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 for providing a result data set includes providing a first planning image that maps a first physiological phase of a motion of an object under examination, wherein the first planning image contains planning information about a planned positioning of a medical object in the object under examination. The method further includes acquiring a first monitoring image that maps the first physiological phase of the motion of the object under examination and the medical object arranged in the object under examination. The method further includes providing the result data set: (a) based on the first planning image and positioning information, which is determined by identification of a mapping of the medical object in the first monitoring image, or (b) based on the planning information and the first monitoring image.

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: 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: 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: 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: 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 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: 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: A method and system for simulating blood flow in a vessel of a patient to estimate hemodynamic quantities of interest using enhanced blood flow computations based on invasive physiological measurements of the patient is disclosed. Non-invasive patient data including medical image data is received and a patient-specific anatomical model the patient's vessels is generated. Invasive physiological measurements of the patient are received and a computational blood flow model is personalized using the invasive physiological measurements. Blood flow is simulated in the patient-specific anatomical model and one or more hemodynamic quantities of interest are computed using the personalized computational blood flow model.

Abstract: A method for determining a clinical characteristic of a body vessel segment including providing, to a computing device, a three-dimensional reconstruction of a body vessel containing the body vessel segment. A segmented angiography recording of the body vessel segment is provided to the computing device. The computing device extracts at least one global feature of the body vessel from the three-dimensional reconstruction and extracts at least one local feature of the body vessel segment from the angiography recording. The clinical characteristic is determined for the body vessel segment as a function of the at least one extracted local feature and the at least one extracted global feature.

Abstract: A method for planning treatment of a stenosis in a vascular segment includes providing a geometric description of the vascular segment on a computer and determining a course of a hemodynamic parameter of the vascular segment along the vascular segment based on the geometric description provided by the computer. The computer calculates a mathematical derivative of the hemodynamic parameter over the length of the vascular segment along the vascular segment. At least one length section is specified for the vascular segment, and a value of the hemodynamic parameter in a distal end region of the vascular segment is simulated for a treatment device introduced virtually into the specified length section as a function of the mathematical derivative. The treatment of the stenosis including the introduction of the treatment device into the specified length section is planned as a function of the simulated value for the hemodynamic parameter.

Abstract: A method and system are provided for at least symbolically reconstructing a reconstruction data set of at least one vessel segment in a vessel tree of a patient. Input data for the reconstruction comprises at least two two-dimensional angiographic projection images taken in different acquisition geometries. At least one first angiographic projection image showing the vessel segment is acquired. An evaluation measure is automatically determined for each first angiographic projection image using three-dimensional preliminary information for the vessel segment. The evaluation measure describes the suitability of the at least one angiographic projection image for reconstructing the reconstruction data set. When a quality criterion evaluating the evaluation measure is not fulfilled, at least one additional acquisition geometry is determined using the three-dimensional preliminary information and/or the evaluation measure.

Abstract: A method and a corresponding system for assessing a haemodynamic parameter for a vascular region of interest of a patient based on angiographic images are provided. After acquiring multiple angiographic images, a three dimensional (3D) representation of at least a first portion of the respective region of interest is performed, and geometric features are extracted from complete or partial views. Additional geometric features are extracted from partial incomplete views. A complete set of 3D geometric features for an anatomical structure, such as a vessel tree, is then generated by combining the extracted geometric features and estimating any missing geometric features. Using the complete set of 3D geometric features, a feature-based assessment of the haemodynamic parameter, such as a fractional flow reserve, is then performed.

Abstract: Systems and methods are provided for evaluating the complexity of a stenosis or a section of a vessel. At least one image of the stenosis or the section of the vessel is provided. A geometrical feature value of the stenosis and/or or the section of the vessel is identified from the at least one image. At least one intensity feature value is determined based on a grey level intensity of the stenosis or the section of the vessel from the at least one image. A complexity value relating to the geometrical complexity of the stenosis or the section of the vessel is calculated as a function of the at least one geometrical feature value and the at least one intensity feature value of the stenosis or the section of the vessel.

Abstract: A method for segmenting a two-dimensional angiographic recording of a vessel of a body using a computing apparatus includes providing a three-dimensional reconstruction of the vessel of the body to the computing apparatus. The two-dimensional angiographic recording of the vessel of the body is provided on the computing apparatus. The three-dimensional reconstruction of the vessel of the body is registered with the two-dimensional recording of the vessel of the body. Spatial information of the three-dimensional reconstruction is projected onto the two-dimensional recording, and the two-dimensional recording is segmented using the spatial information projected onto the two-dimensional recording.

Abstract: A method and system for determining hemodynamic indices, such as fractional flow reserve (FFR), for a location of interest in a coronary artery of a patient is disclosed. Medical image data of a patient is received. Patient-specific coronary arterial tree geometry of the patient is extracted from the medical image data. Geometric features are extracted from the patient-specific coronary arterial tree geometry of the patient. A hemodynamic index, such as FFR, is computed for a location of interest in the patient-specific coronary arterial tree based on the extracted geometric features using a trained machine-learning based surrogate model. The machine-learning based surrogate model is trained based on geometric features extracted from synthetically generated coronary arterial tree geometries.

Abstract: A method for operating an x-ray device, (e.g., a fluoroscope), is described herein. The method includes: creating planning information for a therapeutic intervention into a body vessel segment based on a reconstruction of the body vessel segment; providing the planning information to a processing unit of the x-ray device; providing the reconstruction of the body vessel segment to the processing unit; creating a recording of the body vessel segment introduced into a recording region of the x-ray device; registering the reconstruction of the body vessel segment with the body vessel segment in the recording region of the x-ray device; displaying the recording of the body vessel segment on a display device of the x-ray device; and superimposing a graphical representation of the planning information on the recording displayed on the display device, in order to increase the efficiency of the therapeutic intervention into the body vessel segment.

Abstract: The disclosure relates to a device and a method for ascertaining at least one individual fluid-dynamic characteristic parameter of a stenosis in a vascular segment having a plurality of serial stenoses, wherein angiography image data of the vascular segment is received from an angiography recording device, geometry data of the vascular segment is ascertained by an analysis device based on the angiography image data and combined into a segment model. At least one division point located between two of the stenoses respectively is ascertained by a dividing device in the segment model, the segment model is subdivided into subsegment models at each of the at least one division points, and the respective fluid-dynamic characteristic parameter is ascertained by a simulation device for at least one of the subsegment models based on respective geometry data of the subsegment model.

Abstract: A method and a corresponding system for assessing a haemodynamic parameter for a vascular region of interest of a patient based on angiographic images are provided. After acquiring multiple angiographic images, a three dimensional (3D) representation of at least a first portion of the respective region of interest is performed, and geometric features are extracted from complete or partial views. Additional geometric features are extracted from partial incomplete views. A complete set of 3D geometric features for an anatomical structure, such as a vessel tree, is then generated by combining the extracted geometric features and estimating any missing geometric features. Using the complete set of 3D geometric features, a feature-based assessment of the haemodynamic parameter, such as a fractional flow reserve, is then performed.