Abstract: Methods, systems, and apparatus for brain tractography by shading fiber bundles. In one aspect, a method includes forwarding patient brain data for presentation to a user; receiving, from the user, a selection of a brain parcel in response to presentation of the patient brain data; forwarding, for display to the user, tract health data comprising i) tract data for tracts connected to the brain parcel and ii) at least one metric for the tracts, the metric reflecting the health of the tracts; and taking an action in response to forwarding the tract health data.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for harmonizing diffusion tensor images. One of the methods includes obtaining a diffusion tensor image; determining a set of RISH features for the diffusion tensor image; processing a model input generated from the set of RISH features using a machine learning model to generate a model output identifying an image transformation from a set of image transformations, wherein each image transformation in the set of image transformations corresponds to a respective different first MRI scanner and represents a transformation that, when applied to first diffusion tensor images captured by the first MRI scanner, harmonizes the first diffusion tensor images with second diffusion tensor images captured by a reference MRI scanner; and processing the diffusion tensor image using the identified image transformation to generate a harmonized diffusion tensor image.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating a mental health prediction for a patient using a centrality ranking of the brain of the patient. One of the methods includes obtaining brain data of a patient, wherein the brain data comprises, for each of a plurality of pairs of parcellations formed from a set of parcellations where each pair comprises a first parcellation and a second parcellation, data characterizing a number of tracts connecting the first parcellation and the second parcellation; determining a network graph from the brain data; generating, for each of a plurality of nodes in the network graph, a measure of centrality of the node; determining a centrality ranking of the plurality of nodes of the network graph according to the respective measures of centrality; generating a mental health prediction for the patient using the determined centrality ranking.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for selecting automatically a machine learning model that locates region(s) of the brain of a subject that is/are associated with a clinically relevant outcome. One of the methods includes: receiving a brain image dataset of a subject; receiving, from a user, an indication of a patient outcome of interest; selecting, based on the indication of a patient outcome of interest, a model from a plurality of models to produce a selected model; determining brain data of interest for the patient outcome of interest; determining, using the selected model, subject specific brain data of interest based on the brain image dataset of the subject and on the brain data of interest; and taking an action based on the subject specific brain data of interest.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for grouping brain parcellation data. One of the methods includes receiving brain parcellation data for a subject; receiving an indication from a user of a brain function category; forwarding data for display, the data comprising a set of functions within the brain function category; receiving a selection from the user of a brain function from the set of functions within the brain function category; determining a subset of the brain parcellation data for parcellations that have an overlap with the selected brain function where the overlap exceeds a threshold; and taking an action based on the determined subset of the brain parcellation data for parcellations that have an overlap with the selected brain function where the overlap exceeds a threshold.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining and visualizing contribution values of different brain regions to a medical condition. One of the methods includes receiving brain data for a brain of a patient, processing the brain data to determine a partition of the data into a plurality of brain parcellation pairs, receiving an indication of a medical condition, determining a contribution value for at least some of the plurality of brain parcellation pairs, where the contribution value characterizes a contribution of the brain parcellation pair to the medical condition, and providing the contribution values for display on a user computing device.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for harmonizing diffusion tensor images. One of the methods includes obtaining a diffusion tensor image; determining a set of RISH features for the diffusion tensor image; processing a model input generated from the set of RISH features using a machine learning model to generate a model output identifying an image transformation from a set of image transformations, wherein each image transformation in the set of image transformations corresponds to a respective different first MRI scanner and represents a transformation that, when applied to first diffusion tensor images captured by the first MRI scanner, harmonizes the first diffusion tensor images with second diffusion tensor images captured by a reference MRI scanner; and processing the diffusion tensor image using the identified image transformation to generate a harmonized diffusion tensor image.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for harmonizing diffusion tensor images. One of the methods includes obtaining a diffusion tensor image; determining a set of RISH features for the diffusion tensor image; processing a model input generated from the set of RISH features using a machine learning model to generate a model output identifying an image transformation from a set of image transformations, wherein each image transformation in the set of image transformations corresponds to a respective different first MRI scanner and represents a transformation that, when applied to first diffusion tensor images captured by the first MRI scanner, harmonizes the first diffusion tensor images with second diffusion tensor images captured by a reference MRI scanner; and processing the diffusion tensor image using the identified image transformation to generate a harmonized diffusion tensor image.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating a mental health prediction for a patient using a centrality ranking of the brain of the patient. One of the methods includes obtaining brain data of a patient, wherein the brain data comprises, for each of a plurality of pairs of parcellations formed from a set of parcellations where each pair comprises a first parcellation and a second parcellation, data characterizing a number of tracts connecting the first parcellation and the second parcellation; determining a network graph from the brain data; generating, for each of a plurality of nodes in the network graph, a measure of centrality of the node; determining a centrality ranking of the plurality of nodes of the network graph according to the respective measures of centrality; generating a mental health prediction for the patient using the determined centrality ranking.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating a mental health prediction for a patient using a centrality ranking of the brain of the patient. One of the methods includes obtaining brain data of a patient, wherein the brain data comprises, for each of a plurality of pairs of parcellations formed from a set of parcellations where each pair comprises a first parcellation and a second parcellation, data characterizing a number of tracts connecting the first parcellation and the second parcellation; determining a network graph from the brain data; generating, for each of a plurality of nodes in the network graph, a measure of centrality of the node; determining a centrality ranking of the plurality of nodes of the network graph according to the respective measures of centrality; generating a mental health prediction for the patient using the determined centrality ranking.