123 results about "Ultrasonic cardiography" patented technology

The invention includes a novel method and system to achieve leaflet coaptation in a cardiac valve percutaneously by creation of neochordae to prolapsing valve segments. This technique is especially useful in cases of ruptured chordae, but may be utilized in any segment of prolapsing leaflet. The technique described herein has the additional advantage of being adjustable in the beating heart. This allows tailoring of leaflet coaptation height under various loading conditions using image-guidance, such as echocardiography. This offers an additional distinct advantage over conventional open-surgery placement of artificial chordae. In traditional open surgical valve repair, chord length must be estimated in the arrested heart and may or may not be correct once the patient is weaned from cardiopulmonary bypass. The technique described below also allows for placement of multiple artificial chordae, as dictated by the patient's pathophysiology.

A method for relating to each other cardiovascular and sleep disordered breathing conditions of a patient. The patient's heart rate and/or detailed echocardiogram data is monitored and recorded continuously or periodically together with sleep disordered breathing information on similar time scales. Changes in the patient's heart rate associated with changes in sleep disordered breathing can then be observed. More specifically, positive airway pressure at therapeutic levels for treatment of sleep disordered breathing is applied while events associated with the treatment of the patient's sleep disordered breathing are detected and recorded. At the same time, information concerning the cardiovascular condition of the patient is stored and the stored information concerning the cardiovascular condition of the patient and the recorded events associated with the treatment of the patient's sleep disordered breathing are related to each other.

The present invention thus provides a simple and automatic method for determining an optimal AV interval and/or range of AV intervals for, in an exemplary embodiment, LV-only pacing. Such a method provides significant advantages for patients while reducing burdens related to post-implant follow-up by clinicians in that it greatly reduces the need for doing echocardiographic-based AV interval optimization procedures as well as providing a way to dynamically optimize AV intervals as the patient moves about their activities of daily living (ADL).

An echocardiogram report generation method and system are disclosed for creating a complete medical report describing an echocardiogram without dictation, transcription or typing. The report is tailored to describe an individual patient and generated in complete grammatically complex sentences in response to the user's input with a text report that is complete and understandable for a primary care physician. The method and system provides the user the parallel options of an anatomical structure approach and a disease-specific approach in order to amplify the description of the echocardiogram in specific areas and give a more meaningful report. The echo report generated by the method and system creates a table of measurements and calculations in compact form, omitting any data fields not used. The method and system guides the user through the various areas of the heart which merit comment on the report and provides clear color coded segments of the heart muscle and provides several heart segment classifications so that the user can use his favored classification scheme. Diagnostic possibilities are provided for inclusion in the report conclusions.

Determining an optimal atrioventricular interval is of interest for proper delivery of cardiac resynchronization therapy. Although device optimization is gradually and more frequently being performed through a referral process with which the patient undergoes an echocardiographic optimization, the decision of whether to optimize or not is still generally reserved for the implanting physician. Recent abstracts have suggested a formulaic approach for setting A-V interval based on intrinsic electrical sensing, that may possess considerable appeal to clinicians versus a patient average nominal A-V setting of 100 ms. The present invention presents a methods of setting nominal device settings based on entering patient cardiac demographics to determine what A-V setting may be appropriate. The data is based on retrospective analysis of the MIRACLE trial to determine what major factors determined baseline A-V settings.

Transesophageal echocardiography is implemented using a miniature transversely oriented transducer that is preferably small enough to fit in a 7.5 mm diameter probe, and most preferably small enough to fit in a 5 mm diameter probe. Signal processing techniques improve the depth of penetration to the point where the complete trans-gastric short axis view of the left ventricle can be obtained, despite the fact that the transducer is so small. The reduced diameter of the probe (as compared to prior art probes) reduces risks to patients, reduces or eliminates the need for anesthesia, and permits long term direct-visualization monitoring of patients' cardiac function.

Acute and chronic heart disease is treated using a rational, multi-tier approach. A patient is pretreated with growth factor proteins or gene therapy, followed by the administration of adult stem cells. The progress of treatment is continuously monitored by echo-cardiogram with growth factor treatment and/or stem cell administration adjusted according to the results of the echo-cardiogram or clinical status of the patient. Heart disease is also treated by a method that comprises administration of a therapeutically effective amount of a growth factor protein by oral inhalation therapy.

