Systems and methods for detecting cardiovascular anomalies using spatiotemporal neural networks

US11875507B1 · kind B1 · utility

Assignee

• BrightHeart SAS · FR

Inventors

• Christophe Gardella · Paris, FR
• Cécile DUPONT · Paris, FR

Key dates

• Filing date: Mar 14, 2023
• Grant date: Jan 16, 2024
• Expiry date: Mar 14, 2043

Classification

• Technology area (CPC G): Physics
• CPC primary: G06T2207/30048
• WIPO field: Medical technology
• WIPO sector: Instruments

Abstract

Systems and methods are provided for processing image data generated by a medical imaging device such as an ultrasound or echocardiogram device and processing the image data using artificial intelligence and machine learning to determine a presence of one or more congenital heart defects (CHDs) and/or other cardiovascular anomalies in the image data. The image processing system may be used to detect CHDs and/or other cardiovascular anomalies in a fetus. The image data may be processed using a spatiotemporal convolutional neural network (CNN). The spatiotemporal CNN may include a spatial CNN for image recognition and a temporal CNN for processing optical flow data based on the image data. The outputs of the spatial CNN and the temporal CNN may be fused (e.g., using late fusion) to generate a likelihood of CHDs and/or other cardiovascular anomalies.