Abstract: A gas turbine engine includes a turbomachine having a compressor section, a combustion section, and a turbine section. The turbine section includes a band having an upstream end and a downstream end. The band extends between the upstream end and the downstream end, and the band at least partially defines the working gas flow path. A plurality of airfoils extend into the working gas flow path from the band. Each airfoil of the plurality of airfoils includes a leading edge, a trailing edge, a first side, and a second side opposite the first side. Each of the plurality of airfoils is substantially symmetric across an airfoil centerline extending through a center of each of the plurality of airfoils. The band defines a valley portion adjacent the leading edge of each of the plurality of airfoils and a pair of hill portions on opposing sides of the valley portion.

Abstract: A method includes identifying stenosed region within vessel in vascular image data and generating a revascularized model of the vessel based on the vascular image data with a lumen boundary in the stenosed region adjusted to have a same cross-sectional area as healthy sections of the vessel. The method includes determining a first pressure distribution for the revascularized model at hyperemic flow, determining a second pressure distribution for the vessel in the vascular image data, and calculating a subtracted pressure distribution by subtracting the second pressure distribution from the first pressure distribution. The method includes determining an asymptotic value for the subtracted pressure distribution and calculating a value by subtracting the asymptotic value from a pressure value obtained from the second pressure distribution at a location at a beginning of the stenosed region. The method includes normalizing the value to obtain a location independent FFR value for the stenosed region.

Abstract: A gas turbine engine includes a compressor section, a combustion section including an inner liner and an outer liner spaced from the inner liner, and a turbine section. The inner liner and outer liner at least partially define a combustion chamber. The turbine section includes an inner band extending between an upstream side and a downstream side opposite the upstream side and an outer band spaced from the inner band and extending between the upstream side and the downstream. The inner band and outer band at least partially define a working gas flow path. One or both of the inner band and the outer band include a step portion adjacent the upstream side and a body portion extending from the step portion to the downstream side. The step portion extends in a radial direction past the body portion.

Abstract: A computer-implemented method includes obtaining, via a processor, clinical images including vessels and generating, via the processor, straightened-out images for each coronary tree path within respective clinical images, The method also includes extracting, via the processor, segmented 3D image patches, determining, via the processor, overlapping binary mask volumes for each segment, and predicting, via the processor, pressure drops across the segmented image patches using a trained deep neural network.

Abstract: A computer-implemented method includes obtaining, via a processor, segmented image patches of a vessel along a coronary tree path and associated coronary flow distribution for respective vessel segments in the segmented image patches. The method also includes determining, via the processor, a pressure drop distribution along an axial length of the vessel from the segmented image patches and the associated coronary flow distribution. The method further includes determining, via the processor, critical points in the pressure drop distribution. The method even further includes detecting, via the processor, a presence of a stenosis based on the critical points in the pressure drop distribution.

Abstract: A method includes identifying stenosed region within vessel in vascular image data and generating a revascularized model of the vessel based on the vascular image data with a lumen boundary in the stenosed region adjusted to have a same cross-sectional area as healthy sections of the vessel. The method includes determining a first pressure distribution for the revascularized model at hyperemic flow, determining a second pressure distribution for the vessel in the vascular image data, and calculating a subtracted pressure distribution by subtracting the second pressure distribution from the first pressure distribution. The method includes determining an asymptotic value for the subtracted pressure distribution and calculating a value by subtracting the asymptotic value from a pressure value obtained from the second pressure distribution at a location at a beginning of the stenosed region. The method includes normalizing the value to obtain a location independent FFR value for the stenosed region.

Abstract: A computer-implemented method includes obtaining, via a processor, clinical images including vessels and generating, via the processor, straightened-out images for each coronary tree path within respective clinical images, The method also includes extracting, via the processor, segmented 3D image patches, determining, via the processor, overlapping binary mask volumes for each segment, and predicting, via the processor, pressure drops across the segmented image patches using a trained deep neural network.

Abstract: A computer-implemented method includes generating, via a processor, synthetic vessels. The method also includes performing, via the processor, three-dimensional (3D) computational fluid dynamics (CFD) on the synthetic vessels for different flow rates to generate 3D CFD data. The method further includes extracting, via the processor, 3D image patches from the synthetic vessels. The method even further includes obtaining, via the processor, pressure drops across the 3D image patches from the 3D CFD data. The method yet further includes training, via the processor, a deep neural network utilizing the 3D image patches, the pressure drops, and associated flow rates to generate a trained deep neural network.

Abstract: Systems and techniques that facilitate hybrid unsupervised and supervised image segmentation are provided. In various embodiments, a system can access a computed tomography (CT) image depicting an anatomical structure. In various aspects, the system can generate, via an unsupervised modeling technique, at least one class probability mask of the anatomical structure based on the CT image. In various instances, the system can generate, via a deep-learning model, an image segmentation based on the CT image and based on the at least one class probability mask.

Abstract: A turbine engine stage includes a plurality of airfoils extending between an inner band and an outer band. Each airfoil in the plurality of airfoils can have an outer wall defining a pressure side and a suction side, with the outer wall extending between a leading edge and a trailing edge. An intervening flow passage is defined between two adjacent airfoils in the plurality of airfoils.

