Systems and methods for automated assessment of a vessel are provided. One or more input medical images of a vessel of a patient are received. A plurality of vessel assessment tasks for assessing the vessel is performed using a machine learning based model trained using multi-task learning. The plurality of vessel assessment tasks comprises segmentation of reference walls of the vessel from the one or more input medical images and segmentation of lumen of the vessel from the one or more input medical images. Results of the plurality of vessel assessment tasks are output.

A computing system (118) includes a computer readable storage medium (122) with computer executable instructions (124), including a biophysical simulator (126) and an electrocardiogram signal analyzer (128). The computing system further includes a processor (120) configured to execute the electrocardiogram signal analyzer determine myocardial infarction characteristics from an input electrocardiogram and to execute the biophysical simulator to simulate a fractional flow reserve or an instant wave-free ratio index from input cardiac image data and the determined myocardial infarction characteristics.

Disclosed are an apparatus and method for medical image processing according to pathologic lesion properties, the method including: recognizing a readout area different from an original readout area in a medical image by applying a previously trained deep learning model to the medical image, extracting properties, which include at least one of a location and a size of the readout area, from the medical image, and generating a readout image for the readout area, which is different from the original readout area corresponding to a purpose of taking the medical image, by reconstructing the medical image, thereby having an effect on generating a readout image for a different kind of pathologic lesion from a previously acquired medical image.

Methods are provided for dynamically visualizing information in image data of an object of interest of a patient, which include an offline phase and an online phase. In the offline phase, first image data of the object of interest acquired with a contrast agent is obtained with an interventional device is present in the first image data. The first image data is used to generate a plurality of roadmaps of the object of interest. A plurality of reference locations of the device in the first image data is determined, wherein the plurality of reference locations correspond to the plurality of roadmaps. In the online phase, live image data of the object of interest acquired without a contrast agent is obtained with the device present in the live image data, and a roadmap is selected from the plurality of roadmaps. A location of the device in the live image data is determined. The reference location of the device corresponding to the selected roadmap and the location of the device in the live image data is used to transform the selected roadmap to generate a dynamic roadmap of the object of interest. A visual representation of the dynamic roadmap is overlaid on the live image data for display. In embodiments, the first image data of the offline phase covers different of phases of the cardiac cycle of the patient, and the plurality of roadmaps generated in the offline phase covers the different phases of the patient's cardiac cycle. Related systems and program storage devices are also described and claimed.

Systems and methods are provided for enhanced heart medical imaging operations, particularly as by incorporating use of artificial intelligence (AI) based fetal heart functional analysis and/or real-time and automatic ejection fraction (EF) measurement and analysis.

The invention relates to a system (1) for reviewing 3D or 4D medical image data (2), the system (1) comprising (a) a medical review application (MRA) (4) comprising a processing module (6) configured to process a 3D or 4D dataset (2) to generate 3D content (8), and a 2D user interface (16); wherein the 2D user interface (16) is configured to display the 3D content (8) and to allow a user (30) to generate user input (18) commands; (b) an extended reality (XR)-based user interface add-on (XRA) (100); and (c) a data exchange channel (10), the data exchange channel (10) being configured to interface the processing module (6) with the XRA (100); wherein the XRA (100) is configured to interpret and process the 3D content (8) and convert it to XR content displayable to the user (30) in an XR environment (48); wherein the XR environment (48) is configured to allow a user to generate user input (18) events, and the XRA (100) is configured to process the user input (18) events and convert them to user input (18) commands readable by the MRA (4). The invention also relates to an extended reality-based user interface add-on (100), a related method for analysing a 3D or 4D dataset (2), and a related computer program.

Disclosed herein is a medical system (100, 300) comprising a memory (110) storing machine executable instructions (120) and an image segmentation algorithm (122). The image segmentation algorithm is configured for outputting one or more prede-termined anatomical regions within initial magnetic resonance imaging data (124) descriptive of a predetermined field of view (109) of a subject (318). The medical system further comprises a computational system (104), wherein execution of the machine executable in-structions causes the computational system to: receive (200) the initial magnetic resonance imaging data (124); receive (202) the image segmentation comprising the one or more anatomical regions within the magnetic resonance imaging data in response to inputting the initial magnetic resonance imaging data into the image segmentation algorithm; select (204) at least one of the one or more anatomical regions as a selected image portion (128) using a predetermined criterion; and reduce (206) image intensity within the selected image.

An apparatus includes an imaging probe and is configured for dynamically arranging presentation of visual feedback for guiding manual adjustment, via the probe, of a location, and orientation, associated with the probe. The arranging is selectively based on comparisons between fields of view of the probe and respective results of segmenting image data acquired via the probe. In an embodiment, the apparatus includes a sensor which guides a decision that acoustic coupling quality is insufficient, the apparatus issuing a user alert upon the decision.

The present disclosure relates to an image processing method, a storage medium and a mapping system. An imageological image including a plurality of tomographic images is acquired. A three-dimensional reconstruction is performed according to the plurality of tomographic images to obtain a three-dimensional image model. The three-dimensional image model includes a three-dimensional myocardial fibrosis region image. A three-dimensional electroanatomic model including a three-dimensional abnormal myocardial tissue image is acquired. Since there is a certain correlation between an abnormal myocardial tissue region in the three-dimensional electroanatomic model and myocardial fibrosis, the three-dimensional image model and the three-dimensional electroanatomic model are registered, and an overlapping part of the three-dimensional myocardial fibrosis region image and the three-dimensional abnormal myocardial tissue image is determined as the location of a lesion. Therefore, the accurate positioning of a lesion location is realized, which effectively improves the surgery success rate.

A training method and apparatus for angiography image processing and a method and apparatus for automatically processing a vessel image. The training method includes obtaining training data that includes original angiography image data and local segmentation result data of a side branch vessel. The local segmentation result data of the side branch vessel are local segmentation image data of the side branch vessel on a main branch vessel determined from an original angiography image. A neural network is trained according to the obtained training data to make the neural network perform local segmentation on the side branch vessel on the determined main branch vessel in the original angiography image. The training method can obtain the neural network for performing local segmentation on the side branch vessel, thereby realizing improvement of segmentation accuracy while improving segmentation efficiency, and avoiding missing segmentation and wrong segmentation of the side branch vessel.