Abstract: Systems and methods for determining a 3D centerline of a vessel are provided. A current state observation of an artificial agent is determined based on one or more image view sets, each including 2D medical images of a vessel, a current position of the artificial agent in the 2D medical images, and a start position and a target position in the 2D medical images. Policy values are calculated for a plurality of actions for moving the artificial agent in 3D based on the current state observation using a trained machine learning model. The artificial agent is moved according to a particular action based on the policy values. The steps of determining, calculating, and moving are repeated for a plurality of iterations to move the artificial agent along a 3D path between the start position and the target position. The 3D centerline of the vessel is determined as the 3D path.

Abstract: A method and system for fast non-invasive computer-based computation of a hemodynamic index, such as fractional flow reserve (FFR) from medical image data of a patient is disclosed. A patient-specific anatomical model of one or more arteries of a patient is automatically generated based on medical image data of the patient. Regions in the automatically generated patient-specific anatomical model for which user feedback is required for accurate computation of a hemodynamic index are predicted using one or more trained machine learning models.

Abstract: Systems and methods for determining a 3D centerline of a vessel are provided. A current state observation of an artificial agent is determined based on one or more image view sets, each including 2D medical images of a vessel, a current position of the artificial agent in the 2D medical images, and a start position and a target position in the 2D medical images. Policy values are calculated for a plurality of actions for moving the artificial agent in 3D based on the current state observation using a trained machine learning model. The artificial agent is moved according to a particular action based on the policy values. The steps of determining, calculating, and moving are repeated for a plurality of iterations to move the artificial agent along a 3D path between the start position and the target position. The 3D centerline of the vessel is determined as the 3D path.

Abstract: Systems and methods for determining myocardium strain and intracardiac blood flow data of the heart are provided. Input medical imaging data of a heart of a patient is received. At least one of extracted myocardium strain data of the heart and extracted intracardiac blood flow data of the heart is determined from the input medical imaging data. At least one of predicted myocardium strain data of the heart and predicted intracardiac blood flow data of the heart is determined based on the at least one of the extracted myocardium strain data and the extracted intracardiac blood flow data using a model of the heart. The model of the heart jointly models myocardium strain of the heart and intracardiac blood flow of the heart. The at least one of the predicted myocardium strain of the heart and the predicted intracardiac blood flow of the heart is output.

Abstract: Systems and methods are provided for training an artificial intelligence model for detecting calcified portions of a vessel in an input medical image. One or more first medical images of a vessel in a first modality and one or more second medical image of the vessel in a second modality are received. Calcified portions of the vessel are detected in the one or more first medical images, The artificial intelligence model is trained for detecting calcified portions of the vessel in the input medical image in the second modality based on the one or more second medical images and the detected calcified portions of the vessel detected in the one or more first medical images.

Abstract: A method includes processing at least one input dataset (using a multi-level processing algorithm, one or more of the at least one input dataset comprising imaging data of an echocardiography of a cardiovascular system of a patient. The multi-level processing algorithm comprises a multi-task level and a consolidation-task level. An input of the consolidation-task level is coupled to an output of the multi-task level. The multi-task level is configured to determine multiple diagnostic metrics of the cardiovascular system based on the at least one input dataset. The consolidation-task level is configured to determine a fitness of the cardiovascular system of the patient.

Abstract: Systems and methods for automatically detecting a disease in medical images are provided. Input medical images are received. A plurality of metrics for a disease is computed for each of the input medical images. The input medical images are clustered into a plurality of clusters based on one or more of the plurality of metrics to classify the input medical images. The plurality of clusters comprise a cluster of one or more of the input medical images associated with the disease and one or more clusters of one or more of the input medical images not associated with the disease. In one embodiment, the disease is COVID-19 (coronavirus disease 2019).

Abstract: A computer-implemented method for personalized assessment of patients with acute coronary syndrome (ACS) includes extracting (i) patient-specific coronary geometry data from one or more medical images of a patient; (ii) a plurality of features of a patient-specific coronary arterial tree based on the patient-specific coronary geometry data; and (iii) a plurality of ACS-related features from additional patient measurement data. A surrogate model is used to predict patient-specific hemodynamic measures of interest related to ACS based on the plurality of features of the patient-specific coronary arterial tree and the plurality of ACS-related features from the additional patient measurement data.

Abstract: Systems and methods for computing a transformation for correction motion between a first medical image and a second medical image are provided. One or more landmarks are detected in the first medical image and the second medical image. A first tree of the anatomical structure is generated from the first medical image based on the one or more landmarks detected in the first medical image and a second tree of the anatomical structure is generated from the second medical image based on the one or more landmarks detected in the second medical image. The one or more landmarks detected in the first medical image are mapped to the one or more landmarks detected in the second medical image based on the first tree and the second tree. A transformation to align the first medical image and the second medical image is computed based on the mapping.

Abstract: Systems and methods are provided for assessing collateral circulation of a patient. Patient data of a patient is received. A collateral circulation score is computed based on the patient data using a trained machine learning network. The collateral circulation score represents functioning of collateral circulation of the patient. The collateral circulation score is output.

