15th May 2023
Inspectra CXR is an AI-based software that analyzes adult frontal chest x-rays for signs of 8 abnormality conditions including Tuberculosis. The software aims to assist doctors in prioritization and triage of chest X-ray images. In addition to the top accuracy, Inspectra CXR also offers flexible installation solutions, full integration with PACS system or a standalone AI server, all with a world-class security standard.
Currently, Inspectra CXR identifies features suggestive of 8 abnormality conditions including:
2. Pleural effusion
3. Lung opacity
4. Pulmonary edema
The system returns AI results as a secondary capture on the DICOM for PACS integration option or JPEG for Inspectra application in which both display location of the lesions in heatmap, list of AI findings, and abnormality score corresponding to each finding.
Thai FDA (approved)
Singapore’s HSA (pending)
On the Market
Online & Offline
Intended Age Group
Primary health centres,
general hospital (above primary level), teleradiology companies,
government/public sector, e.g. national TB programme,
Dichotomous output indicating for each abnormality whether this is present or absent.
Dichotomous output only indicating whether TB is likely present or likely absent.
Probability score for TB
Probability score for each abnormality
Location of each abnormality
The default threshold probability score is set at the optimal score for each abnormality condition, 44% for Tuberculosis. The threshold cannot be adjusted by users, but can be adjusted as customization per request.
The structured report presents the probability of abnormal findings in percentage. It consists of 3 subsections.
1. The overall abnormality score of the case across 8 possible findings.
2. The abnormality score of Tuberculosis, i.e. the probability of signs of Tuberculosis.
3. The abnormality score of 7 other findings.
Other: Atelectasis, Blunted costophrenic angle, Consolidation, Fibrosis, Interstitial markings, Loculated pleural effusion, Mass, Nodule, Opacity, Pleural effusion
Inspectra CXR identifies features suggestive of 8 abnormality conditions:
Pleural effusion, Tuberculosis, Lung opacity (includes consolidation, fibrosis, and interstitial markings), Pulmonary edema, Mass, Nodule, Cardiomegaly, Atelectasis
TB Score: Calcification, Cavity, Consolidation, Fibrosis, Interstitial markings, Opacity and Granuloma
We offer various installation options (on-prem, software-as-a-service) and integration options (with PACS). Please contact email@example.com for more details.
Integration with X-ray Systems
Integration with PACS and Legacy Systems
Inspectra CXR is compatible with any digital radiography x-ray machines. The solution can be integrated with x-ray systems from leading global manufacturers such as FujiFilm, Siemens, GE, Phillips, Shimadzu, Canon, Carestream, etc.
Inspectra CXR can be integrated with PACS systems via DICOM protocol.
Please contact firstname.lastname@example.org for more details.
Average processing time is less than 60 seconds per image.
Data Sharing & Privacy
Inspectra CXR ensures patients’ privacy with our best-practice security standard including:
1. HIPAA, GDPR, and PDPA compliance
2. At-rest and in-transit encryption
3. User authentication and access authorization
4. Machine hardening with CIS benchmark
Inspectra CXR offers a volume-based annual subscription plan which includes license costs and all maintenance services. For Installation, there will be a one-time upfront fee which is depending on the solution that the client chooses. Please contact email@example.com for more information
Customers using Inspectra CXR as a service receive instant updates when a new product version is released. They will receive notifications regarding the updates.
On-prem customers can sign up for maintenance service and software updates. Please contact us for details.
Product Development Method
Supervised deep learning (CNN)
1.5 Million CXR images from worldwide population
We use certified radiologist reports ground truth/reference standards. For TB cases, we use certified radiologist reports , sputum test, culture test and CT scan as ground truth/reference standards.
Chaisangmongkon, W., Chamveha, I., Promwiset, T., Saiviroonporn, P. and Tongdee,
T., 2021. External Validation of Deep Learning Algorithms for Cardiothoracic
Ratio Measurement. IEEE Access.
Saiviroonporn, P., Rodbangyang, K., Tongdee, T., Chaisangmongkon, W., Yodprom,
P., Siriapisith, T., Wonglaksanapimon, S. and Thiravit, P., 2021. Cardiothoracic
ratio measurement using artificial intelligence: observer and method validation
studies. BMC Medical Imaging, 21(1), pp.1-11.
Chamveha, I., Tongdee, T., Saiviroonporn, P., Chaisangmongkon, W. (2020). Local
Adaptation Improves Accuracy of Deep Learning Model for Automated X-Ray
Thoracic Disease Detection : A Thai Study. arXiv preprint arXiv:2004.10975.
Chamveha, I., Promwiset, T., Tongdee, T., Saiviroonporn, P., Chaisangmongkon, W.
(2020). Automated Cardiothoracic Ratio Calculation and Cardiomegaly
Detection using Deep Learning Approach. arXiv preprint arXiv:2002.07468.
● Saiviroonporn, P., Wonglaksanapimon, S., Chaisangmongkon, W. et al.
This website works best with browsers other than Internet Explorer.