Embodiments herein disclose a method and system for staging diabetic kidney disease using deep learning techniques. An image capturing unit captures a set of ophthalmic images of a user. The ophthalmic images set undergoes pre-processing before being fed to a first deep learning module. The first deep learning module extracts pathological data indicative of vascular abnormalities from the pre-processed set of ophthalmic images. The first deep learning module quantifies the extracted pathological data, and maps them to a stage of diabetic retinopathy and urine protein levels. A second deep learning module receives as input the quantified pathological data, the mapped diabetic retinopathy stage and urine protein levels, and clinical and demographic parameters. Based on this input, the second deep learning module predicts a stage of diabetic kidney disease.

A system and method are provided that includes acquiring or accessing x-ray data of a subject experiencing a delivery of a contrast agent to the vessel of the subject and generating time-attenuation curves for the vessel using the x-ray data. The method also includes identifying a plurality of points within the vessel and extending along a lumen of the vessel and sampling the time-attenuation curves at the plurality of points to generate a time-attenuation map. The method further includes performing a Fourier transform on the time-attenuation map to generate a spatio-temporal map of spatial frequency versus temporal frequency and identifying a peak frequency in the spatio-temporal map corresponding to flow or velocity in the vessel. The method then includes quantifying the flow or velocity within the vessel of the subject using the peak frequency and generating a report including quantified flow or velocity through the vessel.

In some embodiments, the present disclosure relates to a method that includes accessing data stored in an electronic memory. The data includes digitized imaging data from a segmented non-contrast computerized tomography (CT) image of an obstructive coronary artery disease (OCAD) patient. A plurality of assessment features are extracted from the data. The plurality of assessment features include image based features that characterize one or more of calcifications, fat tissue, heart structures, bone density, muscle, a lung, and breast tissue. The plurality of assessment features and a plurality of clinical factors are provided to a machine learning stage that is configured to generate a medical assessment corresponding to whether or not the OCAD patient would benefit from additional diagnostic tests to identify a presence and extent of the obstructive coronary artery disease.

Provided herein are methods of generating optimized models of vascular grafts for subjects in certain embodiments. Methods of treating subjects in need of vascular grafts are also provided. Related systems and computer program products are additionally provided.

A computer implemented method for training a whole medical image foundation model, including: receiving a plurality of medical image datasets; extracting local sections of image data from the plurality of medical image datasets; obtaining one or more causal variables associated with the local sections and/or patient; training one or more self-supervised learning models based on the local sections of image data and the causal variables; combining the one or more trained self-supervised learning models with a deep learning network configured to combine a latent representation of the local sections of image data from the one or more trained self-supervised learning models into a patient-level representation; and combining, with the one or more trained self-supervised learning models and the deep learning network, at least one further network or function configured to accept the patient-level representation as input, the at least one further network or function operable to perform one or more patient-specific prediction tasks.

A method of performing 3D vessel tree reconstruction includes providing segmented binary angiography images, applying a distance transform to the images, and generating distance transformed binary angiography images. The set of distance transformed binary angiography images are provided to a trained 3D vessel reconstruction machine learning model capable of reconstructing 3D vessels. The 3D vessel tree reconstruction machine learning model includes a multi-stage convolutional neural network comprising a multi-stage architecture with (i) a vessel centerline stage, and (ii) a radius reconstruction stage. Resultant 3D reconstructed vessel trees may be used in performing clinical assessment of coronary vessel health, and occlusion.

Digital images are used for time-based mapping of metabolic activity within a selected anatomy of a subject, particularly within a brain of the subject. Machine learning algorithms receive magnetic resonance image (MRI) data and four-dimensional dynamic positron emission tomography (dPET) data of the brain. A tracer may be applied prior to the anatomical scanning, and the MRI data is co-registered with the dPET data. A convolutional neural network (CNN) outputs localized data frames and a probability distribution for respective localized data frames. The probability distribution corresponds to a section of the subject's anatomy, such as internal carotid arteries, being visible in each of the respective localized data frames. The chosen section of the anatomy is segmented from the visible frames and a model-corrected input function (MCIF) for blood flow is calculated to compute a Ki map that illustrates influx of the tracer into the preferred anatomical portion.

A method for quantitative mapping of vasa vasorum density within and adjacent to the coronary arterial wall using contrast-enhanced coronary CT angiography scans, including time-resolved perfusion, multi-energy material decomposition, and longitudinal functional monitoring of vasa vasorum dynamics.

Example systems and techniques are disclosed that may determine a three-dimensional (3D) model of a coronary vasculature of a patient. An example system may include memory configured to store the 3D model and processing circuitry communicatively coupled to the memory. The processing circuitry may be configured to obtain first fluoroscopy imaging data from a first viewing angle and obtain second fluoroscopy imaging data from a second viewing angle. The processing circuitry may be configured to determine the 3D model of the coronary vasculature of the patient based on the first fluoroscopy imaging data and the second fluoroscopy imaging data. The processing circuitry is configured to obtain additional imaging data from one or more imagers other than a fluoroscopy imager and update the 3D model based on the additional imaging data. The processing circuitry may be configured to output for display a representation of the 3D model.

A smart echocardiography (ECHO) system includes a processor programmed to access a two-stage machine-learning (ML) model for analyzing echocardiograms. The two-stage ML model is trained to output a validated cardiac profile of a patient having improved accuracy based upon an inputted echocardiogram. The processor is further programmed to receive echocardiographic imaging data of a patient from the inputted echocardiogram and execute a first-stage of the two-stage ML model to generate an initial cardiac profile based on the echocardiographic imaging data. The initial cardiac profile includes a plurality of cardiac parameters each having a parameter value. The processor is further programmed to execute a second stage of the two-stage ML model on the initial cardiac profile by executing a plurality of validation calculations using the plurality of cardiac parameters and associated parameter values to generate a validated cardiac profile for the patient and output the validated cardiac profile.