Abstract: A computer-implemented method includes generating, via a processor, synthetic vessels. The method also includes performing, via the processor, three-dimensional (3D) computational fluid dynamics (CFD) on the synthetic vessels for different flow rates to generate 3D CFD data. The method further includes extracting, via the processor, 3D image patches from the synthetic vessels. The method even further includes obtaining, via the processor, pressure drops across the 3D image patches from the 3D CFD data. The method yet further includes training, via the processor, a deep neural network utilizing the 3D image patches, the pressure drops, and associated flow rates to generate a trained deep neural network.

Abstract: A computer-implemented method includes obtaining, via a processor, segmented image patches of a vessel along a coronary tree path and associated coronary flow distribution for respective vessel segments in the segmented image patches. The method also includes determining, via the processor, a pressure drop distribution along an axial length of the vessel from the segmented image patches and the associated coronary flow distribution. The method further includes determining, via the processor, critical points in the pressure drop distribution. The method even further includes detecting, via the processor, a presence of a stenosis based on the critical points in the pressure drop distribution.

Abstract: Systems and techniques that facilitate hybrid unsupervised and supervised image segmentation are provided. In various embodiments, a system can access a computed tomography (CT) image depicting an anatomical structure. In various aspects, the system can generate, via an unsupervised modeling technique, at least one class probability mask of the anatomical structure based on the CT image. In various instances, the system can generate, via a deep-learning model, an image segmentation based on the CT image and based on the at least one class probability mask.

Abstract: A turbine rotor blade including an airfoil that extends from a platform. The platform may include a first portion of a nominal platform contour substantially in accordance with Cartesian coordinate values of X?, Y?, and Z? as set forth in Table II. The Cartesian coordinate values of X?, Y?, and Z? are non-dimensional values from 0% to 100% convertible to dimensional distances by multiplying the Cartesian coordinate values of X?, Y?, and Z? by a height of the airfoil defined along a Z? axis. The X? and Y? values of the first portion are coordinate values that, when connected by smooth continuing arcs, define contour lines of the first portion of the nominal airfoil profile at each Z? coordinate value. The contour lines may be joined smoothly with one another to form the first portion.

Abstract: The present disclosure relates to the use of prior images acquired of the patient and acoustic signature from a vascular region of interest to create a patient-specific model of sound propagation from the vascular region. This model is then used to monitor the progression of disease in the vascular region of interest, using subsequently-acquired acoustic signals. In an alternate embodiment, population-based images and/or population-based acoustic signatures are used to generate predictive data when a priori patient-specific imaging information is not available and this data is used to characterize or categorize at-risk patients suspected of coronary artery disease, but without prior cardiac events.

Abstract: The present disclosure relates to training one or more neural networks for vascular vessel assessment using synthetic image data for which ground-truth data is known. In certain implementations, the synthetic image data may be based in part, or derived from, clinical image data for which ground-truth data is not known or available. Neural networks trained in this manner may be used to perform one or more of vessel segmentation, decalcification, Hounsfield unit scoring, and/or estimation of a hemodynamic parameter.

Abstract: The present disclosure relates to localization of bleeds (e.g., arterial bleed events) using a limited or minimal number of ultrasound scans. In one implementation, Doppler ultrasound is used to measure blood flow velocities in a one-dimensional (1D) arterial tree model to determine the location and size of bleed. In a second implementation, ultrasound measured waveforms for blood flow velocity and vessel cross-sectional area are de-composed. The features in the de-composed waveforms are then used to locate the bleed using a trained algorithm.

Abstract: The present approach provides a non-invasive methodology for estimation of coronary flow and/or fractional flow reserve. In certain implementations, various approaches for personalizing blood flow models of the coronary vasculature are described. The described personalization approaches involve patient-specific measurements and do not assume or rely on the resting coronary flow being proportional to myocardial mass. Consequently, there are fewer limitations in using these approaches to obtain coronary flow and/or fractional flow reserve estimates non-invasively.

Abstract: A turbine rotor blade including an airfoil that extends from a platform. The platform may include a first portion of a nominal platform contour substantially in accordance with Cartesian coordinate values of X?, Y?, and Z? as set forth in Table II. The Cartesian coordinate values of X?, Y?, and Z? are non-dimensional values from 0% to 100% convertible to dimensional distances by multiplying the Cartesian coordinate values of X?, Y?, and Z? by a height of the airfoil defined along a Z? axis. The X? and Y? values of the first portion are coordinate values that, when connected by smooth continuing arcs, define contour lines of the first portion of the nominal airfoil profile at each Z? coordinate value. The contour lines may be joined smoothly with one another to form the first portion.

Abstract: The present disclosure relates to training one or more neural networks for vascular vessel assessment using synthetic image data for which ground-truth data is known. In certain implementations, the synthetic image data may be based in part, or derived from, clinical image data for which ground-truth data is not known or available. Neural networks trained in this manner may be used to perform one or more of vessel segmentation, decalcification, Hounsfield unit scoring, and/or estimation of a hemodynamic parameter.