Abstract: A computer implemented method of identifying contacts of an electrode implanted into the brain of a subject via bolts through the skull of the subject, based on an image of the subject, the method comprising: identifying at least one bolt region of the image corresponding to a bolt; identifying one or more contact regions of the image corresponding to electrode contacts; determining contact regions associated with an identified bolt region by searching for identified contact regions, the search being performed based on a search axis extending from the identified bolt region, the direction of the search axis being determined based on the identified bolt region.

Abstract: A system and method are provided for analysing a functional magnetic resonance imaging (MRI) scan representing a time-sequence, comprising t time points, of images comprising v voxels, where each scan can be represented by a data matrix X?t×v. The method comprises modelling the scan data X as the convolution of neural activation time courses N?+t×v and a haemodynamic filter ?, and performing an inverse operation to estimate N from X and ?. The method further compasses decomposing the neural activation time courses N into multiple brain network components by representing N as the product of a first matrix H defining, for each component, a spatial map of the voxels belonging to that component, and a second matrix W defining, for each component, the time sequence of activation of that component during the scan. In other implementations, the matrix decomposition may be performed before the deconvolution.

Abstract: A computer-implemented method of transmitting through a disordered medium from a transmitter to a receiver an image represented as input coherent electromagnetic radiation, the disordered medium having a transmission matrix comprising a plurality of complex-valued transmission constants that relate said input coherent electromagnetic radiation to output electromagnetic radiation at said receiver, which method comprises the steps of: performing a characterising process on said disordered medium to determine said transmission matrix; using said transmitter to transmit said image through said disordered medium; performing a reconstruction process using said transmission matrix to generate a reconstructed image from the output electromagnetic radiation at said receiver; wherein in said characterisation process the step of determining said transmission matrix comprises: determining said complex-valued transmission constants as real-valued transmission constants by using an approximately linear relationship bet

Abstract: Examples of the present disclosure relate to an apparatus comprising input circuitry configured to acquire imaging data corresponding to a branched organic structure, and image processing circuitry. The image processing circuitry is configured to determine, from the imaging data, a parametric configuration of the branched organic structure comprising solid and volumetric scaffolding data indicative of the branched organic structure, and determine, based on the scaffolding data, a multi-dimensional parametric representation of the branched organic structure.

Abstract: Examples of the present disclosure relate to an apparatus comprising input circuitry configured to acquire imaging data corresponding to a branched biological structure. The apparatus further comprises image processing circuitry configured to: extract, from the imaging data, a configuration of the branched biological structure; determine graph data indicative of the configuration of the branched biological structure; and detect, based on the graph data, a biological characteristic of the branched biological structure.

Abstract: A computer-implemented method for segmenting an input image, the method comprises: generating a first segmentation of the input image using a first machine learning system, the first segmentation comprising multiple segments; receiving, from a user, at least one indication, wherein each indication corresponds to a particular segment from the multiple segments, and indicates one or more locations of the input image as belonging to that particular segment; constructing, for each segment of the multiple segments having at least one corresponding indication, a respective geodesic distance map, based on the input image and the user indications received for that segment; and generating a second segmentation using a second machine learning system based on the input image and the constructed geodesic distance maps.

Abstract: A computer system and corresponding method are used to assist in planning a trajectory for a surgical insertion into a skull to a target representing an anatomical region.

Abstract: A system and method are provided for analysing a functional magnetic resonance imaging (MRI) scan representing a time-sequence, comprising t time points, of images comprising v voxels, where each scan can be represented by a data matrix X?t×v. The method comprises modelling the scan data X as the convolution of neural activation time courses N?+t×v and a haemodynamic filter ?, and performing an inverse operation to estimate N from X and ?. The method further compasses decomposing the neural activation time courses N into multiple brain network components by representing N as the product of a first matrix H defining, for each component, a spatial map of the voxels belonging to that component, and a second matrix W defining, for each component, the time sequence of activation of that component during the scan. In other implementations, the matrix decomposition may be performed before the deconvolution.

Abstract: An apparatus is configured for performing a computer-implemented method comprising: receiving data comprising physical measurements of a biological organ across a three-dimensional (3D) volume, the organ having a hierarchical structure of elements with multiple levels; transforming the physical measurement data into a two-dimensional (2D) data representation having first and second axes, wherein the first axis corresponds to location of an element a spatial path through the three-dimensional volume based on the hierarchical structure of the organ, and the second axis corresponds to descending successive levels through said hierarchical structure; and outputting the two-dimensional data representation to an apparatus for display.

Abstract: A computer implemented method of identifying contacts of an electrode implanted into the brain of a subject via bolts through the skull of the subject, based on an image of the subject, the method comprising: identifying at least one bolt region of the image corresponding to a bolt; identifying one or more contact regions of the image corresponding to electrode contacts; determining contact regions associated with an identified bolt region by searching for identified contact regions, the search being performed based on a search axis extending from the identified bolt region, the direction of the search axis being determined based on the identified bolt region.

