Last Updated:
10th March 2025
ZYing M-D IntelReport is an AI-based system to automatically detect and segment 68 different abnormalities as well as generate diagnostic reports on frontal chest x-ray (CXR) image. It serves as a “first-reader” to interpret and generate diagnostic report from frontal CXR such that radiologists can quickly approve or edit the report.
Magic TB is an AI-based hardware plugin to automatically detect and segment pulmonary tuberculosis lesion(s) on frontal chest x-ray (CXR) image. The product used HDMI connection, with the characteristics of plug and play. TB screening results which contain (1) tuberculosis suspected probability with scores and (2) location information with lesion outlines were marked on user's screen.
Certification
China NMPA Class II
China NMPA Class III (Pending)
Development Stage
On the Market
Deployment
ZYing M-D IntelReport: Online & Offline
Magic TB: Offline only
Intended Age Group
15+ 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
China
Input
Can be used to read images from any chest X-ray machine and model
Chest X-ray image format: DICOM, JPG (Magic TB only), PNG (Magic TB only)
Chest X-ray type: Posterior-anterior chest X-ray, Anterior-posterior chest X-ray
Output
Output includes:
Probability score for TB
Location of each abnormality
Probability score for each abnormality (ZYing M-D IntelReport)
Recommendation for each abnormality (Probability score for each abnormality (ZYing M-D IntelReport)
For ZYing M-D IntelReportThree different threshold levels are set to fine-tune the sensitivity and specificity for TB detection. The results are generated in DICOM SR/SEG format and also display on web-based editor for reporting.
Lung abnormalities included in the TB Score: Calcification, Cavity, Chest wall invasion/destruction, Consolidation, Fibrosis
Additional findings reported by the product: Abscess, Atelectasis, Bronchiectasis, Calcification, Cavity, Chest wall invasion/destruction, Consolidation, Fibrosis, Hyperinflation, Interstitial markings, Loculated pleural effusion, Lymphadenopathy, Mass, Nodule, Opacity, Pleural effusion, Pneumoconiosis, Prominence in hilar region, Pneumothorax, Rib fracture, Scoliosis, Tracheal shift
Hardware
Hardware requirements:
CPU:Intel Core i3 or above
Memory: above 2GB
Server
ZYing M-D IntelReport:
CPU: Intel Xeon E4-2603 or above
Memory: above 8GB
GPU: Nvidia, 6GB or above memory
Magic TB:
CPU:RK3588 or above
Interface: HDMI*2
Memory: above 100GB
Integration with X-ray Systems
Integration with PACS and Legacy Systems
ZYing M-D IntelReport: It is possible to integrate with third party X-ray system(s) through DICOM3.0. The product starts StoreSCP to receive DICOM from X-ray system(s) and sends the SR/SEG back.
Magic TB: The product get input through HDMI and is software API free.
ZYing M-D IntelReport: It is possible to integrate the "Product" with the client’s legacy picture archiving and communication system (PACS).The product gets DICOM files through DICOM3.0/Http/ftp from PACS and posts results back in DICOM/Json format through DICOM3.0 or web API.
Magic TB: The product get input through HDMI and is software API free.
Software
Chrome core explorer.
Processing Time
Less than 30 seconds.
Data Sharing & Privacy
Data are not shared with the developer.
The product has de-identification characteristics.
Software Updates
Software is updated at least once a year.
Please contact info@zying.com.cn for software updates.
Product Development Method
Supervised deep learning (CNN,RNN).
Training
The training dataset contains 350,000 chest X-ray images.
Reference Standard
Human reader and clinically diagnosed.
Publications
1. Guo, L., Hong, K., Xiao, Q. et al. Developing and assessing an AI-based multi-task prediction system to assist radiologists detecting lung diseases in reading chest x-ray images. Medical Imaging 2023: Image Perception, Observer Performance, and Technology Assessment. SPIE, 2023;12467: 73-90. https://doi.org/10.1117/12.2652338
2. Guo, L., Hong, K., Zhang, Z. et al. Assessing an AI-based smart imagery framing and truthing (SIFT) system to assist radiologists annotating lung abnormalities on chest x-ray images for development of deep learning models. Medical Imaging 2023: Computer-Aided Diagnosis. SPIE, 2023;12465: 147-155. https://doi.org/10.1117/12.2653826
3. Hong, K., Guo, L., Lure, Y. M. F. Self-Rating Curriculum Learning for Localization and Segmentation of Tuberculosis on Chest Radiograph. In Medical Image Computing and Computer Assisted Intervention–MICCAI 2022: 25th International Conference, Singapore, September 18–22, 2022, Proceedings, Part I (pp. 686-695). Cham: Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-16431-6_65
4. Zhou, W., Cheng, G., Zhang, Z. et al. Deep learning-based pulmonary tuberculosis automated detection on chest radiography: Large-scale independent testing. Quantitative Imaging in Medicine and Surgery, 2022;12(4):2344. https://doi.org/10.21037/qims-21-676
5. Zhang, X., Wang, Q., Xia, L. et al. Clinical evaluation of chest X-radiograph computer aided diagnostic system for pulmonary tuberculosis applied in primary hospitals. Journal of Tuberculosis and Lung Disease, 2022;2:96-101. https://doi.org/10.19983/j.issn.2096-8493.20210129
6. Nijiati, M., Zhang, Z., Abulizi, A. et al. Deep learning assistance for tuberculosis diagnosis with chest radiography in low-resource settings. Journal of X-ray Science and Technology, 2021;29(5):785-796. https://doi.org/10.3233/XST-210894
This website works best with browsers other than Internet Explorer.