Abstract: A method and system for extracting coronary artery centerlines from 3D medical image volumes is disclosed. Heart chambers are segmented in a 3D volume. Coronary artery centerlines are initialized in the 3D volume coronary artery based on the segmented heart chambers. The coronary artery centerlines are locally refined based on a vesselness measure. A length of each coronary artery centerline is shrunk to verify that the coronary artery centerline is within a coronary artery. The coronary artery centerline is the extended using data-driven vessel tracing.

Abstract: A method and system for segmentation and removal of pulmonary arteries, pulmonary veins, and a left atrial appendage from 3D medical image data, such as 3D computed tomography (CT) volumes, is disclosed. A global shape model is segmented for each of pulmonary arteries, pulmonary veins, and a left atrial appendage in a 3D volume. The segmented global shape model for each of the pulmonary arteries, pulmonary veins, and left atrial appendage is locally refined based in local voxel intensities in the 3D volume, resulting in a respective mask for each structure. The mask is used to remove voxels belonging to the pulmonary arteries, pulmonary veins, and left atrial appendage from the 3D volume in order to better visualize coronary arteries and bypass arteries.

Abstract: A method and system for adaptive discriminant learning and measurement fusion for image based catheter tracking is disclosed. An adaptive discriminant model is trained online based on a tracked object, such as a pigtail catheter tip, in at least one previous frame of a fluoroscopic image sequence. The object is tracked in the current frame of the fluoroscopic image sequence based at least on the adaptive discriminant model trained online. The object may be tracked in the current frame based on a fusion of three types of measurement models including the adaptive discriminant model trained online, an object detection model trained offline, and an online appearance model.

Abstract: A method and system for estimating 3D cardiac motion from a single C-arm angiography scan is disclosed. An initial 3D volume is reconstructed from a plurality of 2D projection images acquired in a single C-arm scan. A static mesh is extracted by segmenting an object in the initial 3D volume. The static mesh is projected to each of the 2D projection images. A cardiac phase is determined for each of the 2D projection images. A deformed mesh is generated for each of a plurality of cardiac phases based on a 2D contour of the object and the projected mesh in each of the 2D projection images of that cardiac phase.

Abstract: A method and system for multi-part left atrium (LA) segmentation in a C-arm CT volume is disclosed. Multiple LA part models, including an LA chamber body mesh, an appendage mesh, a left inferior pulmonary vein (PV) mesh, a left superior PV mesh, a right inferior PV mesh, and a right superior PV mesh, are segmented in a 3D volume. A volume mask is generated from the LA chamber mesh, the appendage mesh, and the PV meshes. Erosion is performed in the LA chamber body and a plurality of ostia regions in the volume mask. The plurality of ostia regions in the volume mask are refined using region growing, and a smooth mesh is fit to each ostia region. A consolidated LA mesh is generated from the volume mask and the parts of the LA mesh are relabeled in the ostia region based on part boundaries detected using an optimization approach.

Abstract: A method and system for detecting a virtual electrode (VE) on a coronary sinus (CS) catheter in a fluoroscopic image sequence is disclosed. User inputs indicating locations of CS catheter electrodes and a location of a VE are received. A catheter electrode model and a VE part model is initialized in a first frame of the fluoroscopic image sequence. The VE is tracked by detecting electrode position candidates and catheter body point candidates in the subsequent frames of the fluoroscopic image sequence using respective trained detectors, tracking the catheter electrode model in the subsequent frames based on the detected electrode position candidates, generating VE part hypotheses in the subsequent frames based on detection of the most proximal electrode (MPE) in each subsequent frame, calculating a probability score for each of the VE part hypotheses, and selecting an VE part hypothesis with the highest probability score.

Abstract: A method and system for multi-part left atrium (LA) segmentation in a C-arm CT volume is disclosed. Multiple LA part models, including an LA chamber body mesh, an appendage mesh, a left inferior pulmonary vein (PV) mesh, a left superior PV mesh, a right inferior PV mesh, and a right superior PV mesh, are segmented in a 3D volume. The LA chamber body mesh and the appendage mesh may be segmented as a combined object and the PV meshes may be segmented subject to a statistical shape constraint. A consolidated LA mesh is generated from the segmented LA part models.

Abstract: A method for automatically assessing medical ultrasound (US) image usability, includes extracting one or more features from at least one part of a medical ultrasound image, calculating for each feature a feature score for each pixel of the at least one part of the ultrasound image, and classifying one or more image pixels of the at least one part as either usable or unusable, based on a combination of feature scores for each pixel, where usable pixels have intensity values substantially representative of one or more anatomical structures.

Abstract: Background information is subtracted from projection data in medical diagnostic imaging. The background is removed using data acquired in a single rotational sweep of a C-arm. The removal may be by masking out a target, leaving the background, in the data as constructed into a volume. For subtraction, the masked background information is projected to a plane and subtracted from the data representing the plane.

Abstract: The left ventricle epicardium is estimated in medical diagnostic imaging. C-arm x-ray data is used to detect an endocardium at different phases. The detected endocardium at the different phases is compared to sample endocardiums at different phases. The sample endocardiums have corresponding sample epicadriums. The transformation between the most similar sample endocardium or endocardiums over time and the detected endocardium over time is applied to the corresponding sample epicardium or epicardiums. The transformed sample epicardium over time is the estimated epicardium over time for the C-arm x-ray data.