Abstract: Systems and methods for performing a simulation for an anatomical object of interest are provided. A physiological model of an anatomical object of interest of a patient is generated. Electroanatomical mapping data of the anatomical object of interest is received. The physiological model is updated based on the electroanatomical mapping data of the anatomical object of interest. A simulation for the anatomical object of interest is performed using the updated physiological model. Results of the simulation are output.

Abstract: Machine-based risk prediction or assistance is provided for peri-procedural complication, such as peri-procedural myocardial infarction (PMI). A machine-learned model is used to predict risk of PMI and/or recommend courses of action to avoid PMI in PCI. Various combinations of types or modes of information are used in the prediction, such as both imaging and non-imaging data. The prediction may be made prior to, during, and/or after PCI using the machine-learned model to more quickly reduce the chance of PMI. The workflows for prior, during, and/or post PCI incorporate the risk prediction and/or risk-based recommendations to reduce PMI for patients.

Abstract: Systems and methods for computing a transformation for correction motion between a first medical image and a second medical image are provided. One or more landmarks are detected in the first medical image and the second medical image. A first tree of the anatomical structure is generated from the first medical image based on the one or more landmarks detected in the first medical image and a second tree of the anatomical structure is generated from the second medical image based on the one or more landmarks detected in the second medical image. The one or more landmarks detected in the first medical image are mapped to the one or more landmarks detected in the second medical image based on the first tree and the second tree. A transformation to align the first medical image and the second medical image is computed based on the mapping.

Abstract: In hemodynamic determination in medical imaging, the classifier is trained from synthetic data rather than relying on training data from other patients. A computer model (in silico) may be perturbed in many different ways to generate many different examples. The flow is calculated for each resulting example. A bench model (in vitro) may similarly be altered in many different ways. The flow is measured for each resulting example. The machine-learnt classifier uses features from medical scan data for a particular patient to estimate the blood flow based on mapping of features to flow learned from the synthetic data. Perturbations or alterations may account for therapy so that the machine-trained classifier may estimate the results of therapeutically altering a patient-specific input feature. Uncertainty may be handled by training the classifier to predict a distribution of possibilities given uncertain input distribution.

Abstract: A first sequence of cardiac image frames are received by a first neural network of the neural network system. The first neural network outputs a first set of feature values. The first set of feature values includes a plurality of data subsets, each corresponding to a respective image frame and relating to spatial features of the respective image frame. The first set of feature values are received at a second neural network of the neural network system. The second neural network outputs a second set of feature values relating to temporal features of the spatial features. Based on the second set of feature values, a cardiac phase value relating to a cardiac phase associated with a first image frame is determined.

Abstract: Systems and methods for retraining a trained machine learning model are provided. One or more input medical images are received. Measures of interest for a primary task and a secondary task are predicted from the one or more input medical images using a trained machine learning model. The predicted measures of interest for the primary task and the secondary task are output. User feedback on the predicted measure of interest for the secondary task is received. The trained machine learning model is retrained for predicting the measures of interest for the primary task and the secondary task based on the user feedback on the output for the secondary task.

Abstract: Systems and methods are provided for assessing collateral circulation of a patient. Patient data of a patient is received. A collateral circulation score is computed based on the patient data using a trained machine learning network. The collateral circulation score represents functioning of collateral circulation of the patient. The collateral circulation score is output.

Abstract: In hemodynamic determination in medical imaging, the classifier is trained from synthetic data rather than relying on training data from other patients. A computer model (in silico) may be perturbed in many different ways to generate many different examples. The flow is calculated for each resulting example. A bench model (in vitro) may similarly be altered in many different ways. The flow is measured for each resulting example. The machine-learnt classifier uses features from medical scan data for a particular patient to estimate the blood flow based on mapping of features to flow learned from the synthetic data. Perturbations or alterations may account for therapy so that the machine-trained classifier may estimate the results of therapeutically altering a patient-specific input feature. Uncertainty may be handled by training the classifier to predict a distribution of possibilities given uncertain input distribution.

Abstract: A method and system for personalized blood flow modeling based on wearable sensor networks is disclosed. A personalized anatomical model of vessels of a patient is generated based on initial patient data. Continuous cardiovascular measurements of the patient are received from a wearable sensor network on the patient. A computational blood flow model for simulating blood flow in the patient-specific anatomical model of the vessels of the patient is personalized based on the continuous cardiovascular measurements from the wearable sensor network. Blood flow and pressure in the patient-specific anatomical model of the vessels of the patient are simulated using the personalized computational blood flow model. Hemodynamic measures of interest for the patient are computed based on the simulated blood flow and pressure.

Abstract: Systems and methods for generating an ablation map identifying target ablation locations on a heart of a patient are provided. One or more input medical images of a heart of a patient and a voltage map of the heart of the patient are received. An ablation map identifying target ablation locations on the heart is generated using one or more trained machine learning based models based on the one or more input medical images and the voltage map. The ablation map is output.