-premise servers that meet required specifications.
Integration with X-ray Systems
Integration with PACS and Legacy Systems
qXR can work with any X-ray machine type (CR/DR/ ultraportable) and has been tested with over 20 leading x-ray manufacturers globally like Fujifilm, MinXray, Siemens, Mylab, Allengers, Prognosys, Molbio, LTE, SIUI etc. X-ray files are transmitted to qXR using DICOM protocol.
It is possible to integrate qXR with the client’s legacy PACS. The AI outputs can be sent to the X-ray device console, PACS viewer or RIS or any other EMR systems.
Software
Ubuntu 22.04 is preferred
Processing Time
15-30 seconds depending on the hardware and internet speed.
Data Sharing & Privacy
Data is protected under the HIPAA act 1996,ensuring confidentiality and integrity 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 operations. All data can be de-identified if needed.
Software Updates
Routine product upgrades for improvements and periodic updates for improved accuracy (annual).
Price
Through GDF, a perpetual license for qXR will cost USD 11,000. Alternatively, a 3-years service and maintenance license for qXR will cost USD 16,000. To use the software offline, it is necessary to procure the additional qXR AI laptop, which has the AI software locally installed for offline processing and costs USD 3,000. Furthermore, it is advised to procure CAD with installation and training, costing USD 2,500 for the qXR system.
Service and maintenance licenses can be extended for 1 year at a cost of USD 3,000 or 3 years, costing USD 8,000.
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
GeneXpert and radiologist reports
Publications
1. Tuberculosis detection from chest x-rays for triaging in a high tuberculosis-burden setting: an evaluation of five artificial intelligence algorithms.
Citation: Qin ZZ, Ahmed S, Sarker MS, Paul K, Adel ASS, Naheyan T, Barrett R, Banu S, Creswell J. Tuberculosis detection from chest x-rays for triaging in a high tuberculosis-burden setting: an evaluation of five artificial intelligence algorithms. Lancet Digit Health. 2021 Sep;3(9):e543-e554. doi: 10.1016/S2589-7500(21)00116-3. PMID: 34446265.
2. 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.
Citation: Faiz, Ahmad & Khan, Arman & Majidulla, Gamuchirai & Tavaziva, Ahsana & Nazish, Ahsana & Syed, Kumail & Abidi, Andrea & Benedetti, Dick & Menzies, James & Johnston, Javed & Khan, Saima & Saeed, & Ahmad Khan, Faiz. (2020). 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. The Lancet Digital Health. 2. 10.1016/S2589-7500(20)30221-1.
3. Using artificial intelligence to read chest radiographs for tuberculosis detection: A multi-site evaluation of the diagnostic accuracy of three deep learning systems.
Citation: 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 9, 15000 (2019). https://doi.org/10.1038/s41598-019-51503-3
4. Comparing tuberculosis symptom screening to chest X-ray with artificial intelligence
in an active case finding campaign in Northeast Nigeria.
Citation: John, S., Abdulkarim, S., Usman, S. et al. Comparing tuberculosis symptom screening to chest X-ray with artificial intelligence in an active case finding campaign in Northeast Nigeria. BMC Global Public Health 1, 17 (2023). https://doi.org/10.1186/s44263- 023-00017-2
5. Independent evaluation of 12 artificial intelligence solutions for the detection of tuberculosis.
Citation: Codlin, A.J., Dao, T.P., Vo, L.N.Q. et al. Independent evaluation of 12 artificial intelligence solutions for the detection of tuberculosis. Sci Rep 11, 23895 (2021). https://doi.org/10.1038/s41598-021-03265-0
6. Diagnostic accuracy of chest X-ray interpretation for tuberculosis by three artificial intelligence-based software in a screening use-case: an individual patient meta-analysis of global data.
