A diffusion-weighted magnetic resonance imaging (MRI) method acquires MRI scan data from a multi-direction, multi-shot, diffusion-weighted MRI scan, and jointly reconstructs from the MRI scan data 1) magnitude images for multiple diffusion-encoding directions and 2) phase images for multiple shots and multiple diffusion-encoding directions using an iterative reconstruction method. Each iteration of the iterative reconstruction method comprises a gradient calculation, a phase update to update the phase images, and a magnitude update to update the magnitude images. Each iteration minimizes a cost function comprising a locally low-rank (LLR) regularization constraint on the magnitude images from the multiple diffusion-encoding directions.

A deep learning model learning device is proposed, including: a parametric MRI image input part inputting an image corresponding to a diagnosis region, inputting at least one parametric MRI image constructed on the basis of parameters different from each other, and constructing and providing an MRI moving image by using the at least one parametric MRI image; a cancer detection model learning part receiving an input of the at least one parametric MRI image and the MRI moving image corresponding to the diagnosis region, and learning a deep learning model on the basis of information labeling the cancer region; a labeling reference information providing part providing at least one reference information contributing to the labeling of the cancer region; and a labeling processing part checking the cancer region input on the basis of the at least one reference information and processing the labeling of the checked cancer region.

A system and a method for mapping lesions or damage instances of a brain. The method includes receiving a lesion segmentation mask for the brain and receiving a tractography atlas. A connectivity damage brain map is constructed from (i) superimposing the lesion segmentation mask and a tractography atlas-based image, and (ii) combining information from the lesion segmentation mask with information from the tractography atlas-based image. The tractography atlas-based image is an image obtained from the tractography atlas, and the tractography atlas-based image and the lesion segmentation mask are registered to a common space.

There is provided a computer implemented method of automatic segmentation of three dimensional (3D) anatomical region of interest(s) (ROI) that includes predefined anatomical structure(s) of a target individual, comprising: receiving 3D images of a target individual, each including the predefined anatomical structure(s), each 3D image is based on a different respective imaging modality. In one implementation, each respective 3D image is inputted into a respective processing component of a multi-modal neural network, wherein each processing component independently computes a respective intermediate, and the intermediate outputs are inputted into a common last convolutional layer(s) for computing the indication of segmented 3D ROI(s). In another implementation, each respective 3D image is inputted into a respective encoding-contracting component a multi-modal neural network, wherein each encoding-contracting component independently computes a respective intermediate output. The intermediate outputs are inputted into a single common decoding-expanding component for computing the indication of segmented 3D ROI(s).

There is provided a computer implemented method of automatic segmentation of three dimensional (3D) anatomical region of interest(s) (ROI) that includes predefined anatomical structure(s) of a target individual, comprising: receiving 3D images of a target individual, each including the predefined anatomical structure(s), each 3D image is based on a different respective imaging modality. In one implementation, each respective 3D image is inputted into a respective processing component of a multi-modal neural network, wherein each processing component independently computes a respective intermediate, and the intermediate outputs are inputted into a common last convolutional layer(s) for computing the indication of segmented 3D ROI(s). In another implementation, each respective 3D image is inputted into a respective encoding-contracting component a multi-modal neural network, wherein each encoding-contracting component independently computes a respective intermediate output. The intermediate outputs are inputted into a single common decoding-expanding component for computing the indication of segmented 3D ROI(s).

The present solution can segment tracts by performing two-pass tractography. The system can first perform deterministic tractography and then probabilistic tractography. The system can use the result from the deterministic tractography to update and refine initial identified regions of interest. The refined regions of interest can be used to filter and select streamlines identified through the probabilistic tractography.

Inventive technology is directed to diffusion weighted magnetic resonance measurements. In an embodiment, a method for performing a diffusion weighted magnetic resonance measurement on a sample includes operating a magnetic resonance scanner to apply a diffusion encoding sequence to the sample. The method also includes operating the magnetic resonance scanner to acquire from the sample one or more echo signals. The diffusion encoding sequence includes a diffusion encoding time-dependent magnetic field gradient g(t) with non-zero components g.sub.l(t) along at least two orthogonal directions y and z, and a b-tensor having at least two non-zero eigenvalues, the magnetic field gradient comprising a first and subsequent second encoding block.

A pre-event connectome of a subject brain is accessed, the pre-event connectome defining i) first functional nodes in the subject brain and ii) first edges that represent connections between the first functional nodes before the subject has undergone an event. A post-event connectome of the subject brain is accessed, the post-event connectome defining i) second functional nodes in the subject brain and ii) second edges that represent connections between the second functional nodes after the subject has undergone the event. A connectome-difference map data is generated that records the difference between the pre-event connectome and the post-event connectome. An action is taken based on the connectome-difference map data.

A method of quantitatively evaluating a cognitive status and its future change from a medical image of an individual's brain, the method comprising scanning the individual's brain with a scanning device so as to acquire at least one medical brain image; processing the medical brain image to obtain at least one feature of the image; using a pre-established prediction model to determine a condition of the cognitive status and predict its future change based on the at least one feature obtained.

Aspects of the disclosure provide a method for denoising an image. The method can include receiving an acquired image from an image acquisition system, and processing the acquired image with a nonlinear diffusion coefficient based filter having a diffusion coefficient that is calculated using gradient vector orientation information in the acquired image.