A method of quantitatively evaluating a cognitive impairment 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 impairment and predict its future change based on the at least one feature obtained.

A computer implemented method is provided. The method includes establishing, via multiple processors, a continuous federated learning framework including a global model at a global site and respective local models derived from the global model at respective local sites. The method also includes retraining or retuning, via the multiple processors, the global model and the respective local models without sharing actual datasets between the global site and the respective local sites but instead sharing synthetic datasets generated from the actual datasets.

A medical image diagnostic apparatus according to an embodiment includes processing circuitry. The processing circuitry is configured to obtain image data which is generated by scanning a brain of a subject; select a target region from the image data; extract a connected region of which a brain function is associated with a brain function of the target region, as an additional region; and output scan target region including the target region and the additional region.

A medical image processing apparatus comprises processing circuitry configured to: obtain image data representative of a brain of a subject; obtain data representing a clinical sign or symptom of the subject, wherein the clinical sign or symptom is relevant to a brain condition; process the image data to obtain an estimation of an abnormality in the brain of the subject; and determine whether the estimation of the abnormality is consistent with the data representing the clinical sign or symptom.

Systems and techniques for generating and/or employing a medical imaging stroke model are presented. In one example, a system employs a convolutional neural network to generate output data regarding a brain anatomical region based on diffusion-weighted imaging (DWI) data associated with the brain anatomical region and apparent diffusion coefficient (ADC) data associated with the brain anatomical region. The system also detects presence or absence of a medical stroke condition associated with the brain anatomical region based on the output data.

Presented are concepts for adapting a first, pre-defined mesh topology representing an organ to a second, different mesh topology of the organ. One such concept includes identifying correspondence between the first and second mesh topologies based on spectral matching of the first and second mesh topologies. The first, predefined mesh topology is aligned with the second mesh topology based on the identified correspondence between the first and second mesh topologies.

A two-stage medical image registration method based on progressive images (PIs) to solve the technical problem of low registration accuracy of traditional image registration methods includes: merging a reference image with a floating image to generate multiple intermediate PIs; registering, by a speeded-up robust features (SURF) algorithm and an affine transformation, the floating image with the intermediate PIs to acquire coarse registration results; registering, by the SURF algorithm and the affine transformation, the reference image with the coarse registration results to acquire fine registration results; and comparing the fine registration results of the intermediate PIs, which are acquired by iteration, and selecting an optimal registration result as a final registration image. The method can achieve multimodal registration for brain imaging with MI, NCC, MSD, and NMI superior to those of the existing registration algorithms. The method effectively improves the registration accuracy through the progressive medical image registration strategy.

A localized evaluation network incorporates a discriminator acting as classifier, which may be included within a generative adversarial network (GAN). GAN may include a generative network such as U-NET for creating segmentations. The localized evaluation network is trained on image pairs including medical images of organs of interest and segmentation (mask) images. The network is trained to distinguish whether an image pair does or does not represent the ground truth. GAN examines interior layers of the discriminator and evaluates how much each localized image region contributes to the final classification. The discriminator may analyze regions of the image pair that contribute to a classification by analyzing layer weights of the machine learning model. Disclosed embodiments include a visual attribute, such as a heat map, that represents contributions of localized regions of a contour to an overall confidence score. These localized regions may be highlighted and reported for quality assurance review.

Embodiments described herein provide for receiving a second image comprising an overlay depicting an organ-at-risk (OAR) segmentations. The overlay is generated by a first machine learning model based on a first image depicting the anatomical region of a current patient. A second machine learning model receives the second image and set of third images depicting prior patient OAR segmentations on which the second machine learning model was trained. The second machine learning model classifies the second image as one of a set of class names and characterizes the extent to which the second image is similar to, or dissimilar to, images with the same class name in the set of third images. The characterization may be based on outputs of internal layers of the second machine learning model. Dimensionality reduction may be performed on the outputs of the internal layers to present the outputs in a form comprehendible by humans.

Systems and methods for diagnosis of Parkinson's disease (PD) using machine learning are disclosed. In one embodiment, a method may include receiving, on at least one processor, data, comprising one or more Magnetic Resonance Images (MRI) from a human subject; preprocessing the one or more MRIs; applying one or more Convolutional Neural Networks (CNNs) to perform image analysis of the one or more MRIs; applying one or more Generative Adversarial Networks (GANs) to augment a dataset of artificial scans for classification training; outputting, using the at least one processor, a classification based on the one or more MRI images a diagnosis of the subject for PD.