Citation: Gelaw SM, Kik SV, Ruhwald M, Ongarello S, Egzertegegne TS, Gorbacheva O, Gilpin C, Marano N, Lee S, Phares CR, Medina V, Amatya B, Denkinger CM. Diagnostic accuracy of three computer-aided detection systems for detecting pulmonary tuberculosis on chest radiography when used for screening: Analysis of an international, multicenter migrants screening study. PLOS Glob Public Health. 2023 Jul 14;3(7): e0000402. doi: 10.1371/journal.pgph.0000402. PMID: 37450425; PMCID: PMC10348531.
7. Evaluation of chest X-Ray with automated interpretation algorithms for mass tuberculosis screening in prisons.
Citation: Thiego Ramon Soares, Pedroso, R. et al. (2023). Evaluation of chest X-ray with automated interpretation algorithms for mass tuberculosis screening in prisons: a cross- sectional study. The Lancet Regional Health - Americas, 17, 100388–100388. https://doi.org/10.1016/j.lana.2022.100388
8. Deep learning, computer-aided radiography reading for tuberculosis: a diagnostic accuracy study from a tertiary hospital in India.
Citation: Nash M, Kadavigere R, Andrade J, Sukumar CA, Chawla K, Shenoy VP, Pande T, Huddart S, Pai M, Saravu K. Deep learning, computer-aided radiography reading for tuberculosis: a diagnostic accuracy study from a tertiary hospital in India. Sci Rep. 2020 Jan 14;10(1):210. doi: 10.1038/s41598-019-56589-3. Erratum in: Sci Rep. 2024 Mar 26;14(1):7165. doi: 10.1038/s41598-024-57763-y. PMID: 31937802; PMCID: PMC6959311.
9. 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.
Citation: Tavaziva G, Harris M, Abidi SK, Geric C, Breuninger M, Dheda K, Esmail A, Muyoyeta M, Reither K, Majidulla A, Khan AJ, Campbell JR, David PM, Denkinger C, Miller C, Nathavitharana R, Pai M, Benedetti A, Ahmad Khan F. 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. 2022 Apr 28;74(8):1390-1400. doi: 10.1093/cid/ciab639. PMID: 34286831; PMCID: PMC9049274.
10.Implementing a chest X-ray artificial intelligence tool to enhance tuberculosis screening in India: Lessons learned
Citation: Vijayan S, Jondhale V, Pande T, Khan A, Brouwer M, Hegde A, Gandhi R, Roddawar V, Jichkar S, Kadu A, Bharaswadkar S, Sharma M, Vasquez NA, Richardson L, Robert D, Pawar S. Implementing a chest X-ray artificial intelligence tool to enhance tuberculosis screening in India: Lessons learned. PLOS Digit Health. 2023 Dec 7;2(12):e0000404. doi: 10.1371/journal.pdig.0000404. PMID: 38060461; PMCID: PMC10703224.
11.Computer-Aided Detection for Chest Radiography to Improve the Quality of Tuberculosis Diagnosis in Vietnam’s District Health Facilities: An Implementation Study
Citation: Innes, A.L.; Martinez, A.; Gao, X.; Dinh, N.; Hoang, G.L.; Nguyen, T.B.P.; Vu, V.H.; Luu, T.H.T.; Le, T.T.T.; Lebrun, V.; et al. Computer-Aided Detection for Chest Radiography to Improve the Quality of Tuberculosis Diagnosis in Vietnam’s District Health Facilities: An Implementation Study. Trop. Med. Infect. Dis. 2023, 8, 488. https://doi.org/10.3390/tropicalmed8110488
12. Benefits of Artificial Intelligence versus Human- Reader in Chest X-ray Screening for Tuberculosis in the Philippines
Citation: Nampewo, I; Ariana, P; Vijayan,S; Holthof, B. Benefits of Artificial Intelligence versus Human- Reader in Chest X-ray Screening for Tuberculosis in the Philippines. International Journal of Health Sciences and Research Volume14; Issue: 2; February 2024. https://doi.org/10.52403/ijhsr.20240237
13. Spectrum of TB Disease and Treatment Outcomes in a Mobile Community Based Active Case Finding Program in Yogyakarta Province, Indonesia
Citation: Ananda NR, Triasih R, Dwihardiani B, Nababan B, Hidayat A, Chan G, Cros PD. Spectrum of TB Disease and Treatment Outcomes in a Mobile Community Based Active Case Finding Program in Yogyakarta Province, Indonesia. Trop Med Infect Dis. 2023 Sep 15;8(9):447. doi: 10.3390/tropicalmed8090447. PMID: 37755908; PMCID: PMC10536381.
