Aspects of the invention are directed to coil positioning apparatuses, systems, and methods of employing the same. One portable head coil apparatus is provided for use with a magnetic resonance imaging system. The portable head coil apparatus includes a base having at least one coil array comprising at least two coil elements. The base is positionable relative to the patients head and has a receiving portion defining a receiving surface positionable adjacent the patient positioning device. The portable head coil apparatus includes an extension movable relative to the base and having at least one coil array comprising at least two coil elements. The extension defines an inner surface having a curvature the degree of which is greater than that of the receiving surface of the base. The inner surface of the extension and the receiving surface of the base together at least partially define an imaging region therebetween.

A combined physics-based and machine learning framework is used for reconstructing images from k-space data, in which motion artifacts are significantly reduced in the reconstructed images. In general, model-based retrospective motion correction techniques are accelerated using fast machine learning (“ML”) steps, which may be implemented using a trained neural network such as a convolutional neural network. In this way, the confidence of a classical physics-based reconstruction is obtained with the computational benefits of an ML-based network.

A system to generate images based on imaging data of a portion of a body and physiological event data associated with a physiological process of the body. The system is to identify a plurality of physiological cycles based on the physiological event data, determine a duration of each of the plurality of physiological cycles, determine a representative duration based on the durations of each of the plurality of physiological cycles, identify a first plurality of the plurality of physiological cycles based on a difference between the durations of the first plurality of physiological cycles and the representative duration, identify a second plurality of the plurality of physiological cycles different from the first plurality of the plurality of physiological cycles, determine a predetermined number of portions of each of the second plurality of the plurality of physiological cycles, accumulate imaging data acquired during respective portions of each of the second plurality of the plurality of physiological cycles to determine a set of accumulated imaging data for each of the predetermined number of portions, and generate a plurality of images, each of the plurality of images being generated based on a respective one of the sets of accumulated imaging data.

Reducing noise and dose (radiation or contrast) for perfusion imaging in Computed Tomography Perfusion (CTP), Positron Emission Tomography (PET), Single Photon Emission Computed Tomography (SPECT), and Magnetic Resonance Imaging (MRI) medical scanning devices by using a k-space based method. The time sequence of images from the scanner data set is converted as necessary, such as using a 2D Fast Fourier Transform (FFT), into a k-space having multiple timeframes. View-shared averaging is performed to reduce noise and preserve spatial and temporal resolutions of CTP, PET, SPECT and MRI data by progressively increasing the number of time frames for view-shared averaging for more distant regions of “k-space”, before converting the data, such as through a 2D FFT into a time sequence of noise reduced images.

An aggravation estimation system is provided for accurately estimating aggravation of a patient. The aggravation estimation system acquires bed image data chronologically capturing a capturing region including a bed of a patient, analyzes movement of the patient or a body part of the patient captured in the acquired bed image data, and estimates aggravation of the patient by performing, based on the movement that is determined by analysis, scoring in relation to at least one of oxygen administration or a state of consciousness included in indices of national early warning score.

Presented are systems and methods for the accurate acquisition of medical measurement data of a body part of patient. To assist in acquiring accurate medical measurement data, an automated diagnostic and treatment system provides instructions to the patient to allow the patient to precisely position a medical instrument in proximity to a target spot of a body part of patient. For a stethoscope examination, the steps may include utilizing object tracking to determine if the patient has moved the stethoscope to a recording site; utilizing DSP processing to confirm that the stethoscope is in operation, utilizing DSP processing to generate a pre-processed audio sample from a recorded audio signal; using machine learning (ML) to determine if a signal of interest (SOI) is present in the pre-processed sample. If SoI is present, using ML to evaluate characteristics in the signal which indicate the presence of abnormalities in the organ being measured.

Subjects who are potentially impacted by a medical condition are identified. An experimental group includes subjects having a positive indication for a specific criterion related to the medical condition in their medical profiles. A control groups includes subjects having a negative indication for the specific criterion. An artificial intelligence system is trained using the specific criterion and secondary characteristics of the subjects of the experimental and control groups to construct a classifier for the medical condition. The classifier is used to extract a target group of subjects from a population of subjects. A medical profile of each subject of the target group is marked as potentially affected by the medical condition. A system includes the artificial intelligence system and a database for storing the medical profiles. Deep learning or machine learning may be used to analyze medical images such as retinal images.

A method for providing an optimum subtraction data set includes: receiving first image data sets acquired by a medical imaging device and which map an object under examination within a first time phase; receiving at least one second image data set acquired by the same or another medical imaging device and which maps a change in the object under examination within a second time phase; dividing the at least one second image data set into a plurality of image regions; generating subtraction image regions for the plurality of image regions; determining an image quality parameter for each subtraction image region; determining an optimum subtraction image region for each image region of the plurality of image regions of the at least one second image data set by comparing the image quality parameters; generating the optimum subtraction data set from the optimum subtraction image regions; and providing the optimum subtraction data set.

A single volume soft sensor capable of sensing real-time continuous contact and stretching. A low-cost and an easy method to fabricate such piezoresistive elastomer-based soft sensors for instant interactions is also provided. An electrical impedance tomography (EIT) technique is employed to estimate changes of resistance distribution on the sensor caused by fingertip contact. To compensate for the rebound elasticity of the elastomer and achieve real-time contact sensing, an adaptive baseline update for EIT is utilized. The baseline updates are triggered by fingertip contact and movement detections.

A computing device: compares an anatomical magnetic resonance (MR) image of a patient region and reference anatomical data associated with the region to determine a first transform of a bore anatomical coordinate space of the anatomical MR image to a patient anatomical coordinate space associated with the patient; determines, from the first transform, a second transform of a bore DWMR coordinate space of a DWMR image to a patient DWMR coordinate space associated with the patient, the anatomical and the DWMR images being in respective bore coordinate spaces associated with a bore of an MR device which acquired the anatomical and the DWMR images; transforms, using the second transform, the DWMR image to the patient DWMR coordinate space; and controls a display screen to render the DWMR image, as transformed, according to visual attributes associated with the patient DWMR coordinate space.