Abstract: A value indicative of an ejection fraction, EF, of a cardiac chamber of a heart is based on a temporal sequence of cardiac magnetic resonance, CMR, images of the cardiac chamber. A neural network system has an input layer configured to receive the temporal sequence of a stack of slices of the CMR images along an axis of the heart. The temporal sequence is one or multiple consecutive cardiac cycles of the heart. The neural network system has an output layer configured to output the value indicative of the EF based on the temporal sequence. The neural network system has interconnections between the input layer and the output layer and is trained with a plurality of datasets. Each of the datasets comprises an instance temporal sequence of the stack of slices of the CMR images along the axis over one or multiple consecutive cardiac cycles for the input layer and an associated instance value indicative of the EF for the output layer.

Abstract: CMR imaging is synthesized, and/or machine learning for a CMR imaging task uses synthetic sample generation. A machine-learned model generates synthetic samples. For example, the machine-learned model generates the synthetic samples in response to input of values for two or more parameters from the group of electrocardiogram (ECG), an indication of image style, a number of slices, a pathology, a measure of heart function, sample image, and/or an indication of slice position relative to anatomy. The indication of image style may be in the form of a latent representation, which may be used as the only input or one of multiple inputs. These inputs provide for better control over generation of synthetic samples, providing for greater variance and breadth of samples then used to machine train for a CMR task.

Abstract: A machine-learned model classifies disease, such as a CVD type or sub-type. After identifying a link between the pathology (e.g., CVD type or sub-type) and one or more functional and/or anatomical characteristics, machine learning is performed to learn to predict the functional and/or anatomical characteristics from medical data. The trained model is then adapted using few-shot learning to predict the class of disease. As a result of this few-shot learning approach, less training data may be needed for disease classification. A greater number of classifiers trained to classify a greater number of diseases may be created.

Abstract: A value indicative of an ejection fraction, EF, of a cardiac chamber of a heart is based on a temporal sequence of cardiac magnetic resonance, CMR, images of the cardiac chamber. A neural network system has an input layer configured to receive the temporal sequence of a stack of slices of the CMR images along an axis of the heart. The temporal sequence is one or multiple consecutive cardiac cycles of the heart. The neural network system has an output layer configured to output the value indicative of the EF based on the temporal sequence. The neural network system has interconnections between the input layer and the output layer and is trained with a plurality of datasets. Each of the datasets comprises an instance temporal sequence of the stack of slices of the CMR images along the axis over one or multiple consecutive cardiac cycles for the input layer and an associated instance value indicative of the EF for the output layer.

Abstract: The application relates to a computer implemented method for determining a basal and an apex plane in a set of Magnetic Resonance, MR, image slices of a heart, wherein the set of MR image slices comprises short axis views of the heart obtained over the heartbeat. The set of MR image slices is applied to a multitask deep learning artificial intelligence Model which is configured to identify a basal plane slice and an apex plane slice on the applied set of image slices, wherein the multitask deep learning artificial intelligence model is further configured to determine at least one further parameter of cardiac anatomy or of a cardiac function. A first output of the multitask deep learning artificial intelligence Model is determined as the apex plane slice and a second output as the basal plane slice. At least one further output of the multitask deep learning artificial intelligence Model is determined as the at least one further parameter of the cardiac anatomy or of the cardiac function.

Abstract: The application relates to a computer implemented method for determining a basal and an apex plane in a set of Magnetic Resonance, MR, image slices of a heart, wherein the set of MR image slices comprises short axis views of the heart obtained over the heartbeat. The set of MR image slices is applied to a multitask deep learning artificial intelligence Model which is configured to identify a basal plane slice and an apex plane slice on the applied set of image slices, wherein the multitask deep learning artificial intelligence model is further configured to determine at least one further parameter of cardiac anatomy or of a cardiac function. A first output of the multitask deep learning artificial intelligence Model is determined as the apex plane slice and a second output as the basal plane slice. At least one further output of the multitask deep learning artificial intelligence Model is determined as the at least one further parameter of the cardiac anatomy or of the cardiac function.

