Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: Methods and systems are provided for medical imaging systems. In one embodiment, a method comprises acquiring three-dimensional image data with a three-dimensional imaging modality, generating an image of an anatomical structure within the three-dimensional image data with an angled portion of the anatomical structure rendered as at least partially transparent in the image, and displaying, via a display device, the image to a user. In this way, a three-dimensional anatomical structure, such as a vessel, may be visualized such that a user may view the inner wall without distortion.

Abstract: A computer implemented technique for real-time exploration of a vessel network is disclosed. According to the technique, medical image data of a region of interest (ROI) is accessed and a medical image of the ROI is displayed based on the medical image data. Real-time exploration of vessels of a vessel network associated with the medical image are enabled based on received operator input, so as to provide for generating and displaying a vessel curve preview of a vessel on the medical image based on an operator initiated positioning of a cursor in the medical image, generating and displaying a highlighted vessel curve of a vessel on the medical image based on an operator initiated input, and generating and displaying one or more parameters associated with a vessel based on an operator initiated input. The real-time exploration may be performed with/without any prior vessel validation in the vessel network.