摘要:
A method and system for providing detecting and classifying coronary stenoses in 3D CT image data is disclosed. Centerlines of coronary vessels are extracted from the CT image data. Non-vessel regions are detected and removed from the coronary vessel centerlines. The cross-section area of the lumen is estimated based on the coronary vessel centerlines using a trained regression function. Stenosis candidates are detected in the coronary vessels based on the estimated lumen cross-section area, and the significant stenosis candidates are automatically classified as calcified, non-calcified, or mixed.
摘要:
A method and system for physiological image registration and fusion is disclosed. A physiological model of a target anatomical structure in estimated each of a first image and a second image. The physiological model is estimated using database-guided discriminative machine learning-based estimation. A fused image is then generated by registering the first and second images based on correspondences between the physiological model estimated in each of the first and second images.
摘要:
A method and system for coronary artery detection in 3D cardiac volumes is disclosed. The heart chambers are segmented in the cardiac volume, and an initial estimation of a coronary artery is generated based on the segmented heart chambers. The initial estimation of the coronary artery is then refined based on local information in the cardiac volume in order to detect the coronary artery in the cardiac volume. The detected coronary artery can be extended using 3D dynamic programming.
摘要:
A method and system for left ventricle (LV) detection in 2D magnetic resonance imaging (MRI) images is disclosed. In order to detect the LV in a 2D MRI image, a plurality of LV candidates are detected, for example using marginal space learning (MSL) based detection. Candidates for distinctive anatomic landmarks associated with the LV are then detected in the 2D MRI image. In particular, apex candidates and base candidates are detected in the 2D MRI image. One of the LV candidates is selected as a final LV detection result using component-based voting based on the detected LV candidates, apex candidates, and base candidates.
摘要:
A method and system for left ventricle (LV) endocardium surface segmentation using constrained optimal mesh smoothing is disclosed. The LV endocardium surface in the 3D cardiac volume is initially segmented in a 3D cardiac volume, such as a CT volume, resulting in an LV endocardium surface mesh. A smoothed LV endocardium surface mesh is generated by smoothing the LV endocardium surface mesh using constrained optimal mesh smoothing. The constrained optimal mesh smoothing determines an optimal adjustment for each point on the LV endocardium surface mesh by minimizing an objective function based at least on a smoothness measure, subject to a constraint bounding the adjustment for each point. The adjustment for each point can be constrained to prevent adjustments inward toward the blood pool in order to ensure that the smoothed LV endocardium surface mesh encloses the entire blood pool.
摘要:
A method and system for left ventricle (LV) detection in 2D magnetic resonance imaging (MRI) images is disclosed. In order to detect the LV in a 2D MRI image, a plurality of LV candidates are detected, for example using marginal space learning (MSL) based detection. Candidates for distinctive anatomic landmarks associated with the LV are then detected in the 2D MRI image. In particular, apex candidates and base candidates are detected in the 2D MRI image. One of the LV candidates is selected as a final LV detection result by ranking the LV candidates based on the LV candidates, the apex candidates, and the base candidates using a trained ranking model.
摘要:
A method and system for intraoperative guidance in an off-pump mitral valve repair procedure is disclosed. A plurality of patient-specific models of the mitral valve are generated, each from pre-operative image data obtained using a separate imaging modality. The pre-operative image data from the separate imaging modalities are fused into a common coordinate system by registering the plurality of patient-specific models. A model of the mitral valve is estimated in real-time in intraoperative image data using a fused physiological prior resulting from the registering of the plurality of patient-specific models.
摘要:
A method and system for left ventricle (LV) endocardium surface segmentation using constrained optimal mesh smoothing is disclosed. The LV endocardium surface in the 3D cardiac volume is initially segmented in a 3D cardiac volume, such as a CT volume, resulting in an LV endocardium surface mesh. A smoothed LV endocardium surface mesh is generated by smoothing the LV endocardium surface mesh using constrained optimal mesh smoothing. The constrained optimal mesh smoothing determines an optimal adjustment for each point on the LV endocardium surface mesh by minimizing an objective function based at least on a smoothness measure, subject to a constraint bounding the adjustment for each point. The adjustment for each point can be constrained to prevent adjustments inward toward the blood pool in order to ensure that the smoothed LV endocardium surface mesh encloses the entire blood pool.
摘要:
A method and system for virtual percutaneous valve implantation is disclosed. A patient-specific anatomical model of a heart valve is estimated based on 3D cardiac medical image data and an implant model representing a valve implant is virtually deployed into the patient-specific anatomical model of the heart valve. A library of implant models, each modeling geometrical properties of a corresponding valve implant, is maintained. The implant models maintained in the library are virtually deployed into the patient specific anatomical model of the heart valve to select an implant type and size and deployment location and orientation for percutaneous valve implantation.
摘要:
A method and apparatus for detecting 3D anatomical objects in medical images using constrained marginal space learning (MSL) is disclosed. A constrained search range is determined for an input medical image volume based on training data. A first trained classifier is used to detect position candidates in the constrained search range. Position-orientation hypotheses are generated from the position candidates using orientation examples in the training data. A second trained classifier is used to detect position-orientation candidates from the position-orientation hypotheses. Similarity transformation hypotheses are generated from the position-orientation candidates based on scale examples in the training data. A third trained classifier is used to detect similarity transformation candidates from the similarity transformation hypotheses, and the similarity transformation candidates define the position, translation, and scale of the 3D anatomic object in the medical image volume.