14. The utility of artificial intelligence in identifying radiological evidence of lung cancer and pulmonary tuberculosis in a high-burden tuberculosis setting
Citation: Nxumalo, Z & Irusen, E & Allwood, B & Tadepalli, M & Bassi, J & Koegelenberg, C. (2024). The utility of artificial intelligence in identifying radiological evidence of lung cancer and pulmonary tuberculosis in a high-burden tuberculosis setting. South African Medical Journal. e1846. 10.7196/SAMJ.2024.v114i6.1846.
15. An independent, multi-country head-to-head accuracy comparison of automated chest x-ray algorithms for the triage of pulmonary tuberculosis
Citation: William Worodria, Robert Castro, Sandra V. Kik, Victoria Dalay, Brigitta Derendinger, Charles Festo, Thanh Quoc Nguyen, Mihaja Raberahona, Swati Sudarsan, AlfredAndama, Balamugesh Thangakunam, Issa Lyimo, Viet Nhung Nguyen, RivoRakotoarivelo, Grant Theron, Charles Yu, Claudia M. Denkinger, Simon GrandjeanLapierre, Adithya Cattamanchi, Devasahayam J. Christopher, Devan Jaganath, R2D2 TB Network (2024). An independent, multi-country head-to-head accuracy comparison of automated chest x-ray algorithms for the triage of pulmonary tuberculosis. medRxiv 2024.06.19.24309061; doi:https://doi.org/10.1101/2024.06.19.24309061
16. Diagnostic accuracy of Chest X-Ray Computer Aided Detection software and blood biomarkers for detection of prevalent and incident tuberculosis in household contact followed up for 5 years
Citation: Liana Macpherson, SandraV. Kik, Matteo Quartagno, Francisco Lakay, Marche Jafth, Nombuso Yende, Shireen Galant, Saalikha Aziz, Remy Daroowala, Richard Court, Arshad Taliep, Keboile Serole, Rene T. Goliath, Nashreen Omar Davies, AmandaJackson, Emily Douglass, Bianca Sossen, Sandra Mukasa, Friedrich Thienemann, Taeksun Song, Morten Ruhwald, Robert J. Wilkinson, Anna K. Coussens, Hanif Esmail. Diagnostic accuracy of Chest X-Ray Computer Aided Detection software and blood biomarkers for detection of prevalent and incident tuberculosis in household contacts followed up for 5 years. medRxiv 2024.06.30.24309731; doi:https://doi.org/10.1101/2024.06.30.24309731
17. Accuracy of digital chest x-ray analysis with artificial intelligence software as a triage and screening tool in hospitalized patients being evaluated for tuberculosis in Lima, Peru
Citation: Biewer AM, Tzelios C, Tintaya K, Roman B, Hurwitz S, et al. (2024) Accuracy of digital chest x-ray analysis with artificial intelligence software as a triage and screening tool in hospitalized patients being evaluated for tuberculosis in Lima, Peru. PLOS Global Public Health 4(2): e0002031. https://doi.org/10.1371/journal.pgph.0002031
Other related publications:
18. Pattern of abnormalities amongst chest X-rays of adults undergoing computer-assisted digital chest X-ray screening for tuberculosis in Peri- Urban Blantyre, Malawi: A cross- sectional study.
