Abstract: In some examples, a capacitive micromachined ultrasonic transducer (CMUT) array may include a plurality of CMUT elements arranged in a plurality of rows, each row including multiple CMUT elements. A bias voltage supply may be connected for supplying bias voltages to a first row, a second row, and a third row of the plurality of rows. In addition, a processor may be configured by executable instructions to control the bias voltages by applying a first bias voltage to the second row, and a second, different bias voltage to the first and third rows to configure the CMUT elements of the second row to at least one of transmit or receive ultrasonic energy with different efficiency than the CMUT elements of the first row and the third row. In some examples, individual contributions from different rows can be computed from different firing sequences for synthetic aperture beamformation in an elevation dimension.

Abstract: In some examples, a capacitive micromachined ultrasonic transducer (CMUT) array may include a plurality of CMUT elements arranged in a plurality of rows, each row including multiple CMUT elements. A bias voltage supply may be connected for supplying bias voltages to a first row, a second row, and a third row of the plurality of rows. In addition, a processor may be configured by executable instructions to control the bias voltages by applying a first bias voltage to the second row, and a second, different bias voltage to the first and third rows to configure the CMUT elements of the second row to at least one of transmit or receive ultrasonic energy with different efficiency than the CMUT elements of the first row and the third row. In some examples, individual contributions from different rows can be computed from different firing sequences for synthetic aperture beamformation in an elevation dimension.

Abstract: Automated image interpretation is provided with transducer position and/or orientation sensing. The current position of a transducer is used to determine the anatomy being imaged. Other reference information, such as (1) the previous position of the transducer and the known anatomy being imaged at that time or (2) a reference device at a known location, is used in the determination. The anatomy is determined based on position sensing or determined based on position sensing and other anatomy features, such as image analysis.

Abstract: Tissue information is equalized by adaptively controlling gain and mapping input data to output data based on the gain in three-dimensional medical diagnostic imaging. A hypersurface is fit in three spatial dimensions to tissue information in input data. The hypersurface is used to adjust the gain so that input values are mapped to output values with more uniform soft tissue levels.

Abstract: A method for view classification includes providing a frame of an object of interest, detecting a region of interest within the object of interest for each of a plurality of detectors (e.g., binary classifiers), wherein each binary classifier corresponds to a different view, performing a global view classification using a multiview classifier for each view, outputting a classification for each view, fusing outputs of the multiview classifiers, and determining and outputting a classification of the frame based on a fused output of the multiview classifiers.

Abstract: A method and system for detection of deformable structures in medical images is disclosed. Deformable structures can represent blood flow patterns in images such as Doppler echocardiograms. A probabilistic, hierarchical, and discriminant framework is used to detect such deformable structures. This framework integrates evidence from different primitive levels via a progressive detector hierarchy, including a series of discriminant classifiers. A target deformable structure is parameterized by a multi-dimensional parameter, and primitives or partial parameterizations of the parameter are determined. An input image is received, and a series of primitives are sequentially detected using the progressive detector hierarchy, in which each detector or classifier detects a corresponding primitive. The final detector detects configuration candidates for the deformable structure.

Abstract: A view represented by echocardiographic data is classified. A probabilistic boosting network is used to classify the view. The probabilistic boosting network may include multiple levels where each level has a multi-class local structure classifier and a plurality of local-structure detectors corresponding to the respective multiple classes. In each level, the local structure is classified as a particular view and then the local structure is detected to determine whether the currently selected local structure corresponds to the class. The view classification may be used to determine gate locations, such as a gate for spectral Doppler analysis.

Abstract: Disclosed are a system and method of selecting one or more operational parameters of an ultrasonic imaging system. In particular, methods and means are disclosed for automatically or semi-automatically determining a best operating frequency, or for determining whether a system should operate in a fundamental imaging mode or a harmonic imaging mode.

Abstract: Methods and systems are provided for automatic optimization for ultrasound medical imaging. In one approach, velocity values are unwrapped to avoid aliasing artifacts. Multi-dimensional phase unwrapping is applied to the velocity data. The unwrapped velocity information is used to optimize one or both of the velocity scale (e.g., pulse repetition frequency) and the imaging frequency. For optimizing the scale setting, the distribution of unwrapped velocities from a systolic time period of the heart cycle are used to identify the pulse repetition frequency. For optimizing the imaging frequency, a correlation as a function of depth shows the penetration depth for a given imaging frequency. In a dependent or independent approach, one or more thresholds for velocity or energy in flow imaging are adaptively selected as a function of an amount of clutter. Velocity or other energy information in addition to the clutter information may be used for selecting the thresholds.

Abstract: Phase unwrapping is applied to velocity data to remove aliasing artifacts. Phase unwrapping is applied on multidimensional regions of velocity data. The unwrapped velocity image is displayed. The displayed image may have high sensitivity to slow motion but may also avoid aliasing of fast motion despite being undersampled.