The invention relates to a method and device for calculating ultrasonic cardiogram cardiac parameters and measuring myocardial strain. A trained neural network is employed for executing the processingof the method, and the processing at least comprises: the classification of a cardiac ultrasonic video to obtain a section classification result; image segmentation of the section classification result to obtain a segmentation result; and acquisition of cardiac parameters and myocardial strain according to the segmentation result. In embodiments of the invention, automatic section classificationprocessing and image segmentation are carried out on the cardiac ultrasonic video through the trained neural network, and the measurement results of the cardiac parameters and the myocardial strain are further automatically obtained, so the workload of doctors is effectively reduced, and working efficiency is improved.

A support device for holding a transesophageal echocardiography probe is disclosed, the device comprising a liner component forming an interior portion and an exterior portion, the interior portion of the liner configured to receive the transesophageal echocardiography probe therein; a base component forming a support region having a support surface, the support region of the base component configured to receive the liner component therein; and an attachment component in connection with the base component, the attachment component configured to attach the base component to a support structure. A method for holding a transesophageal echocardiography probe is disclosed, the method comprising attaching an anchor portion to a support structure so as to attach a base portion to the support structure; and securing a handle of the transesophageal echocardiography probe and a liner in the base portion by positioning a cord of the transesophageal echocardiography probe through the slot of the base portion and positioning the handle into a top end of the base portion with a liner substantially surrounding the handle.

Techniques for providing expert instruction in interpreting outputs of a test instrument to a student who is at a location remote from the expert. The student makes outputs from the test instrument and an interpretation of the outputs available to an expert via a network and receives a commented and graded response in return. The outputs, the interpretation, and the response may be made available in real time or in non-real time. In the non-real-time embodiment, the student makes his interpretation by selecting from menus of possible observations, the expert does the same, and the two interpretations are automatically compared to produce the comments and grade for the response. One application of the invention is teaching echocardiography.

The present invention relates to methods for selecting racehorse candidates. Provided herein are methods for increasing the likelihood of selecting candidates that will be high earners, while reducing the likelihood of selecting candidates that will be low carners, on the basis of certain cardiac measurements.

The present invention relates to compounds of Formula (Ia) and pharmaceutical compositions thereof that modulate the activity of the beta-3 adrenergic receptor. Compounds of the present invention and pharmaceutical compositions thereof are directed to methods useful in the treatment of a beta-3 adrenergic receptor-mediated disorder, such as, heart failure; cardiac performance in heart failure; mortality, reinfarction, and/or hospitalization in connection with heart failure; acute heart failure; acute decompensated heart failure; congestive heart failure; severe congestive heart failure; organ damage associated with heart failure (e.g., kidney damage or failure, heart valve problems, heart rhythm problems, and/or liver damage); heart failure due to left ventricular dysfunction; heart failure with normal ejection fraction; cardiovascular mortality following myocardial infarction; cardiovascular mortality in patients with left ventricular failure or left ventricular dysfunction; left ventricular failure; left ventricular dysfunction; class II heart failure using the New York Heart Association (NYHA) classification system; class III heart failure using the New York Heart Association (NYHA) classification system; class IV heart failure using the New York Heart Association (NYHA) classification system; LVEF<40% by radionuclide ventriculography; LVEF≤35% by echocardiography or ventricular contrast angiography; and conditions related thereto.

The invention discloses a mitral valve opening area detection method, system and device based on artificial intelligence. The method comprises the steps that a two-dimensional section video reflectinga mitral valve structure in an ultrasonic cardiogram of a detection object is acquired; inputting the two-dimensional section video into a trained deep learning classification model, and obtaining aprediction value of the two-dimensional section video containing mitral valve stenosis image features; if the prediction value meets a preset condition, inputting the heart tip four-cavity heart mitral valve continuous Doppler frequency spectrum section image of the detection object into an image segmentation network model, and obtaining a frequency spectrum oscillogram corresponding to the section image; and predicting the mitral valve opening area according to the frequency spectrum oscillogram. According to the method, the system and the equipment, the accuracy and the consistency of ultrasonic detection are greatly improved.

