Abstract: A post-task-completion retention period for which a computing resource is to be retained, without de-activating the resource, on behalf of a set of requesters of machine learning tasks is determined at a machine learning service. A first task, identified at the service prior to expiration of the retention period at a first computing resource at which a second task has completed, is initiated at the first computing resource. In response to obtaining an indication of a third task and determining that a threshold criterion associated with the retention period satisfies a criterion, the third task is initiated at an additional computing resource. The additional computing resource is de-activated after the third task completes, without waiting for the retention period to expire.

Abstract: Parameters of a pool of computing resources to be utilized for machine learning tasks from a set of entities are stored, including a category of the computing resources, and a post-task-completion retention period during which, after completion of a task, at least a portion of data stored at the resource is not to be deleted. A compute instance of the pool is assigned to a task requested from the set of entities after determining that one or more configuration settings of the instance satisfy a preference indicated in the request for the task, and that the retention period of the instance relative to a completion of an earlier task on the instance has not expired. A result of the task is stored.

Abstract: Techniques are provided for guidance for navigation and positioning of intravascularly delivered devices. A medical navigation system includes a delivery device comprising a catheter, an intravascularly delivered device configured to be releasably disposed in the catheter for deployment at a target site of a patient, and a navigation computer system. The intravascularly delivered device includes a plurality of electrodes including at least one indicator electrode and at least one reference electrode configured to not contact tissue when the intravascularly delivered device is deployed at the target site. The navigation computer system is configured to be electrically coupled with the plurality of electrodes.

Abstract: A heart valve repair clip includes a stud, two arms operatively coupled to the stud and capable of transitioning between an open condition and a closed condition, and includes an indicator coupled to each of the two arms and moveable relative thereto.

Abstract: An integrated imaging and device deployment platform and method may include a catheter, at least one imaging unit, at least one deployment unit, and at least one device configured to be deployed by the at least one deployment unit. The integrated imaging and device deployment platform facilitates improved navigation and deployment of a therapeutic or medical device by providing the at least one imaging unit proximate the deployment unit. Information generated from the at least one imaging unit may be utilized with additional imaging modalities to provide improved imaging and delivery of devices while reducing use of X-ray radiation and contrast injection.

Abstract: An integrated imaging and device deployment platform and method may include a catheter, at least one imaging unit, at least one deployment unit, and at least one device configured to be deployed by the at least one deployment unit. The integrated imaging and device deployment platform facilitates improved navigation and deployment of a therapeutic or medical device by providing the at least one imaging unit proximate the deployment unit. Information generated from the at least one imaging unit may be utilized with additional imaging modalities to provide improved imaging and delivery of devices while reducing use of X-ray radiation and contrast injection.

Abstract: Methods and systems for passively detecting stable cavitation and enhancing stable cavitation during sonothrombolysis are provided. The method of passively detecting stable cavitation includes providing a determined level of ultrasonic energy and detecting a scattered level of ultrasonic energy. The system for inducing and passively detecting stable cavitation includes a dual-element annular transducer array configured to provide a fundamental ultrasonic frequency and to detect an ultrasonic frequency that is a derivative of the fundamental frequency. The method of enhancing stable cavitation includes administering a nucleating agent and a thrombolytic agent to a treatment zone, providing a determined level of ultrasonic energy, and detecting a scattered level of ultrasonic energy.

Abstract: Spatially distinct Spectral Doppler information is acquired. Spatially distinct transmit beams are formed at a same time or in parallel. One or more receive beams are formed in response to each transmit beam, providing samples for a plurality of laterally spaced locations. A spectrum is determined for each of a plurality of spatial locations. In another approach, samples are acquired for different regions at different times. The scanning for each region is interleaved based on the anatomic operation. Since spectral estimation relies on a time-continuous series of transmission and reception, the scanning for a region occurs over a sufficient period for spectral estimation before the scanning for a different region occurs. By using anatomic operation, sufficient time is provided for spectral estimation. Due to anatomic operation, different regions are associated with flow at different times.

Abstract: Methods and systems for passively detecting stable cavitation and enhancing stable cavitation during sonothrombolysis are provided. The method of passively detecting stable cavitation includes providing a determined level of ultrasonic energy and detecting a scattered level of ultrasonic energy. The system for inducing and passively detecting stable cavitation includes a dual-element annular transducer array configured to provide a fundamental ultrasonic frequency and to detect an ultrasonic frequency that is a derivative of the fundamental frequency. The method of enhancing stable cavitation includes administering a nucleating agent and a thrombolytic agent to a treatment zone, providing a determined level of ultrasonic energy, and detecting a scattered level of ultrasonic energy.

Abstract: Volumetric quantification is provided in medical diagnostic ultrasound. By acquiring both B-mode and color flow data without stitching or acquiring in real-time at tens of volumes a second, more reliable quantification may be provided. Using multiple regions of interest in a volume may allow for more accurate and/or complete flow information, such as averaging flow from different locations in the same structure (e.g., use preservation of mass to acquire multiple measures of the same flow).