Abstract: Anatomical information is identified from a medical image and/or used for controlling a medical diagnostic imaging system, such as an ultrasound system. To identify anatomical information from a medical image, a processor applies a multi-class classifier. The anatomical information is used to set an imaging parameter of the medical imaging system. The setting or identification may be used in combination or separately.

Abstract: Disclosed are an apparatus and method of adjusting gain of an ultrasound system 100. In particular, subject matter is disclosed for receiving an indication 102 of a rate of change in motion of an object 106, and adjusting a gain based 108, at least in part, on said rate of change in motion, where the gain is adjusted at least partially corresponding to the rate of change in motion of the object 106.

Abstract: Methods are provided for automatic setting of parameters for contrast agent quantification. Various processes may improve quantification. For example, for consistency in contrast agent quantification, a gain or other setting of an ultrasound system is automatically determined in response to destruction of the contrast agent or at the initiation of the contrast agent quantification procedure. Automatic setting of an adaptive gain provides equalized image intensity for each repetition of a contrast agent quantification procedure based on a same triggering event, the destruction of contrast agent. By synchronizing the adaptive setting algorithms with contrast agent destruction, similar base line information is provided for each iteration of a contrast agent quantification procedure. As another example, the contrast agent gain setting treats acoustic signals representing tissue or other non-contrast agent structure as noise, mapping the tissue values to a substantially constant low value within the dynamic range.

Abstract: A view represented by echocardiographic data is classified. A probabilistic boosting network is used to classify the view. The probabilistic boosting network may include multiple levels where each level has a multi-class local structure classifier and a plurality of local-structure detectors corresponding to the respective multiple classes. In each level, the local structure is classified as a particular view and then the local structure is detected to determine whether the currently selected local structure corresponds to the class. The view classification may be used to determine gate locations, such as a gate for spectral Doppler analysis.

Abstract: Tissue information is equalized by adaptively controlling gain and mapping input data to output data based on the gain in three-dimensional medical diagnostic imaging. A hypersurface is fit in three spatial dimensions to tissue information in input data. The hypersurface is used to adjust the gain so that input values are mapped to output values with more uniform soft tissue levels.

Abstract: A method for view classification includes providing a frame of an object of interest, detecting a region of interest within the object of interest for each of a plurality of detectors (e.g., binary classifiers), wherein each binary classifier corresponds to a different view, performing a global view classification using a multiview classifier for each view, outputting a classification for each view, fusing outputs of the multiview classifiers, and determining and outputting a classification of the frame based on a fused output of the multiview classifiers.

Abstract: A method and system for detection of deformable structures in medical images is disclosed. Deformable structures can represent blood flow patterns in images such as Doppler echocardiograms. A probabilistic, hierarchical, and discriminant framework is used to detect such deformable structures. This framework integrates evidence from different primitive levels via a progressive detector hierarchy, including a series of discriminant classifiers. A target deformable structure is parameterized by a multi-dimensional parameter, and primitives or partial parameterizations of the parameter are determined. An input image is received, and a series of primitives are sequentially detected using the progressive detector hierarchy, in which each detector or classifier detects a corresponding primitive. The final detector detects configuration candidates for the deformable structure.

Abstract: Automated image interpretation is provided with transducer position and/or orientation sensing. The current position of a transducer is used to determine the anatomy being imaged. Other reference information, such as (1) the previous position of the transducer and the known anatomy being imaged at that time or (2) a reference device at a known location, is used in the determination. The anatomy is determined based on position sensing or determined based on position sensing and other anatomy features, such as image analysis.

Abstract: Methods and systems are provided for automatic optimization for ultrasound medical imaging. In one approach, velocity values are unwrapped to avoid aliasing artifacts. Multi-dimensional phase unwrapping is applied to the velocity data. The unwrapped velocity information is used to optimize one or both of the velocity scale (e.g., pulse repetition frequency) and the imaging frequency. For optimizing the scale setting, the distribution of unwrapped velocities from a systolic time period of the heart cycle are used to identify the pulse repetition frequency. For optimizing the imaging frequency, a correlation as a function of depth shows the penetration depth for a given imaging frequency. In a dependent or independent approach, one or more thresholds for velocity or energy in flow imaging are adaptively selected as a function of an amount of clutter. Velocity or other energy information in addition to the clutter information may be used for selecting the thresholds.

Abstract: During scanning or in real-time with acquisition of ultrasound data, a plurality of images is generated corresponding to a plurality of different planes in a volume. The volume scan data is searched by a processor to identify desired views. Multiple standard or predetermined views are generated based on plane positioning within the volume by the processor. Multi-planar reconstruction, guided by the processor, allows for real-time imaging of multiple views at a substantially same time. The images corresponding to the identified views are generated independent of the position of the transducer. The planes may be positioned in real-time using a pyramid data structure of coarse and fine data sets.