Hi-D Imaging 4TAVR

The Hi-D Imaging 4TAVR is a cloud-based Software as a Medical Device leveraging AI deep learning and computer vision to automate the analysis, segmentation, and 3D reconstruction of CT-based cardiac anatomy. Its purpose is to assist healthcare professionals in accurate pre-operational planning and sizing for Transcatheter Aortic Valve Replacement (TAVR) procedures, demonstrating high agreement with expert measurements for key anatomical parameters.

Hi-D Imaging AG received clearance for its Hi-D Imaging 4TAVR, a Class II medical image management and processing system classified as Software as a Medical Device (SaMD). This device is designed to assist trained healthcare professionals, including cardiologists, radiologists, and clinical specialists, in assessing cardiovascular anatomy and measuring heart and vessel structures, specifically the aortic valve. Its primary utility lies in supporting pre-operational planning and sizing for Transcatheter Aortic Valve Replacement (TAVR) procedures, indicated for patients with tricuspid aortic stenosis eligible for TAVR operations without prior aortic valve implants. The Hi-D Imaging 4TAVR is a cloud-based software solution employing artificial intelligence (AI) deep learning models and computer vision methods to provide automated analysis, full automated segmentation of CT-based cardiac anatomy, and 3D reconstruction and visualization. It facilitates automated extraction of heart components, multiplanar reconstruction, 3D surface rendering, and calculation of crucial anatomical parameters for TAVR planning. Performance data, including extensive accuracy testing across 929 CT scans, demonstrated high agreement (over 97%) between automated measurements and expert-derived ground truth measurements, affirming the device's reliability and effectiveness.

AI Regulatory Concerns

Powered by

Jev reads the full FDA letter and returns calibrated concern probabilities per regulatory category. These are AI estimates, not regulatory advice.

• Q1. What specific AI deep learning models and computer vision methods are employed by the Hi-D Imaging 4TAVR, and how do they differ from existing solutions?; Beyond accuracy, what are the observed clinical impacts of using Hi-D Imaging 4TAVR on TAVR procedure efficiency or patient outcomes?; How does the cloud-based nature of the software ensure data security and patient privacy, especially concerning sensitive CT scan data?; Are there plans to expand the device's indications to other valvular heart diseases or complex cardiac interventions beyond tricuspid aortic stenosis?; What is the inter-observer and intra-observer variability when clinicians use the Hi-D Imaging 4TAVR for measurements compared to manual methods?