A method of determining a residue function in brain tissue, from medical images acquired after introducing contrast agent into the blood, correcting for contrast agent leakage into the tissue, comprising: a) providing time signals indicating contrast agent concentration for leaking voxels, a time signal indicating average contrast agent concentration for non-leaking voxels, and an artery input function, all derived from the images; b) fitting the leaking voxel signals to a model time signal with a free parameter for leakage rate, the model assuming that the concentration of contrast agent perfusing through a leaking voxel has a same shape as a function of time as the average contrast agent concentration for non-leaking voxels; c) using the best fit leakage rate parameter to make a correction for leakage to the leaking voxel signals; and d) deconvolving the corrected signals from the artery input function, to find the residue function.

A system and method for evaluating subjects using MRI and a contrast agent that overcomes the low sensitivity nature of previous detection methods is provided by using a 3D golden-angle-based radial sampling approach. In one configuration, direct detection of metabolic H.sub.2.sup.17O generated from mitochondrial respiration may be imaged. Radial encoding allows for the use of ultra-short echo-time to compensate for signal loss due to the short T.sub.2 relaxation time of .sup.17O and other contrast agents. In addition, the golden-ratio-based sampling scheme has the flexibility of enabling various undersampling schemes and retrospective selection of temporal resolution for dynamic imaging. A 3D radial sampling scheme may also give rise to additional SNR gain by further shortening the echo-time.

A method for dynamic contrast enhanced (DCE) image processing and kinetic modeling of an organ's region-of-interest is provided. The method includes deriving at least a contour of an exterior of the organ's region-of-interest from one or more of a plurality of images; generating a spline function in response to the derived contour of the exterior of the organ's region-of-interest from the one or more of the plurality of images; registering the plurality of images wherein the organ's region-of-interest has been segmented; deriving a tracer curve for the organ's region-of-interest in the registered images, the tracer curve indicating a change in concentration of a contrast agent flowing through the organ's region-of-interest over a time period; and kinetic modeling by fitting a kinetic model to the tracer curve to generate one or more maps of tissue physiological parameters associated with the kinetic model.

A medical navigation system is provided for registering a patient for a medical procedure with the medical navigation system using fiducial markers. The fiducial markers are placed on the patient prior to a 3D scan and the fiducial markers each have a target for use with a tracking system. The medical navigation system comprises a 3D scanner, a tracking system, a display, and a controller electrically coupled to the 3D scanner, the tracking system, and the display. The controller has a processor coupled to a memory. The controller is configured to: receive 3D scan data generated by the 3D scanner representative of a 3D scan of at least a portion of the patient, the 3D scan including the fiducial markers visible by the 3D scanner; load from the memory saved medical image data, the saved medical data including preoperative image data saved during a previous scan of at least a portion of the patient; receive position data from the tracking system based on the target for each of the fiducial markers; and perform a transformation mapping to create a single unified virtual coordinate space based on the 3D scan data, the position data, and the medical image data, and updating registration data of the medical navigation system based on the transformation mapping.

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 imaging method may include obtaining imaging data associated with a region of interest (ROI) of an object. The imaging data may correspond to a plurality of time-series images of the ROI. The imaging method may also include determining, based on the imaging data, a data set including a spatial basis and one or more temporal bases. The spatial basis may include spatial information of the imaging data. The one or more temporal bases may include temporal information of the imaging data. The imaging method may also include storing, in a storage medium, the spatial basis and the one or more temporal bases.

An image acquisition unit acquires a phase contrast image consisting of a plurality of phases, in which a pixel value of each pixel represents a velocity of fluid, the phase contrast image being acquired by imaging a subject including a structure inside which fluid flows by a phase contrast magnetic resonance method. An identification unit identifies a region of the structure in the phase contrast image on the basis of a maximum value of the velocity of the fluid between corresponding pixels in each of the phases of the phase contrast image.

Embodiments associated with classifying a region of tissue using features extracted from nodules and surrounding structures. One example apparatus includes a feature extraction circuit configured to automatically extract a first set of quantitative features from a nodule represented in at least one CT image, and automatically extract a second set of quantitative features from the lung parenchyma region immediately surrounding the nodule represented in the at least one CT image; a feature selection circuit configured to select an optimally predictive feature set from the first set of quantitative features and the second set of quantitative features; and a training circuit configured to train a classifier using the optimally predictive feature set to assign malignancy risk to a lung nodule represented in a CT image of a region of tissue demonstrating lung nodules. A prognosis or treatment plan may be provided based on the malignancy risk.

A system and method for automated contrast arrival detection in temporally phased images or datasets of tissues effectively determines contrast arrival in regions that are substantially free of arteries. A plurality of tissue voxels in a plurality of temporally phased images are identified as a function of voxel enhancement characteristics associated with discrete tissue voxels. A processor/process computes average enhancement characteristics from the plurality of identified tissue voxels. The average enhancement characteristics are compared with predetermined average enhancement characteristics associated with contrast media arrival phases. Contrast media arrival phases in the temporally phased images are provided based on the comparison.

Embodiments predict prostate cancer (PCa) biochemical recurrence (BCR) employing an image acquisition circuit that accesses a first pre-treatment image and a second pre-treatment image of a region of tissue demonstrating PCa, a distension feature circuit that extracts a set of distension features from the first pre-treatment image, and computes a first probability of PCa BCR based on the set of distension features, a radiomics circuit that extracts a set of radiomics features from the second pre-treatment image, and computes a second probability of PCa recurrence based on the set of radiomics feature, a combined tumor induced organ distension with tumor radiomics (COnTRa) circuit that computes a joint probability that the region of tissue will experience PCa BCR based on the first probability and the second probability, and a display circuit that displays the joint probability.