A jaundice analysis system includes a database and a processing device for accessing the database. The processing device includes: a data processing module for generating a training data according to an image data, correlating the training data with a category data, and storing the training data in the database; and a deep learning module for training a target convolutional neural network module with the training data correlating with the category data to obtain a trained convolutional neural network module. The image data includes a first sclera image. The trained convolutional neural network module of the processing device generates a testing data according to an input image data. The input image data includes a second sclera image of a target subject. The testing data indicates the target subject's bilirubin concentration range.

Systems and methods are provided for determine the fat composition in an organ of interest using a non-invasive health measurement system. The non-invasive health measurement system may include an open magnet NMR apparatus. The NMR apparatus may measure NMR signals in a sensitive volume of a patient. The sensitive volume may coincide with an organ of interest, such as a liver. Systems and methods disclosed herein may provide for separation of the water contribution and the fat contribution to the measured NMR signal. Diffusion based separation, T.sub.2 based separation, and T.sub.1 based separation may each serve as different methods for separating the water and fat contributions to the signal. Separating the water and fat contributions to the single may allow for computation of a proton density fat fraction which may reflect the fat composition of the organ of interest.

A method of providing a quantitative volumetric assessment of organ health or a quantitative map of an organ. The method comprises obtaining a volumetric map of organ health comprising information defining a state of tissue health across at least part of an organ, receiving an input defining at least one organ section, determining an assessment organ volume based at least partly on the at least one defined organ section, calculating an organ-viability measure for the assessment organ volume based at least partly on information within the volumetric map defining the state of tissue health across the organ volume, and outputting an indication of the organ-viability measure.

A system and method for processing highly undersampled multi-echo spin-echo data by linearizing the slice-resolved extended phase graph model generates highly accurate T.sub.2 maps with indirect echo compensation. Principal components are used to linearize the signal model to estimate the T.sub.2 decay curves which can be fitted to the slice-resolved model for T2 estimation. In another example of image processing for highly undersampled data, a joint bi-exponential fitting process can compensate for image variations within a voxel and thus provide partial voxel compensation to produce more accurate T.sub.2 maps.

The invention relates to diagnosis in general and more specifically a system and a method for determining the presence of jaundice in newborn babies, also known as neonatal jaundice.

A main objective of the present invention is to provide a simple system and method for determining the presence of jaundice. Particularly since most deaths due to jaundice occur in low-income countries, there is a large unmet need of simple, reliable and affordable technologies able to identify at-risk newborn.

The objective is accomplished through receiving a depiction of skin from an RGB sensor, and then using either an optical diffusion model of the skin or Monte Carlo simulations to calculate the bilirubin concentration. A meta model of the optical diffusion model or Monte Carlo simulations can also be used. Colour calibration is also performed by e.g. thin-plate spline interpolation.

A method and system for registering a pre-operative 3D medical image volume of a target organ to intra-operative ultrasound images is disclosed. An intra-operative 3D B-mode ultrasound volume and an intra-operative 3D ultrasound elastography volume are acquired. Patient-specific boundary conditions for a biomechanical tissue model of a target organ are determined using the intra-operative 3D B-mode volume. Patient-specific material properties for the biomechanical tissue model of the target organ are determined using the 3D ultrasound elastography volume. The target organ in the pre-operative 3D medical image volume is deformed using the biomechanical tissue model with the patient-specific material properties with the deformation of the target organ in the pre-operative 3D medical image volume constrained by the patient-specific boundary conditions.

A method of analysing MRI images is described. The method comprising the steps of: acquiring a first medical MR image, and a second medical MR image, of a subject at the same nominal magnetic field strength; analysing the first and second MR images to determine a wT1 map from the first and second images; applying a field strength correction based on modification of the nominal field strength used for the first and second MR image acquisitions, and an iron correction to correct for differences in the iron concentration from a normal level using a T2*map, to the wT1 map from the first and second images to generate a corrected wT1 map; using the corrected wT1 map to determine simulated signals for a subject with normal iron levels, and fitting the simulated signals to a standard cT1 to determine a standard cT1 image for the subject.

The present disclosure generally relates to medical imaging and, more particularly, relates to systems, apparatus and methods for performing processing of relaxation data obtained by magnetic resonance (MR) T1-mapping of the liver or other visceral organs in the presence of elevated iron and elevated fat levels, and in the presence of off-resonance frequencies in the MR system. The processing results in corrected values of T1 relaxation times of extracellular liquid of the mapped visceral organ that would have been measured if iron content had been at normal levels, if there had been zero fat in the mapped visceral organ and/or there had been zero off-resonance frequencies in the MR system.

Provided is a technique in MRI to efficiently suppress downstream blood in a specific region in a blood vessel having a slow flow velocity, such as the portal vein. For this purpose, a plurality of Beam Sat pulses are applied so as to equally suppress signals of blood flowing into a desired imaging region from a desired blood vessel during the period from applying an IR pulse to starting main imaging. Downstream blood in a specific region in a blood vessel having a slow flow velocity, such as the portal vein, can be suppressed efficiently by determining application conditions of the plurality of Beam Sat pulses that achieve the above based on a flow velocity of blood in a desired blood vessel and T1 of the said blood.

Systems and methods for measuring autofluorescent signals from lipopigments associated with various disease states are disclosed.