An ultrasonic diagnosis apparatus includes a position detector, and control circuitry. The position detector detects a position in a three-dimensional space of one of an ultrasonic image and an ultrasonic probe. The control circuitry uses a vivisection view defined in a three-dimensional space. The control circuitry associates a structure related to a subject included in the ultrasonic image with a structure included in the vivisection view using a position and orientation in a first three-dimensional coordinate system of the structure related to the subject included in the ultrasonic image and a position and orientation in a second three-dimensional coordinate system of the structure included in the vivisection view.

For three-dimensional segmentation from two-dimensional intracardiac echocardiography imaging, the three-dimension segmentation is output by a machine-learnt multi-task generator. Rather than the brute force approach of training the generator from 2D ICE images to output a 2D segmentation, the generator is trained from 3D information, such as a sparse ICE volume assembled from the 2D ICE images. Where sufficient ground truth data is not available, computed tomography or magnetic resonance data may be used as the ground truth for the sample sparse ICE volumes. The generator is trained to output both the 3D segmentation and a complete volume (i.e., more voxels represented than in the sparse ICE volume). The 3D segmentation may be further used to project to 2D as an input with an ICE image to another network trained to output a 2D segmentation for the ICE image. Display of the 3D segmentation and/or 2D segmentation may guide ablation of tissue in the patient.

The present disclosure provides using ultrasound technology and artificial intelligence to enhance MSR assessment by making the assessment more objective, reproducible, and recordable to allow a more precise and/or personalized approach to the medical practice of individual patients via using multiple ultrasound functions and artificial intelligence to improve the accuracy and consistency of assessing reflexes and allowing MSR data to be combined with other patient medical information for improved diagnosis and management of a patient's condition.

A system and method are presented for treating targeted tissue using cryoablation. An introducer canula and a cryoprobe are inserted the targeted tissue. The cryoprobe is cooled and an ice ball is formed. The cryoprobe is removed while the ice ball is still frozen, and an ultrasound catheter is inserted. Ultrasound generated within the ice ball is used to determine the distance from the ultrasound catheter to a perimeter of the ice ball. This is repeated at different angles to model a slice of the ice ball. The ultrasound catheter is moved radially, and the process is repeated to create a model of at least a portion of the ice ball. The ice ball model can be displayed on a registered set of images representing the targeted tissue to ensure that the tissue lies within the treatment zone of the ice ball.

Disclosed herein is a medical device system configured to detect one or more blood vessels within a target area. The medical device system includes an ultrasound probe configured to detect one or more blood vessels, the ultrasound probe in communication with a console. The medical device system further includes one or more blood vessel correlation tools configured to generate a local output detectable by a user. The one or more blood vessel correlation tools are coupled to the ultrasound probe and in communication with a console. The one or more blood vessel correlation tools are selected from the group consisting of a light array, one or more visible light projectors, a haptic feedback system, and an auditory device.

A method and system may be used for tracking a medical instrument. The method may include capturing image data. The method may include capturing ultrasound data. The ultrasound data may be captured via an ultrasound probe. The method may include dewarping the image data. The method may include searching for a marker in the dewarped image data. If it is determined that the marker is found, the method may include extracting an identification. The method may include comparing fiducials with a known geometry. The method may include determining a pose. The method may include determining a location of the medical instrument relative to the ultrasound probe. The method may include overlaying a three-dimensional projection of the medical instrument onto the ultrasound data.

A system may transform sensor data from a sensor domain to an image domain using data-driven manifold learning techniques which may, for example, be implemented using neural networks. The sensor data may be generated by an image sensor, which may be part of an imaging system. Fully connected layers of a neural network in the system may be applied to the sensor data to apply an activation function to the sensor data. The activation function may be a hyperbolic tangent activation function. Convolutional layers may then be applied that convolve the output of the fully connected layers for high level feature extraction. An output layer may be applied to the output of the convolutional layers to deconvolve the output and produce image data in the image domain.

A method of diagnosing Alzheimer's disease using a positron emission tomography-computed tomography (PET-CT) image may include generating a standard brain CT template in a Montreal Neurological Institute (MNI) region based on a CT image calculated from a PET-CT apparatus, calculating a whole cortex volume of interest (VOI) for a plurality of detail regions capable of being used in .sup.18F-florbetaben (FBB) and .sup.18F-flutemetamol (FMM) in common within a cortex ROI region in which a deposition of beta amyloid protein is equal to or higher than a given value based on the standard brain CT template, and calculating a centiloid of each of the plurality of detail regions based on an amyloid standardized uptake value ratio (SUVR) of each of the plurality of detail regions.

A medical system that includes a temperature scanning device configured to identify and locate blood vessels by obtaining a thermal image from a skin surface where blood flowing within blood vessels beneath the skin surface has been altered to define temperature variations of the skin. The system includes a console configured to communicate with the temperature scanning device, the console including processors and logic that, when executed by the processors, causes operations including defining the thermal image. The system may further include a camera, and/or an ultrasound probe. The thermal image may be portrayed on various forms of a display include augmented reality glasses. The thermal image may be overlayed onto a camera image and/or an ultrasound image.

A system may include an ultrasound probe and a controller unit configured to obtain a baseline ultrasound image of a patient's breast area using the ultrasound probe and to obtain a follow-up ultrasound image of the patient's breast area using the ultrasound probe. The controller unit may further be configured to use one or more machine learning models to compare the baseline ultrasound image with the follow-up ultrasound image; detect a change in a morphology or integrity of the patient's breast area based on the comparison of the baseline ultrasound image with the follow-up ultrasound image; and generate a recommendation for a medical intervention based on the detected change.