128 results about "Ultrasonic cardiography" patented technology

A method of and apparatus for transmitting video images allows a viewer to receive at a receiving display device, all or a selected portion of a video stream of frames, in a storage-efficient format from a transmitting device and view the received video stream of frames before the transmission is complete. The video system also allows a viewer to receive at the receiving device, all or a selected portion of a video stream of frames, in a high-resolution format, by marking sections of interest within the received stream of frames in the storage-efficient format and requesting enhancement of those marked sections of interest. This apparatus preferably includes a source device, a transmitting device and at least one receiving device. Preferably, the transmitting device and the receiving device communicate over a network such as the Internet Protocol network. Alternatively, the transmitting device and the receiving device communicate over any appropriate data network. The transmitting device transmits the video images to the receiving device for display and storage at the receiving device. The receiving device is also capable of communicating with the transmitting device while simultaneously receiving video images. The source device is preferably a medical test device such as an ultrasound, a sonogram, an echocardiogram, and the like. Alternatively, the source device can be any video capture or storage device capable of sourcing a stream of video frames.

A method for tracking motion and shape changes of a deformable model in a volumetric image sequence. The method is operable to predict the surface of a space from a 3D image, such as cardiac structures from a 3D ultrasound. The shape and position of a deformable model is predicted for each frame of an ultrasound image. Edge detection is then performed for each predicted point on the deformable model perpendicular to the model surface. The distances between the predicted and measured edges for the deformable model are measurements for a Kalman filter. The measurements are coupled with noise values that specify the spatial uncertainty of the edge detection. The measurement data are subsequently summed together in information space and combined with the prediction in the Kalman filter to estimate the position and deformation for the deformable model. The deformable model is then updated to generate an updated surface model.

A method of and system for transmitting video images preferably allows a specially trained individual to remotely supervise, instruct, and observe administration of medical tests conducted at remote locations. This system preferably includes a source device, a transmitting device, and at least one remote receiving device. The transmitting device, and the remote receiving device communicate over a network such as any appropriate data network. The transmitting device transmits the video images to the remote receiving device either for live display from the source device or for pre-recorded display from a video recorder device. The remote receiving device is also capable of communicating with the transmitting device while simultaneously receiving video images to provide remote control. The source device is preferably a medical test device such as an ultrasound, a sonogram, an echocardiogram, an angioplastigram, and the like. The transmitting device captures the video images in real-time from the source device and compresses these video images utilizing a compression method prior to transmitting data representing the video images to the remote receiving device. The compressor and compression method preferably utilize data structures comprising line number data structures and the repeat data structures. Remote users utilizing the remote receiving devices are capable of viewing a live stream of video and remotely controlling a number of parameters relating to the source device and the transmitting device. Such parameters include compression method, image quality, storage of the video images on the transmitting device, manipulating and controlling the source device, and the like.

In heart failure (HF) patients diagnosed according to the New York Heart Association (NYHA) rating scale as either Class III or Class IV, with QRS duration ≧120 ms, left ventricular (LV) EF≦35% (when in sinus rhythm), cardiac resynchronization therapy (CRT) can predict sustained improvement in at least LV structure and function. The knowledge of aetiology of a subject's HF status and of a few simple echocardiographic characteristics provides useful information as to whether such patients and undergo significant and beneficial reverse remodelling of the LV in particular and, in the long term can be expected to experience an improvement in all-cause mortality, for example such patients can be reasonably expected to survive and enjoy a relatively enhanced quality of life (QOL). A patient who qualifies according to the invention can be termed a reverse remodelling responder (RRR) or the like.

A computer vision pipeline is provided for fully automated interpretation of cardiac function, using a combination of machine learning strategies to enable building a scalable analysis pipeline for echocardiogram interpretation. Videos from patients with heart failure can be analyzed and processed as follows: 1) preprocessing of echo studies; 2) convolutional neural networks (CNN) processing for view identification; 3) segmentation of chambers and delineation of cardiac boundaries using CNNs; 4); particle tracking to compute longitudinal strain; and 5) targeted disease detection.

The invention discloses a method for establishing image data through nuclear magnetic resonance and belongs to the technical field of medical images. The method comprises the following steps that nuclear magnetic resonance image sequential data of a target zone in the first pass process of a contrast agent are extracted; registration is conducted on an image sequence, so that displacement deviation of the target zone in the image sequence is eliminated; the myocardium outline in the target zone of an image is segmented, so that an inner outline and an outer outline of the myocardium are obtained; quantitative analysis is conducted, the myocardium in the image is segmented into a plurality of partial zones according to an ultrasonic cardiogram seventeen-segmentation division method along the outline, a pixel mean value of each zone is calculated, and a data curve of the relation of the signal intensity and time is obtained. The nuclear magnetic resonance image data are collected, image registration is conducted, the myocardium outline image data are obtained through segmentation, quantitative analysis is conducted, a data model and an accurate data analysis platform are established, and therefore waste of resources is avoided.

The invention provides a system and device for improving the segmentation accuracy of left ventricles of multiple heart views based on deep learning, and the system comprises a data collection modulewhich is configured to collect the image data of ultrasonic cardiograms of a plurality of different views to form an original image data set, and collecting a to-be-processed echocardiogram as to-be-segmented data; a preprocessing module which is configured to preprocess the original image data set to form an experimental data set; a training module which is configured to construct a deep neural network training model, input the experimental data set into the training model for training, and when a loss function value in the training model is not reduced any more, stop the training of the training model and save model parameters; a data processing module which is configured to input a to-be-processed echocardiogram into the training module for storing the model parameters to obtain an endocardial and epicardial segmentation result. According to the invention, the training precision of processing different ventricular images is improved, and then the heart view segmentation precision isimproved.

The present invention concerns an optical transesophageal echocardiography probe (OPTEE) having an optical fiber bundle, a suction channel and light channels for illumination, wherein the OPTEE has a circumference along its distal tip that allows both safe insertion and insures the stability of the probe. The probe tip is generally circular in circumference, but levels off to a flat surface for a portion of the circumference, and is provided with beveled edges and corner throughout so that there are no sharp edges to traumatize the patient. The invention also concerns an optically-recessed OPTEE comprising an optical transesophageal probe comprising a longitudinally extending main body having an outer surface and a substantially circular cross-section and a distal portion having an outer surface and a distal tip, wherein an optical bundle having a distal tip is positioned on the outer surface of the main body and the outer surface of the distal portion and the distal tip of the optical bundle does not extend as far as the distal tip of the distal portion.

Methods and systems for segmentation in echocardiography are provided. One method includes obtaining echocardiographic images and defining a search space within the echocardiographic images using a pair of one-dimensional (1D) profiles. The method also includes using an energy based function constrained by non-local temporal priors within the defined search space to automatically segment a contour of a cardiac structure with the 1D profiles.

An intracardiac imaging system 10 configured to display electrode visualization elements within an intracardiac echocardiography image 12 where the electrode visualization elements represent intracardiac electrodes in close proximity to the plane of the image 12. The system 10 further allows cross sections of tissue structures embodied in intracardiac echocardiography images 12 to be modeled within a visualization, navigation, or mapping system 20 when automatically segmented to generate shell elements 36 for modifying the modeled tissue structures.