There is provided a computer-implemented method for analysing echocardiograms, the method comprising: obtaining (302) a plurality of pairs of consecutive echocardiograms for a plurality of subjects from a database (200), each echocardiogram having an associated indication of the content of the echocardiogram; analysing (304) each pair of consecutive echocardiograms to determine an associated class, the class indicating whether there is a change or no change between the consecutive echocardiograms in the pair; for each pair of consecutive echocardiograms, determining (306) an abstract representation of each echocardiogram by performing one or more convolutions and/or reductions on the echocardiograms in the pair, the abstract representation comprising one or more features indicative of the class of the pair; and training (308) a predictive model to determine a class for a new pair of echocardiograms based on the abstract representations for the plurality of pairs of consecutive echocardiograms.

Techniques for providing expert instruction in interpreting outputs of a test instrument to a student who is at a location remote (103) from the expert. The student makes outputs from the test instrument and an interpretation of the outputs available to an expert (129) via a network (113) and the expert makes a comment available to the student in the same fashion. The outputs, the interpretation, and the comment may be made available in real time or in non-real time. In the non-real-time embodiment, the student makes his interpretation by selecting from menus of possible observations and the expert makes comments in the same fashion. Inputs from the menu selections are stored in a database record and a report is generated from the record. One application of the invention is teaching echocardiography.

The invention provides a deep learning atrial septal defect detection method and device, and the method comprises the steps: obtaining an ultrasonic cardiogram, preprocessing the ultrasonic cardiogram, and extracting a region of interest; carrying out feature extraction on the region of interest, and identifying a subsword process atrial septal frontal section, a subsword process atrial septal sagittal section, a cardiac apex four-cavity cardiac tangent plane, a low-position paracarpal four-cavity cardiac tangent plane and a paracarpal aorta short-axis tangent plane; detecting the minimum distance point of the atrial septal defect; segmenting heart structures of a subsword atrial septal frontal section, a subsword atrial septal sagittal section, a cardiac apex four-cavity cardiac tangent plane, a low paracardial four-cavity cardiac tangent plane and a paracardial aorta minor axis section to obtain segmentation results, the heart structures including a left atrium, a right atrium, a left ventricle, a right ventricle, an aorta and pulmonary arteries; and according to the segmentation results, filtering the detected minimum distance point bounding box of the atrial septal defect, andtaking the filtered result as an atrial septal defect detection result.

Artificial intelligence (AI) recognition of echocardiogram (echo) images by a mobile ultrasound device comprises receiving a plurality of the echo images captured by the ultrasound device, the ultrasound device including a display and a user interface (UI) that displays the echo images to a user, the echo images comprising 2D images and Doppler modality images of a heart. One or more neural networks process the echo images to automatically classify the echo images by view type. The view type of the echo images is simultaneously displayed in the UI of the ultrasound device along with the echo images. A report is generated showing the calculated measurements of features in the echo images. The report showing the calculated measurements is displayed on a display device.

Provided herewith are methods and apparatus for optimizing an atrioventricular (AV) pacing delay interval based upon ECG-based optimization is calculated as a linear function of P-wave duration, sensed PR (intrinsic) interval, sensed or paced QRS duration and heart rate. Since the relationship among these parameters is linear, once the coefficients are solved (which can be any value, including null) with reference to a known optimized AV interval (AVopt) such as from an echocardiographic study, an AVopt value can be dynamically adjusted in an ambulatory subject. The various combinations of values can be loaded into a look up table or calculated automatically. And, since some of the parameters do not typically change much over time they can be determined acutely and fed into the equation while the other values can be measured frequently. The parameter values can be measured by an implantable medical device such as a dual- or triple-chamber pacemaker.

The invention discloses a classification model training method and device and a coronary heart disease auxiliary screening method and device, and belongs to the technical field of medical treatment. The training method of the classification model comprises the following steps: preprocessing echocardiogram data and electronic medical record data to obtain a set number of associated effective imagedata and structured feature data so as to form a data set; and training a preset deep learning model through a set number of associated effective image data and structured feature data in the data setto construct a classification model. Through the classification model, the credibility of the screening result is improved, the accurate screening result can be provided for the examinee under the condition that the examinee is prevented from carrying out complex examination, so that the examinee decides whether to receive further cardiovascular examination or not according to the screening result, high examination cost caused by blind examination is avoided, the burden of a subject is reduced, the burden of a doctor can be reduced, and medical resources of a hospital are saved.