Abstract: A pressure wave system having a tubular member, a signal source, a sensor, and a source of noise, has a noise interference system employing one or more a lateral branches to cancel pressure noise, and/or amplify or filter the pressure wave signal. A related method generates the pressure wave signal, connects the lateral branch or branches to amplify or filter the signal and/or cancel noise from the system, and receives the signal or a response of the system to the signal. The lateral branches are simple pipe stubs or loops that can be made using ordinary piping components, or are more complex designs.

Abstract: A method moves a tube wave reflector in a well, generates a tube wave, receives a reflection, and determines the depth of one or more reflector locations from the elapsed time. Also, a method to locate a feature in a well deploys a bottom hole assembly (BHA), generates acoustic noise from the BHA, and autocorrelates to determine the BHA depth. Also, a system has a coiled tubing string to a BHA, a surface wave generator, a surface and/or distributed receiver, and a recorder to determine elapsed times between generation and receipt.

Abstract: A degradable diverter is placed in a flow path to divert fluid flow and exposed to degradation conditions, and after sensing a response to a pressure wave to determine the diverter has degraded, placing the well in service. Also, a treatment sequence is initiated according to a treatment schedule, a degradable diverter is placed in a flow path to divert treatment fluid, and, before completing the treatment, an interruption of the treatment schedule is followed by sensing a response to a pressure wave generated in the well to determine the status of the degradable diverter. Also, in a series of stages a degradable diverter is placed in a flow path, a response to a pressure wave is sensed to confirm placement, fluid flow is diverted, and the sequence repeated for subsequent stages.

Abstract: A method to locate fracture zones in a well by emitting tube waves from different emission locations, sensing responses from the fracture zones at different corresponding receiving locations, and analyzing the responses to map the location of the fracture zones. Also, a system to locate the fracture zones in a well with an emitter movable to emit tube waves at different emission locations in the well, a downhole receiver adapted to sense responses at respective receiving locations a fixed distance relative to the emission locations, and a recorder to track the time between the emission and the response for the different emission locations. Also a downhole tool equipped with a tube wave emitter, a tube wave response receiver in a tandem arrangement with the emitter, and a deployment system selected from wireline, coiled tubing, tractor, and combinations thereof to move the emitter and receiver together in tandem.

Abstract: A method moves a tube wave reflector in a well, generates a tube wave, receives a reflection, and determines the depth of one or more reflector locations from the elapsed time. Also, a method to locate a feature in a well deploys a bottom hole assembly (BHA), generates acoustic noise from the BHA, and autocorrelates to determine the BHA depth. Also, a system has a coiled tubing string to a BHA, a surface wave generator, a surface and/or distributed receiver, and a recorder to determine elapsed times between generation and receipt.

Abstract: A pressure wave system having a tubular member, a signal source, a sensor, and a source of noise, has a noise interference system employing one or more a lateral branches to cancel pressure noise, and/or amplify or filter the pressure wave signal. A related method generates the pressure wave signal, connects the lateral branch or branches to amplify or filter the signal and/or cancel noise from the system, and receives the signal or a response of the system to the signal. The lateral branches are simple pipe stubs or loops that can be made using ordinary piping components, or are more complex designs.

Abstract: A method and system for increasing fracture conductivity. A treatment slurry stage has a continuous first solid particulate concentration and a discontinuous anchorant concentration between anchorant-rich substages and anchorant-lean substages within the treatment slurry stage.

Abstract: A method of treating a subterranean formation, involving performing a fracturing operation and performing a shut in. At a time before or after the shut in is commenced, changes in properties at or near a fracture are estimated based upon monitored data. A plugging agent is injected taking into consideration the estimated changes in properties.

Abstract: A method and system for increasing fracture conductivity. A treatment slurry stage has a continuous first solid particulate concentration and a discontinuous anchorant concentration between anchorant-rich substages and anchorant-lean substages within the treatment slurry stage.