Abstract: A computer-implemented method for segmenting an input image, the method comprises: generating a first segmentation of the input image using a first machine learning system, the first segmentation comprising multiple segments; receiving, from a user, at least one indication, wherein each indication corresponds to a particular segment from the multiple segments, and indicates one or more locations of the input image as belonging to that particular segment; constructing, for each segment of the multiple segments having at least one corresponding indication, a respective geodesic distance map, based on the input image and the user indications received for that segment; and generating a second segmentation using a second machine learning system based on the input image and the constructed geodesic distance maps.

Abstract: A computer system and corresponding method are used to assist in planning a trajectory for a surgical insertion into a skull to a target representing an anatomical region.

Abstract: An apparatus is configured for performing a computer-implemented method comprising: receiving data comprising physical measurements of a biological organ across a three-dimensional (3D) volume, the organ having a hierarchical structure of elements with multiple levels; transforming the physical measurement data into a two-dimensional (2D) data representation having first and second axes, wherein the first axis corresponds to location of an element a spatial path through the three-dimensional volume based on the hierarchical structure of the organ, and the second axis corresponds to descending successive levels through said hierarchical structure; and outputting the two-dimensional data representation to an apparatus for display.

Abstract: A system and method are provided for using a computer system to assist in planning a trajectory (960A, 960B) for a surgical insertion into a skull. The method comprises providing the computer system with a three-dimensional representation of the skull and of critical objects located within the skull, wherein the critical objects comprise anatomical features to be avoided during the surgical insertion. The method further comprises providing the computer system with a target location (770, 970) for the insertion within the skull. The method further comprises generating by the computer system a first set comprising a plurality of entry points, each entry point (760) representing a surface location on the skull, and each entry point (760) being associated (2D) with a trajectory (960A, 960B) from the entry point (760) to the target location (770, 970).

Abstract: An apparatus and method are provided for performing phase unwrapping for an acquired magnetic resonance (MR) image. The method includes modelling the MR phase in the MR image using a Markov random field (MRF) in which the true phase ?(t) and the wrapped phase ?(w) are modelled as random variables such that at voxel i of said MR image ?(t)(i)=?(w)(i)+2?n(i), where n(i) is an unknown integer that needs to be estimated for each voxel i. The method further includes constructing a graph consisting of a set of vertices V and edges E and two special terminal vertices representing a source s and sink t, where there is a one-to-one correspondence between cuts on the graph and configurations of the MRF, a cut representing a partition of the vertices V into disjoint sets S and T such that s?S and t?T.

Abstract: One embodiment of the invention provides a computer-implemented method of annotating images in a data set comprising a first set of images which initially have annotations and a second set of images which initially do not have annotations. The method comprises the steps of determining spatial correspondences for all pairs of images in the data set, wherein each spatial correspondence represents a mapping of a location in a first image to a corresponding location in a second image. For each mapping, the method further comprises calculating a connection strength between the location in the first image and the corresponding location in the second image.

Abstract: A system and method are provided for using a computer system to assist in planning a trajectory (960A, 960B) for a surgical insertion into a skull. The method comprises providing the computer system with a three-dimensional representation of the skull and of critical objects located within the skull, wherein the critical objects comprise anatomical features to be avoided during the surgical insertion. The method further comprises providing the computer system with a target location (770, 970) for the insertion within the skull. The method further comprises generating by the computer system a first set comprising a plurality of entry points, each entry point (760) representing a surface location on the skull, and each entry point (760) being associated (2D) with a trajectory (960A, 960B) from the entry point (760) to the target location (770, 970).

Abstract: An apparatus and method are provided for performing phase unwrapping for an acquired magnetic resonance (MR) image. The method includes modelling the MR phase in the MR image using a Markov random field (MRF) in which the true phase ?(t) and the wrapped phase ?(w) are modelled as random variables such that at voxel i of said MR image ?(t)(i)=?(w)(i)+2?n(i), where n(i) is an unknown integer that needs to be estimated for each voxel i. The method further includes constructing a graph consisting of a set of vertices V and edges E and two special terminal vertices representing a source s and sink t, where there is a one-to-one correspondence between cuts on the graph and configurations of the MRF, a cut representing a partition of the vertices V into disjoint sets S and T such that s?S and t?T.

Abstract: One embodiment of the invention provides a computer-implemented method of annotating images in a data set comprising a first set of images which initially have annotations and a second set of images which initially do not have annotations. The method comprises the steps of determining spatial correspondences for all pairs of images in the data set, wherein each spatial correspondence represents a mapping of a location in a first image to a corresponding location in a second image. For each mapping, the method further comprises calculating a connection strength between the location in the first image and the corresponding location in the second image.

Abstract: An apparatus and a computer-implemented method are provided for determining a location in a target image (T) of a site on a surface of a physical object using two or more reference images (I1, I2) of said physical object that have been obtained with a reference imaging device. Each of said two or more reference images includes said site on the surface of the physical object and was obtained with the reference imaging device having a different position and/or orientation relative to said physical object. The target image is obtained by a target imaging device and includes the site on the surface of the physical object. For each reference image, a set of feature mappings from the reference image to the target image is used to determine the epipolar geometry between the reference image and the target image, and a projection of the site from the reference image onto the target image is calculated from said epipolar geometry.