A method for high spatial and temporal resolution dynamic contrast enhanced magnetic resonance imaging using a random subsampled Cartesian k-space using a Poisson-disk random pattern acquisition strategy and a compressed sensing reconstruction algorithm incorporating magnitude image subtraction is presented. One reconstruction uses a split-Bregman minimization of the sum of the L1 norm of the pixel-wise magnitude difference between two successive temporal frames, a fidelity term and a total variation (TV) sparsity term.

Systems and methods for analyzing perfusion-weighted medical imaging using deep neural networks are provided. In some aspects, a method includes receiving perfusion-weighted imaging data acquired from a subject using a magnetic resonance (“MR”) imaging system and modeling at least one voxel associated with the perfusion-weighted imaging data using a four-dimensional (“4D”) convolutional neural network. The method also includes extracting spatio-temporal features for each modeled voxel and estimating at least one perfusion parameter for each modeled voxel based on the extracted spatio-temporal features. The method further includes generating a report using the at least one perfusion parameter indicating perfusion in the subject.

An exemplary system, method, and computer-accessible medium for generating a gadolinium (“Gd”) enhanced map(s) of a portion(s) of a patient(s), can include, for example, receiving magnetic resonance imaging (MRI) information of the portion(s), and generating the Gd enhanced map(s) based on the MRI information using a machine learning procedure(s). The Gd enhanced map(s) can be a full dosage Gd enhanced map. The full dosage Gd enhanced map(s) can be a full dosage Gd enhanced cerebral blood volume map(s). The machine learning procedure can be a convolutional neural network. The MRI information can include (i) a low-dosage Gd MRI scan(s), or (ii) a Gd-free MRI scan(s). A Gd contrast can be generated in the Gd enhanced map(s) using a T2-weighted MRI image of the portion(s).

A method for performing flow analysis in a target volume of a moving organ having a long axis, such as the heart, from 4D MR Flow volumetric image data set of such organ, wherein such data set comprises structural information and three-directional velocity information of the target volume over time, the devices, program products and methods comprising, under control of one or more computer systems configured with specific executable instructions: a) deriving from the 4D MR Flow volumetric image data set at least one derived image data set related to the long axis of the moving organ, for example, by using a multi planar reconstruction; b) determining at least one feature of interest in the 4D MR Flow volumetric image data set or in said derived image data set. The feature of interest may be determined, for example, by receiving input from a user or by performing automatic detection steps on the 4D MR Flow volumetric image data set; c) tracking the feature of interest within the 4D MR Flow volumetric image data set or in the derived image data set; d) determining the spatial orientation over time of a plane containing the feature of interest in the 4D MR Flow volumetric image data set; e) performing quantitative flow analysis using velocity information on the plane as determined in step d). A corresponding device and computer program are also disclosed.

Embodiments access a pre-neoadjuvant chemotherapy (NAC) radiological image of a region of tissue demonstrating breast cancer (BCa), the region of tissue including a tumoral region, the image having a plurality of pixels; extract a set of patches from the tumoral region; provide the set of patches to a convolutional neural network (CNN) configured to discriminate tissue that will experience pathological complete response (pCR) post-NAC from tissue that will not; receive, from the CNN, a pixel-level localized patch probability of pCR; compute a distribution of predictions across analyzed patches based on the pixel-level localized patch probability; classify the region of tissue as a responder or non-responder based on the distribution of predictions, and display the classification. Embodiments may further generate a probability mask based on the pixel-level localized patch probability; and generate a heatmap of likelihood of response to NAC based on the probability mask and the pre-NAC radiological image.

Systems and methods are disclosed for a simultaneous 3D T.sub.1 and B.sub.1.sup.+ mapping technique based on VFA imaging using a reference region VFA (RR-VFA) approach to eliminate the need for a separate B.sub.1.sup.+ mapping scan while imaging the prostate. The RR-VFA method assumes the existence of a reference region that is distributed throughout the volume of interest and is well characterized by a known T.sub.1 relaxation time. In particular, fat is generally selected as the reference region due to its distribution in the body. B.sub.1.sup.+ inhomogeneity is estimated in the fat tissue and interpolated over the entire volume of interest, thus eliminating the need for an additional scan.

The invention provides for a medical imaging system (100, 300, 500) comprising a processor (104). Machine executable instructions cause the processor to: receive (200) magnetic resonance data (120) comprising discrete data portions (612) that are rotated in k-space; bin (202) the discrete data portions into predetermined motion bins (122) using a motion signal value; reconstruct (204) a reference image (124) for each of the predetermined motion bins; construct (206) a motion transform (126) between the reference images; bin (208) a chosen group (610) of the discrete data portions into a chosen time bin (128). Generate an enhanced image (130) for the chosen time bin using the chosen group of the discrete data portions and the motion transform of each of the chosen group to correct the discrete data portions.

A method for determining quantitative parameters for dynamic contrast-enhanced MR data includes acquiring a set of contrast-enhanced MR data for a region of interest using a T1-weighted pulse sequence, generating at least one contrast concentration curve based on the set of contrast-enhanced MR data, accessing a comprehensive dictionary of contrast concentration curves and generating a grouped dictionary that has a plurality of groups based on the comprehensive dictionary. Each group includes a plurality of correlated contrast concentration curves and a group representative signal for the group. The method also includes comparing a contrast concentration curve with the group representative signal of each group to select a group, comparing the contrast concentration curve to the plurality of correlated contrast concentration curves in the selected group to identify a set of quantitative parameters for the concentration curve and generating a report including the set of quantitative parameter.

Embodiments access a radiological image of tissue having a tumoral volume and a peritumoral volume; define a vasculature associated with the tumoral volume; generate a Cartesian two-dimensional (2D) vessel network representation; compute a first set of localized Hough transforms based on the Cartesian 2D vessel network representation; generate a first aggregated set of peak orientations based on the first set of Hough transforms; generate a spherical 2D vessel network representation; compute a second set of localized Hough transforms based on the spherical 2D vessel network representation; generate a second aggregated set of peak orientations based on the second set of Hough transforms; generate a vascular network organization descriptor based on the aggregated peak orientations; compute a probability that the tissue is a member of a positive class based on the vascular network organization descriptor; classify the ROI based on the probability; and display the classification.

Apparatus for operating MRI is disclosed. The apparatus comprises: a control for operating an MRI scanner to carry out an MRI scan; an input for receiving first and second MRI scans respectively at the beginning and end of a predetermined time interval post contrast administration; a subtraction map former for forming a subtraction map from the first and the second MRI scans by analyzing the scans to distinguish between a population in which contrast clearance from the tissue is slower than contrast accumulation, and a population in which clearance is faster than accumulation; and an output to provide an indication of distribution of the populations. The control is configured to carry out the first scan at least five minutes and no more than twenty minutes post contrast administration and to carry out the second scan such that the predetermined time period is at least twenty minutes.