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: Systems and methods are provided for enhancing a medical image. An initial medical image having an initial field of view is received. An augmented medical image having an expanded field of view is generated using a trained machine learning model. The expanded field of view comprises the initial field of view and an augmentation region. The augmented medical image is output.

Abstract: Systems and methods for determining a concordance between results of medical assessments are provided. Results of a medical assessment of a first type for an anatomical object of a patient and results of a medical assessment of a second type for the anatomical object are received. The results of the medical assessment of the first type are converted to a hemodynamic measure. A concordance analysis between the results of the medical assessment of the first type and the results of the medical assessment of the second type based on the hemodynamic measure is performed. Results of the concordance analysis 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 determining a robustness of a machine learning based medical analysis network for performing a medical analysis task on input medical data are provided. Input medical data is received. Results of a medical analysis task performed based on the input medical data using a machine learning based medical analysis network are received. A robustness of the machine learning based medical analysis network for performing the medical analysis task is determined based on the input medical data and the results of the medical analysis task using a machine learning based audit network. The determination of the robustness of the machine learning based medical analysis network is output.

Abstract: A method and system for non-invasive assessment and therapy planning for coronary artery disease from medical image data of a patient is disclosed. Geometric features representing at least a portion of a coronary artery tree of the patient are extracted from medical image data. Lesions are detected in coronary artery tree of the patient and a hemodynamic quantity of interest is computed at a plurality of points along the coronary artery tree including multiple points within the lesions based on the extracted geometric features using a machine learning model, resulting in an estimated pullback curve for the hemodynamic quantity of interest.

Abstract: Data privacy is a major concern when accessing and processing sensitive medical data. Homomorphic Encryption (HE) is one technique that preserves privacy while allowing computations to be performed on encrypted data. An encoding method enables typical HE schemes to operate on real-valued numbers of arbitrary precision and size by representing the numbers as a series of polynomial terms.

Abstract: Systems and methods for determining a concordance between results of medical assessments are provided. Results of a medical assessment of a first type for an anatomical object of a patient and results of a medical assessment of a second type for the anatomical object are received. The results of the medical assessment of the first type are converted to a hemodynamic measure. A concordance analysis between the results of the medical assessment of the first type and the results of the medical assessment of the second type based on the hemodynamic measure is performed. Results of the concordance analysis are output.

Abstract: Systems and methods for determining one or more measures of interest for optimizing throughput of a catheterization laboratory are provided. A priori medical procedure data relating to a medical procedure to be performed on a patient in a catheterization laboratory is received. One or more measures of interest are predicted based on the received a priori medical procedure data using a trained machine learning model. The one or more measures of interest include an overall time for performing the medical procedure on the patient in the catheterization laboratory. The one or more predicted measures of interest are output.

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 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: Methods for computing hemodynamic quantities include: (a) acquiring angiography data from a patient; (b) calculating a flow and/or calculating a change in pressure in a blood vessel of the patient based on the angiography data; and (c) computing the hemodynamic quantity based on the flow and/or the change in pressure. Systems for computing hemodynamic quantities and computer readable storage media are described.

Abstract: A machine-learned model classifies disease, such as a CVD type or sub-type. After identifying a link between the pathology (e.g., CVD type or sub-type) and one or more functional and/or anatomical characteristics, machine learning is performed to learn to predict the functional and/or anatomical characteristics from medical data. The trained model is then adapted using few-shot learning to predict the class of disease. As a result of this few-shot learning approach, less training data may be needed for disease classification. A greater number of classifiers trained to classify a greater number of diseases may be created.

Abstract: A value indicative of an ejection fraction, EF, of a cardiac chamber of a heart is based on a temporal sequence of cardiac magnetic resonance, CMR, images of the cardiac chamber. A neural network system has an input layer configured to receive the temporal sequence of a stack of slices of the CMR images along an axis of the heart. The temporal sequence is one or multiple consecutive cardiac cycles of the heart. The neural network system has an output layer configured to output the value indicative of the EF based on the temporal sequence. The neural network system has interconnections between the input layer and the output layer and is trained with a plurality of datasets. Each of the datasets comprises an instance temporal sequence of the stack of slices of the CMR images along the axis over one or multiple consecutive cardiac cycles for the input layer and an associated instance value indicative of the EF for the output layer.

Abstract: A technique for determining a cardiac metric from rest and stress perfusion cardiac magnetic resonance (CMR) images is provided. A neural network system for determining at least one cardiac metric from CMR images comprises an input layer configured to receive at least one CMR image representative of a rest perfusion state and at least one CMR image representative of a stress perfusion state. The neural network system further comprises an output layer configured to output at least one cardiac metric based on the at least one CMR image representative of the rest perfusion state and the at least one CMR image representative of the stress perfusion state. The neural network system with interconnections between the input layer and the output layer is trained by a plurality of datasets.

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: The application relates to a computer implemented method for determining a basal and an apex plane in a set of Magnetic Resonance, MR, image slices of a heart, wherein the set of MR image slices comprises short axis views of the heart obtained over the heartbeat. The set of MR image slices is applied to a multitask deep learning artificial intelligence Model which is configured to identify a basal plane slice and an apex plane slice on the applied set of image slices, wherein the multitask deep learning artificial intelligence model is further configured to determine at least one further parameter of cardiac anatomy or of a cardiac function. A first output of the multitask deep learning artificial intelligence Model is determined as the apex plane slice and a second output as the basal plane slice. At least one further output of the multitask deep learning artificial intelligence Model is determined as the at least one further parameter of the cardiac anatomy or of the cardiac function.

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 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: 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.