General Electric Company

Ge Precision Healthcare LLC

Celine Pruvot

Nicolas Gogin

Faycal El Hanchi El Amrani

Mario Viti

Laurent Launay

Guillermo Ruiz

Jean-Marc Treutenaere

Laurent Jean Lucien Stefani

Methods and systems are provided for detecting coronary lesions in 3D cardiac computed tomography and angiography (CCTA) images using deep neural networks. In an exemplary embodiment, a method for detecting coronary lesions in 3D CCTA images comprises, acquiring a 3D CCTA image of a coronary tree, mapping the 3D CCTA image to a multi-label segmentation map with a trained deep neural network, generating a plurality of 1D parametric curves for a branch of the coronary tree using the multi-label segmentation map, determining a location of a lesion in the branch of the coronary tree using the plurality of 1D parametric curves, and determining a severity score for the lesion based on the plurality of 1D parametric curves.

Systems and methods for multi-label segmentation of cardiac computed tomography and angiography images using deep neural networks

A method for generating an image of an obtaining a three-dimensional (3D) volume dataset of an object of interest, automatically analyzing the 3D volume dataset to generate a window level setting, automatically generating a window width setting based on the window level setting, and automatically displaying an image of the object of interest using the window width setting. An imaging system and a non-transitory computer readable medium are also described.

System and method for generating image window view settings

A CT radiographic imaging process implements a processing operation on images in order to detect the use of a saline solution. When a saline solution is detected, it extracts a component or a portion of a component that does not appear to be contrasted in the initial images, for example, in the case of cardiac imaging, the right cavity of the heart. The imaging system comprises means for implementing this process.

CT tomographic imaging process and system

Systems, methods and computer products for automatically extracting automatically cardiac calcifications and obtaining a centerline in the tracking. Exemplary embodiments include a method of cardiac diagnostics, the method including obtaining coronary tree segmentation to obtain cardiac volume information, splitting the volume into portions to obtain an adjacency graph, computing a mean of a sub-volume of the volume, obtaining gray value segmentation of the sub-volume, defining a centerline of a blood vessel that avoids calcifications within the blood vessel and detecting an actual centerline of the blood vessel and enhancing lumen visualization of the blood vessel.

Growing community of inventors

Buc, France

Celine Pruvot