Abstract: Velocities are unaliased using conditional random fields. To constrain the energy minimization function, a global term includes a measure of a level of aliasing. In one example, the measure of the level of aliasing is based on a change in volume, such as the volume of the left ventricle. The unaliasing is performed along one or more surfaces, such as surfaces intersecting the mitral annulus and the left ventricle outflow tract. The anatomy used is identified and/or tracked using one or more machine-learnt detectors. Both B-mode and velocity information may be used for detecting the anatomy.

Abstract: A mitral valve is detected in transthoracic echocardiography. The ultrasound transducer is positioned against the chest of the patient rather than being inserted within the patient. While data acquired from such scanning may be noisier or have less resolution, the mitral valve may still be automatically detected. Using both B-mode data representing tissue as well as flow data representing the regurgitant jet, the mitral valve may be detected automatically with a machine-learnt classifier. A series of classifiers may be used, such as determining a position and orientation of a valve region with one classifier, determining a regurgitant orifice with another classifier, and locating mitral valve anatomy with a third classifier. One or more features for some of the classifiers may be calculated based on the orientation of the valve region.

Abstract: Flow estimation is provided. The flow is predicted. A mathematical, logic, machine learning or other model is used to predict flow. For example, the boundary conditions associated with a previous flow, the previous flow, and current boundary conditions are used to predict the current flow. The current flow is corrected using the predicted flow. Velocities may be unaliased based on the predicted flow. The predicted flow may replace the current flow. Prediction may additionally or alternatively be used in determination of lateral or elevational flow.

Abstract: A method quantifies cardiac volume flow for an imaging sequence. The method includes receiving data representing three-dimensions and color Doppler flow data over a plurality of frames, constructing a ventricular model based on the data representing three-dimensions for the plurality of frames, the ventricular model including a sampling plane configured to measure the cardiac volume flow, computing volume flow samples based on the sampling plane and the color Doppler flow data, and correcting the volume flow samples for aliasing based on volumetric change in the ventricular model between successive frames of the plurality of frames.

Abstract: A mitral valve is detected in transthoracic echocardiography. The ultrasound transducer is positioned against the chest of the patient rather than being inserted within the patient. While data acquired from such scanning may be noisier or have less resolution, the mitral valve may still be automatically detected. Using both B-mode data representing tissue as well as flow data representing the regurgitant jet, the mitral valve may be detected automatically with a machine-learnt classifier. A series of classifiers may be used, such as determining a position and orientation of a valve region with one classifier, determining a regurgitant orifice with another classifier, and locating mitral valve anatomy with a third classifier. One or more features for some of the classifiers may be calculated based on the orientation of the valve region.

Abstract: Pressure-volume analysis is provided in medical diagnostic ultrasound imaging. The heart of a patient is scanned multiple times during a given cycle. B-mode and flow information are obtained for various times. The flow information is used to estimate pressure over time. A reference pressure, such as from a cuff, may be used to calibrate the pressure waveform. The B-mode information is used to determine a heart volume over time, such as a left ventricle volume over time. The heart volume over time and pressure over time are plotted, providing a pressure-volume loop. The pressure-volume loop is determined non-invasively with ultrasound.

Abstract: Velocities are unaliased using conditional random fields. To constrain the energy minimization function, a global term includes a measure of a level of aliasing. In one example, the measure of the level of aliasing is based on a change in volume, such as the volume of the left ventricle. The unaliasing is performed along one or more surfaces, such as surfaces intersecting the mitral annulus and the left ventricle outflow tract. The anatomy used is identified and/or tracked using one or more machine-learnt detectors. Both B-mode and velocity information may be used for detecting the anatomy.

Abstract: Spatially distinct Spectral Doppler information is acquired. Spatially distinct transmit beams are formed at a same time or in parallel. One or more receive beams are formed in response to each transmit beam, providing samples for a plurality of laterally spaced locations. A spectrum is determined for each of a plurality of spatial locations. In another approach, samples are acquired for different regions at different times. The scanning for each region is interleaved based on the anatomic operation. Since spectral estimation relies on a time-continuous series of transmission and reception, the scanning for a region occurs over a sufficient period for spectral estimation before the scanning for a different region occurs. By using anatomic operation, sufficient time is provided for spectral estimation. Due to anatomic operation, different regions are associated with flow at different times.

Abstract: Methods and systems for passively detecting stable cavitation and enhancing stable cavitation during sonothrombolysis are provided. The method of passively detecting stable cavitation includes providing a determined level of ultrasonic energy and detecting a scattered level of ultrasonic energy. The system for inducing and passively detecting stable cavitation includes a dual-element annular transducer array configured to provide a fundamental ultrasonic frequency and to detect an ultrasonic frequency that is a derivative of the fundamental frequency. The method of enhancing stable cavitation includes administering a nucleating agent and a thrombolytic agent to a treatment zone, providing a determined level of ultrasonic energy, and detecting a scattered level of ultrasonic energy.

Abstract: A method quantifies cardiac volume flow for an imaging sequence. The method includes receiving data representing three-dimensions and color Doppler flow data over a plurality of frames, constructing a ventricular model based on the data representing three-dimensions for the plurality of frames, the ventricular model including a sampling plane configured to measure the cardiac volume flow, computing volume flow samples based on the sampling plane and the color Doppler flow data, and correcting the volume flow samples for aliasing based on volumetric change in the ventricular model between successive frames of the plurality of frames.