inHEART Models
inHEART, SASinHEART Models is a suite of medical imaging software tools designed to assist physicians, cardiologists, and radiologists by automatically processing CT images to create 3D models of the heart. It uses AI for automatic segmentation and visualization, helping clinicians better interpret cardiac anatomy for diagnosis and treatment planning.
Intended Use
inHEART MODELS comprises a suite of medical imaging software modules that are intended to provide qualified medical professionals with tools to aid them in reading, interpreting, reporting, and treatment planning. inHEART MODELS accepts DICOM compliant medical images acquired from a variety of imaging devices, including CT and MR. The software is designed to be used by qualified medical professionals (including physicians, cardiologists, radiologists, and technicians) and the users are solely responsible for making all final patient management decisions. The AI software module is indicated for adults only and is designed for CT images only.
Technology
The inHEART MODELS suite consists of three software modules: (1) inHEART MODELS AI for fully automated 3D modeling and segmentation of cardiac structures using a machine learning (UNet) trained on 796 CT cases; (2) inHEART MODELS Shaper for generating digital 3D models from CT or MR images; (3) inHEART MODELS Explorer, a web-based platform for 3D visualization and analysis. The AI module applies data augmentation and uses stochastic gradient descent for training. CT data from multiple manufacturers are supported.
Performance
Performance testing involved software verification and validation, and a clinical study comparing AI-generated segmentations to ground truth and predicate device results on 100 independent CT cases. Metrics included Dice coefficient (>0.9), Average Symmetric Surface Distance (<5mm), and volumetric analysis thresholds. Results showed average Dice score 0.94, ASSD 1.17mm, and volume variations around 7%, meeting validation criteria and confirming substantial equivalence to predicate device (K220727).
Predicate Devices
No predicate devices specified
Device Timeline
- 1
Submission
6/9/2023
8 months - 2
FDA Approval
2/29/2024
Ready to Sharpen Your Edge?
Join hundreds of your peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.
We respect your privacy. Unsubscribe at any time.