A localization and mapping system and method for a motor vehicle is disclosed and includes at least one camera configured to obtain images of an environment surrounding the motor vehicle, at least one sensor configured to obtain location information for objects surrounding the motor vehicle and a controller configured to receive the images captured by the at least one camera and the location information obtained by the at least one sensor. The controller enhances the captured images utilizing a neural network and combines the enhanced images with the location information to localize the vehicle within the mapped environment.

An imaging steering apparatus includes sensors and an imaging processor configured for: acquiring, via multiple ones of the sensors and from a current position (322), and current orientation (324), an image of an object of interest; based on a model, segmenting the acquired image; and determining, based on a result of the segmenting, a target position (318), and target orientation (320), with the target position and/or target orientation differing correspondingly from the current position and/or current orientation. An electronic steering parameter effective toward improving the current field of view may be computed, and a user may be provided instructional feedback (144) in navigating an imaging probe toward the improving. A robot can be configured for, automatically and without need for user intervention, imparting force (142) to the probe to move it responsive to the determination.

Methods and apparatuses for performing automated detection of lung slide using a computing device (e.g., an ultrasound system, etc.) are disclosed. In some embodiments, the techniques determine lung sliding using one or more neural networks. In some embodiments, the neural networks are part of a process that determines probabilities of the lung sliding at one or more M-lines. In some embodiments, the techniques display one or more probabilities of lung sliding in a B-mode ultrasound image.

Retinal diseases, such as age-related macular degeneration (AMD), are the leading cause of blindness in the elderly population. Since no known cures are currently present, it is crucial to diagnose the condition in its early stages so that disease progression is monitored. Systems and methods for detecting and mapping the mechanical elasticity of retinal layers in the posterior eye are disclosed herein. A system including confocal shear wave acoustic radiation force optical coherence elastography (SW-ARF-OCE) is provided, wherein an ultrasound transducer and an optical scan head are co-aligned to facilitate in-vivo study of the retina. In addition, an automatic segmentation algorithm is used to isolate tissue layers and analyze the shear wave propagation within the retinal tissue to estimate mechanical stress on the retina and detect early stages of retinal diseases based on the estimated mechanical stress.

The present invention discloses a method for automatic segmentation of a fuzzy boundary image based on active contour and deep learning. In the method, firstly, a fuzzy boundary image is segmented using a deep convolutional neural network model to obtain an initial segmentation result; then, a contour of a region inside the image segmented using the deep convolutional neural network model is used as an initialized contour and a contour constraint of an active contour model; and the active contour model drives, through image characteristics of a surrounding region of each contour point, the contour to move towards a target edge to derive an accurate segmentation line between a target region and other background regions. The present invention introduces an active contour model on the basis of a deep convolutional neural network model to further refine a segmentation result of a fuzzy boundary image, which has the capability of segmenting a fuzzy boundary in the image, thus further improving the accuracy of segmentation of the fuzzy boundary image.

A method for determining hemodynamic parameters may be provided. The method may include obtaining image data of a subject. The method may include generating a first vascular model and a second vascular model based on the image data and coupling the first vascular model with the second vascular model using an intermediate model to form a coupled vascular model. The method may also include setting at least one of a first boundary condition of the first vascular model or a second boundary condition of the second vascular model and determining a flow field distribution of the coupled vascular model based on the at least one of the first boundary condition or the second boundary condition. The method may further include determining hemodynamic parameters based on the flow field distribution.

Systems and methods for generating adaptive contrast accumulation imaging images are disclosed. A point spread function thinning/skeletonization technique may be performed on contrast enhanced image frames. An aggressiveness parameter of the technique may be adapted temporally and/or spatially. The aggressiveness parameter may be adapted based on various factors, including, but not limited to, time since injection of the contrast agent, signal intensity, and/or vessel size. The images may be temporally accumulated to generate a final sequence of adaptive contrast accumulation imaging images.

A method and instruction memory for processing acoustic images of a downhole casing to determine perforations of the tubular. The images may be acquired by an acoustic logging tool deployed into cased well. A Machine Learning model is trained to recognize regions of the acoustic images that are perforations or not, in order to calculate geometric properties of the perforation and overall casing. Renderings of the imaged casing may be overlaid with contours and properties of perforations to improve perforation, fracturing and producing operations.

An ultrasound diagnostic apparatus (1) includes a urinary bladder extraction unit (9), a feature quantity calculation unit (10), a candidate frame extraction unit (11), and a urine volume measurement unit (13). The urinary bladder extraction unit (9) extracts a urinary bladder region from ultrasound images of a plurality of frames. The feature quantity calculation unit (10) calculates a feature quantity related to the bladder region. The candidate frame extraction unit (11) extracts, from the ultrasound images of the plurality of frames, an ultrasound image of a frame for which the feature quantity becomes a local maximum, as an ultrasound image of at least one candidate frame that serves as a candidate subjected to measurement. The urine volume measurement unit (13) analyzes an ultrasound image of a measurement frame selected from the ultrasound image of the at least one candidate frame to measure a urine volume.

A processor-implemented method with sensor calibration includes: estimating a portion of a rotation parameter for a target sensor among a plurality of sensors based on a capture of a reference object; estimating another portion of the rotation parameter for the target sensor based on an intrinsic parameter of the target sensor and a focus of expansion (FOE) determined based on sensing data collected with consecutive frames by the target sensor while the electronic device rectilinearly moves based on one axis; and performing calibration by determining a first extrinsic parameter for the target sensor based on the portion and the other portion of the rotation parameter.