Citation: Twabi HH, Semphere R, Mukoka M, Chiume L, Nzawa R, Feasey HRA, Lipenga T, MacPherson P, Corbett EL, Nliwasa M. Pattern of abnormalities amongst chest X-rays of adults undergoing computer-assisted digital chest X-ray screening for tuberculosis in Peri-Urban Blantyre, Malawi: A cross-sectional study. Trop Med Int Health. 2021 Nov;26(11):1427-1437. doi: 10.1111/tmi.13658. Epub 2021 Aug 1. PMID: 34297430.
19. Performance of Qure.ai automatic classifiers against a large annotated database of patients with diverse forms of tuberculosis.
Citation: Engle E, Gabrielian A, Long A, Hurt DE, Rosenthal A. Performance of Qure.ai automatic classifiers against a large, annotated database of patients with diverse forms of tuberculosis. PLoS One. 2020 Jan 24;15(1):e0224445. doi: 10.1371/journal.pone.0224445. PMID: 31978149; PMCID: PMC6980594.
20. Early Evaluation of an Ultra-Portable X-ray System for Tuberculosis Active Case Finding.
Citation: Vo LNQ, Codlin A, Ngo TD, Dao TP, Dong TTT, Mo HTL, Forse R, Nguyen TT, Cung CV, Nguyen HB, Nguyen NV, Nguyen VV, Tran NT, Nguyen GH, Qin ZZ, Creswell J. Early Evaluation of an Ultra-Portable X-ray System for Tuberculosis Active Case Finding. Trop Med Infect Dis. 2021 Sep 4;6(3):163. doi: 10.3390/tropicalmed6030163. PMID: 34564547; PMCID: PMC8482270.
21. Early user perspectives on using computer-aided detection software for interpreting chest X-ray images to enhance access and quality of care for persons with tuberculosis
Citation: Creswell, J., Vo L.N.Q., Qin Z.Z et al. Early user perspectives on using computer-
aided detection software for interpreting chest X-ray images to enhance access and quality of
care for persons with tuberculosis. BMC Global Public Health 1, 30 (2023). https://doi.org/10.1186/s44263-023-00033-2
22. Comparing the Output of an Artificial Intelligence Algorithm in Detecting Radiological Signs of Pulmonary Tuberculosis in Digital Chest X-rays and Their Smartphone-captured Photos of X-ray Films: A Retrospective Study
Citation:Ridhi S, Robert D, Soren P, Kumar M,Pawar S, Reddy B
Comparing the Output of an Artificial Intelligence Algorithm in Detecting Radiological Signs of Pulmonary Tuberculosis in Digital Chest X-Rays and Their Smartphone-Captured Photos of X-Ray Films: Retrospective Study. JMIR Form Res 2024;8:e55641. doi: 10.2196/55641
23.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
24.Ozvardar, Melis E, and Jennifer Otiono. 2024. “Pulmonary Tuberculosis Deaths in High-Burden India: Replacing Manual X-Ray Readouts with Computer Vision Systems.” Journal of High School Science 8 (4): 280–311.
25. Qin ZZ, Van der Walt M, Moyo S, Ismail F, Maribe P, Denkinger CM, Zaidi S, Barrett R, Mvusi L, Mkhondo N, Zuma K, Manda S, Koeppel L, Mthiyane T, Creswell J. Computer-aided detection of tuberculosis from chest radiographs in a tuberculosis prevalence survey in South Africa: external validation and modelled impacts of commercially available artificial intelligence software. Lancet Digit Health. 2024 Sep;6(9):e605-e613. doi: 10.1016/S2589-7500(24)00118-3. Epub 2024 Jul 19. Erratum in: Lancet Digit Health. 2024 Sep;6(9):e604. doi: 10.1016/S2589-7500(24)00176-6. PMID: 39033067; PMCID: PMC11339183.
Additional evidence on the product can also be accessed on the website: https://www.qure.ai/evidences
This website works best with browsers other than Internet Explorer.