Siemens Aktiengesellschaft

Siemens Medical Solutions Usa, Inc.

Agency for Science, Technology and Research

Ying Sun

Marie-Pierre Jolly

Jens Gühring

Gareth Funka-Lea

Leo John Grady

Peter Speier

Thomas J O'Donnell

Michaela Schmidt

Ravi Kumar

Carmel Hayes

Christine Lorenz

Nicolae Duta

José M F Moura

Wei Xiong

Wenyu Chen

Jierong Cheng

Ying Quan

Jordin D Green

Yusha Li

This invention relates to a method for training a neural network, comprising detecting a hole in each training image of a plurality of training images; transforming each training image into a transformed image, to suppress non-crack information in the training image; and training a neural network using the transformed images, to detect cracks in images (i.e. in objects in images).

Defect detection in image space

A method for automatically determining a field of view for performing a subsequent medical imaging study includes acquiring one or more preliminary images. A body mask is generated by thresholding the preliminary images and identifying a largest connected component. A boundary mask is obtained from the boundary of the generated body mask. A rectangular bounding box is fit to the obtained boundary mask. The rectangular bounding box is used as a field of view for performing a subsequent medical imaging study.

Automatic determination of field of view in cardiac MRI

A method for automatically localizing left ventricle in medical image data includes acquiring a sequence of three-dimensional medical images spanning a cardiac cycle. Each of the images includes a plurality of two-dimensional image slices, one of which is defined as a template slice. The template slice of each medical image of the sequence is automatically cropped to include the heart and a margin around the heart based on temporal variations between pixels of the template slice throughout the sequence of medical images. The template slice of each medical image of the sequence is automatically contoured to determine the endo-cardial and epi-cardial boundaries for at least the end-diastolic and end-systolic phases. Localization information is generated for the left ventricle based on the determined endo-cardial and epi-cardial boundaries for at least the end-diastolic and end-systolic phases.

Automatic localization of the left ventricle in cardiac cine magnetic resonance imaging

A method for detection of the position and orientation of the tip of a needle-like medical device inserted into a tissue of a patient using scanning apparatus. The method obtains a first scan of the tissue correlating the needle-like medical device with a plurality of needle-like templates, each one having a different angular orientation to obtain an feature image of the device; obtains eigenvalues and an eigenvector of image to obtain the angular orientation of an image plane for a subsequent scan; transforms the orientation of the device in the determined image plane into scanning system reference coordinates with the longitudinal axis of the needle like device having a predetermined orientations with respect to the reference coordinate system; and makes observations along each of a sequence of lines transverse to the longitudinal axis of the image of the device in the determined plane to detect the tip of the device.

Method for automatically determining an image plane having a biopsy device therein

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.

System and method for contour tracking in cardiac phase contrast flow MR images

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.

System and method for automatic registration of 4D (3D plus time) renal perfusion MRI data

A method for automatically generating a myocardial perfusion map from a sequence of magnetic resonance (MR) images includes determining a region of interest (ROI) in a reference frame selected from a time series of myocardial perfusion MR image slices, registering each image slice in the time series of slices to the reference frame to obtain a series of registered ROIs, and using the series of registered ROIs to segment endo- and epi-cardial boundaries of a myocardium in the ROI.

System and method for generating MR myocardial perfusion maps without user interaction

A method for automatically selecting a number of Gaussian modes for segmentation of a cardiac magnetic resonance (MR) image, including: identifying a left ventricle (LV) in a cardiac MR image slice; quantifying the LV blood pool; obtaining a mask for the LV blood pool; generating a ring mask for a myocardium of the LV from the LV blood pool mask; fitting three Gaussian modes to a histogram of the image slice to obtain a corresponding homogeneity image for the myocardium; computing a quality of fitting (QOF) measure for the three Gaussian modes based on the corresponding homogeneity image; repeating the fitting and computing steps for four and five Gaussian modes; and selecting the homogeneity image of the number of Gaussian modes with the largest QOF measure as the homogeneity image for processing.

Method and system for selecting the number of gaussian modes for the segmentation of cardiac magnetic resonance (MR) images

A system and method are provided for contrast-invariant registration of images, the system including a processor, an imaging adapter or a communications adapter for receiving an image data sequence, a user interface adapter for selecting a reference frame from the image sequence or cropping a region of interest (ROI) from the reference frame, a tracking unit for tracking the ROI across the image sequence, and an estimation unit for segmenting the ROI in the reference frame or performing an affine registration for the ROI; and the method including receiving an image sequence, selecting a reference frame from the image sequence, cropping a region of interest (ROI) from the reference frame, tracking the ROI across the image sequence, segmenting the ROI in the reference frame, and performing an affine registration for the ROI.

Contrast-invariant registration of cardiac and renal magnetic resonance perfusion images

A system and method for automatically determining the standard cardiac image views as defined by the American Heart Association from volumetric data of the chest including the heart. The system and method can be used by a health practitioner to quickly see the two dimensional views from which a diagnosis is generally made. The left ventricle is detected. Then the relative orientation of the right ventricle is determined and the standard cardiac views are determined.

Automatic determination of the standard cardiac views from volumetric data acquisitions

Motion of the heart during contrast enhancement is modeled at two hierarchical levels: global translation and local deformation. Large-scale, i.e., global, translational motion is identified using global template matching, while the local deformation of a portion of the object (e.g., the left ventricle where the object is a heart) is obtained using an adaptive local template matching scheme which adapts to the local edge distributions by varying the height and the width of the template as well as the location of the template followed by spatial regularization. To address the difficulty of rapid intensity changes across the image sequence as the contrast agent perfuse into the tissue, an edge-based similarity measure is used for template matching.

Nonrigid registration of cardiac perfusion MR images using adaptive local template matching

A method is provided for segmenting an image of interest of a left ventricle. The method includes determining a myocardium contour according to a graph cut of candidate endocardium contours, and a spline fitting to candidate epicardium contours in the absence of shape propagation. The method further includes applying a plurality of shape constraints to candidate endocardium contours and candidate epicardium contours to determine the myocardium contour, wherein a template is determined by shape propagation of a plurality of images in a sequence including the image of interest in the presence of shape propagation.

System and method for segmenting the left ventricle in a cardiac image

A system and method are provided for integrated registration of images, the system including a processor, a first registration portion for performing rough registration of an image, a first segmentation portion for performing segmentation of an object of interest in the image, a second registration portion for performing fine registration of the image, and a second segmentation portion for performing segmentation of structures of the object of interest in the image; and the method including receiving a sequence of images, selecting an image from the sequence, cropping a region of interest (ROI) from the selected image, performing rough registration of the cropped ROI, performing segmentation of an object of interest from the rough registered ROI, performing fine registration of the ROI, and performing segmentation of structures of the object of interest from the fine registered ROI.

Growing community of inventors

Singapore, Singapore

Ying Sun