To empower the entire workflow for imaging, screening, follow-up, diagnosis, therapy, and assessment of multiple diseases.

The system can accurately detect lung nodules larger than 3mm. When the number of false positives per scan is 1, the detection sensitivity of early lung cancer reaches up to 95%. The quantitative parameters such as nodule size and density can be automatically measured, and the 3D rendering is displayed for advanced visualization. Moreover, an intelligent algorithm is developed to provide a quantitative assessment of nodule malignancy, which can assist doctors in accurate and efficient diagnosis.

The system consists of four modules, including intelligent nodule detection, semantics-aware image registration, synchronized image visualization and lesion tracking. It assists automated and intelligent longitudinal image reading for earlier lung cancer screening and quantitative treatment assessment.

The system automatically detects the rib fractures from CT chest scans within seconds and provides innovative animated visualization of local rib fractures for radiologists to further examine. It consists of automatic vertebrae localization and identification, rib segmentation and labelling, as well as fracture detection to assist the radiologist quickly spot the broken ribs and complete the report with higher sensitivity.

The system is precisely and efficiently segment cerebral hemorrhage regions with deep learning algorithms, localize hemorrhage anatomical regions, classify hemorrhage levels, and generate quantified and structured diagnostic reports.

The intelligent radiotherapy planning system is based on our self-developed deep learning engine for 3D image segmentation. The engine is highly optimized for model size and runtime GPU memory consumption. It improves the segmentation robustness and accuracy compared to atlas-based approaches and can fast contour a target or an organ at risk within CT/MR in seconds. With such an intelligent system, the efficiency of radiotherapy planning as well as the contouring consistency can be improved.

The system automatically assesses a child’s skeletal maturity and predicts the growth potential from child’s hand radiographs with the aid of state-of-the-art machine intelligence technologies. It localizes and analyzes ossification centers of multiple carpal, metacarpal and phalangeal bones, estimates the bone age and generates structured child’s growth report within seconds.

The system generates brain parcellation and provides quantitative metrics of 112 sub-structures of the brain in seconds with one click. It automatically identifies and labels high-risk brain atrophy regions and supports quantitative follow-up studies.

We offer hospitals and clinics medical computer software design services, and we offer further maintenance of the software, such as updating the software. We also provide software assisted diagnosis aid information, tools, and data on medical imaging, and medical imaging information about the patients via the internet, and software based consultation and advisory services for medical imaging staffs and clinicians.

*Not submitted to FDA
*Not applicable in clinical settings