Determining collateral information describing blood flow in collaterals of a blood vessel system in a target region of a patient from a four-dimensional vascular data set describing image values of temporal flow of a contrast medium and/or marked blood constituents as recorded by a medical imaging device is provided. A method includes segmenting the blood vessel system in the vascular data set and determining collaterals among the segmented blood vessels by a collateral classifier. For all collaterals determined, a diameter of the collateral is determined taking into account the segmentation, a filling parameter describing the filling of the collaterals, and a time parameter describing the time response relative to a reference point in the blood vessel system from a temporal course of the image values in a portion of the collaterals under consideration. The method includes determining the collateral information from the diameter, the filling parameter, and the time parameter.

The invention relates to elements of a method (1) for determining a damage characteristic value of a kidney (2). Images comprising the kidney (2) and the kidney artery (3) are entered into the method (1), from a three-dimensional digital subtraction angiography which is carried out by administering a contrast medium at the proximal end of the kidney artery (3) and comprises a fill run and a mask run, said method (1) comprising the following method steps: S1) determining a parenchymal blood volume into which the subtractions from images of the fill run and the mask run of the three-dimensional digital subtraction angiography are entered, additionally determining an arterial input function and normalizing the parenchymal blood volume with said arterial input function; S2) segmenting the kidney (2), determining an average normalized parenchymal blood volume value, and determining a total value of the parenchymal blood volume into which the normalized parenchymal blood volume values of the segmentation of the kidney (2) are entered; S3) receiving an average normalized parenchymal blood volume normal value and a total normal value for a parenchymal blood volume, and determining at least one damage characteristic value of the kidney (2) into which the average normalized parenchymal blood volume value and the average normalized parenchymal blood volume normal value and/or the total value of the parenchymal blood volume and the total normal value of a parenchymal blood volume are entered; S4) issuing the at least one damage characteristic value of the kidney (2).

A method for vascular modeling is disclosed. The method, in some embodiments, comprises receiving a plurality of 2-D angiographic images of a portion of a vasculature of a subject, and processing the images to automatically detect 2-D features, for example, paths along vascular extents, which are projected into 3-D to determine homologous features among blood vessels. In some embodiments, projection and/or image registration is iteratively altered to improve feature position matching. Based on 3-D vascular extents and their registration to 2-D images, additional features such as vascular width are optionally determined and added to the model.

Systems and methods are disclosed for performing probabilistic segmentation in anatomical image analysis, using a computer system. One method includes receiving a plurality of images of an anatomical structure; receiving one or more geometric labels of the anatomical structure; generating a parametrized representation of the anatomical structure based on the one or more geometric labels and the received plurality of images; mapping a region of the parameterized representation to a geometric parameter of the anatomical structure; receiving an image of a patient's anatomy; and generating a probability distribution for a patient-specific segmentation boundary of the patient's anatomy, based on the mapping of the region of the parameterized representation of the anatomical structure to the geometric parameter of the anatomical structure.

Systems and methods are disclosed for determining anatomy directly from raw medical acquisitions using a machine learning system. One method includes obtaining raw medical acquisition data from transmission and collection of energy and particles traveling through and originating from bodies of one or more individuals; obtaining a parameterized model associated with anatomy of each of the one or more individuals; determining one or more parameters for the parameterized model, wherein the parameters are associated with the raw medical acquisition data; training a machine learning system to predict one or more values for each of the determined parameters of the parametrized model, based on the raw medical acquisition data; acquiring a medical acquisition for a selected patient; and using the trained machine learning system to determine a parameter value for a patient-specific parameterized model of the patient.

To acquire information relating to a vessel wall thickness by: acquiring interference signal sets of a plurality of frames including interference signal sets corresponding to a plurality of frames forming an image of the same cross section of an fundus; generating 3-D tomographic image data on the fundus from the interference signal sets of the plurality of frames; generating 3-D motion contrast data in the fundus from the interference signal sets corresponding to the plurality of frames that form the same cross section; extracting a vessel from the fundus based on the 3-D tomographic image data or the 3-D motion contrast data; detecting a coordinate of an outer surface of a vessel wall of the vessel based on the 3-D tomographic image data; and detecting a coordinate of an inner surface of the vessel wall of the vessel based on the 3-D motion contrast data.

In an embodiment, a method converts two images to a transform representation in a transform domain. For each spatial position, the method examines coefficients representing a neighborhood of the spatial position that is spatially the same across each of the two images. The method calculates a first vector in the transform domain based on first coefficients representing the spatial position, the first vector representing change from a first to second image of the two images describing deformation. The method modifies the first vector to create a second vector in the transform domain representing amplified movement at the spatial position between the first and second images. The method calculates second coefficients based on the second vector of the transform domain. From the second coefficients, the method generates an output image showing motion amplified according to the second vector for each spatial position between the first and second images.

An image processing apparatus determines an exceptional frame of a plurality of frames forming a moving image captured by an ophthalmic apparatus including an aberration correction device, and applies image processing of a blood vessel area for a frame, among the plurality of frames, which has not been determined as the exceptional frame.

According to one embodiment, a structuring circuitry temporarily structures a dynamical model of analysis processing based on the time-series medical image. The identification circuitry identifies a latent variable of the dynamical model so that at least one of a prediction value of a blood vessel morphology and a prediction value of a bloodstream based on the temporarily structured dynamical model is in conformity with at least one of an observation value of the blood vessel morphology and an observation value of the bloodstream measured in advance. The analysis circuitry analyzes the dynamical model to which the identified latent variable is allocated.

The invention relates to a registration apparatus (14) for registering images comprising a unit (11) for providing a first and a second image of an object, such that an image element of the first image at a respective position has been reconstructed by multiplying projection data values of rays traversing the image element with weights and by backprojecting the weighted projection data values, a unit (12) for providing a confidence map comprising for different positions in the first image confidence values being indicative of a likelihood that an image feature is caused by a structure of the object, the confidence value being calculated as a sum of a function, which depends on the respective weight, over the rays traversing the respective image element, and a unit (13) for determining a transformation for registering the first and second image to each other under consideration of the confidence map.