Abstract: A method for automatically assessing medical ultrasound (US) image usability, includes extracting one or more features from at least one part of a medical ultrasound image, calculating for each feature a feature score for each pixel of the at least one part of the ultrasound image, and classifying one or more image pixels of the at least one part as either usable or unusable, based on a combination of feature scores for each pixel, where usable pixels have intensity values substantially representative of one or more anatomical structures.

Abstract: A method and system for adaptive discriminant learning and measurement fusion for image based catheter tracking is disclosed. An adaptive discriminant model is trained online based on a tracked object, such as a pigtail catheter tip, in at least one previous frame of a fluoroscopic image sequence. The object is tracked in the current frame of the fluoroscopic image sequence based at least on the adaptive discriminant model trained online. The object may be tracked in the current frame based on a fusion of three types of measurement models including the adaptive discriminant model trained online, an object detection model trained offline, and an online appearance model.

Abstract: A method and system for multi-part left atrium (LA) segmentation in a C-arm CT volume is disclosed. Multiple LA part models, including an LA chamber body mesh, an appendage mesh, a left inferior pulmonary vein (PV) mesh, a left superior PV mesh, a right inferior PV mesh, and a right superior PV mesh, are segmented in a 3D volume. The LA chamber body mesh and the appendage mesh may be segmented as a combined object and the PV meshes may be segmented subject to a statistical shape constraint. A consolidated LA mesh is generated from the segmented LA part models.

Abstract: A method and system for contrast inflow detection in a sequence of fluoroscopic images is disclosed. Vessel segments are detected in each frame of a fluoroscopic image sequence. A score vector is determined for the fluoroscopic image sequence based on the detected vessel segments in each frame of the fluoroscopic image sequence. It is determined whether a contrast agent injection is present in the fluoroscopic image sequence based on the score vector. If it is determined that a contrast agent injection is present in the fluoroscopic image sequence, a contrast inflow frame, at which contrast agent inflow begins, is detected in the fluoroscopic image sequence based on the score vector.

Abstract: A system and method for regression-based segmentation of the mitral valve in 2D+t cardiac magnetic resonance (CMR) slices is disclosed. The 2D+t CMR slices are acquired according to a mitral valve-specific acquisition protocol introduced herein. A set of mitral valve landmarks is detected in each 2D CMR slice and mitral valve contours are estimated in each 2D CMR slice based on the detected landmarks. A full mitral valve model is reconstructed from the mitral valve contours estimated in the 2D CMR slices using a trained regression model. Each 2D CMR slice may be a cine image acquired over a full cardiac cycle. In this case, the segmentation method reconstructs a patient-specific 4D dynamic mitral valve model from the 2D+t CMR image data.

Abstract: A method and system for detecting a virtual electrode (VE) on a coronary sinus (CS) catheter in a fluoroscopic image sequence is disclosed. User inputs indicating locations of CS catheter electrodes and a location of a VE are received. A catheter electrode model and a VE part model is initialized in a first frame of the fluoroscopic image sequence. The VE is tracked by detecting electrode position candidates and catheter body point candidates in the subsequent frames of the fluoroscopic image sequence using respective trained detectors, tracking the catheter electrode model in the subsequent frames based on the detected electrode position candidates, generating VE part hypotheses in the subsequent frames based on detection of the most proximal electrode (MPE) in each subsequent frame, calculating a probability score for each of the VE part hypotheses, and selecting an VE part hypothesis with the highest probability score.

Abstract: A method and system for estimating 3D cardiac motion from a single C-arm angiography scan is disclosed. An initial 3D volume is reconstructed from a plurality of 2D projection images acquired in a single C-arm scan. A static mesh is extracted by segmenting an object in the initial 3D volume. The static mesh is projected to each of the 2D projection images. A cardiac phase is determined for each of the 2D projection images. A deformed mesh is generated for each of a plurality of cardiac phases based on a 2D contour of the object and the projected mesh in each of the 2D projection images of that cardiac phase.

Abstract: A method for tracking a contour in cardiac phase contrast flow magnetic resonance (MR) images includes estimating a global translation of a contour in a reference image in a time sequence of cardiac phase contrast flow MR images to a contour in a current image in the time sequence of images by finding a 2-dimensional translation vector that maximizes a similarity function of the contour in the reference image and the current image calculated over a bounding rectangle containing the contour in the reference image, estimating an affine transformation of the contour in the reference image to the contour in the current image, and performing a constrained local deformation of the contour in the current image.

Abstract: A method for registering digital renal perfusion images includes selecting a volume of interest (VOI) containing a kidney in a reference renal perfusion image, computing 3D intensity gradients for a plurality of points in the VOI of the reference renal perfusion image, computing 3D intensity gradients for a plurality of points in a search window of a current renal perfusion image, and maximizing a similarity measure between the reference image VOI and the current image search window, where the similarity measure is a function of the 3D intensity gradients computed for the reference image and the current image.

Abstract: A computer readable medium is provided embodying instructions executable by a processor to perform a method for sparse volume segmentation for 3D scan of a target. The method including learning prior knowledge, providing volume data comprising the target, selecting a plurality of key contours of the image of the target, building a 3D spare model of the image of the target given the plurality of key contours, segmenting the image of the target given the 3D sparse model, and outputting a segmentation of the image of the target.