Abstract: Methods and apparatus for cross-domain medical image analysis and cross-domain medical image synthesis using deep image-to-image networks and adversarial networks are disclosed. In a method for cross-domain medical image analysis a medical image of a patient from a first domain is received. The medical image is input to a first encoder of a cross-domain deep image-to-image network (DI2IN) that includes the first encoder for the first domain, a second encoder for a second domain, and a decoder. The first encoder converts the medical image to a feature map and the decoder generates an output image that provides a result of a medical image analysis task from the feature map.

Abstract: Systems and method are described for medical image segmentation. A medical image of a patient in a first domain is received. The medical image comprises one or more anatomical structures. A synthesized image in a second domain is generated from the medical image of the patient in the first domain using a generator of a task driven generative adversarial network. The one or more anatomical structures are segmented from the synthesized image in the second domain using a dense image-to-image network of the task driven generative adversarial network. Results of the segmenting of the one or more anatomical structures from the synthesized image in the second domain represent a segmentation of the one or more anatomical structures in the medical image of the patient in the first domain.

Abstract: For non-invasive EP mapping, a sparse number of electrodes (e.g., 10 in a typical 12-lead ECG exam setting) are used to generate an EP map without requiring preoperative 3D image data (e.g. MR or CT). An imager (e.g., a depth camera) captures the surface of the patient and may be used to localize electrodes in any positioning on the patient. Two-dimensional (2D) x-rays, which are commonly available, and the surface of the patient are used to segment the heart of the patient. The EP map is then generated from the surface, heart segmentation, and measurements from the electrodes.

Abstract: Methods and apparatus for cross-domain medical image analysis and cross-domain medical image synthesis using deep image-to-image networks and adversarial networks are disclosed. In a method for cross-domain medical image analysis a medical image of a patient from a first domain is received. The medical image is input to a first encoder of a cross-domain deep image-to-image network (DI2IN) that includes the first encoder for the first domain, a second encoder for a second domain, and a decoder. The first encoder converts the medical image to a feature map and the decoder generates an output image that provides a result of a medical image analysis task from the feature map.

Abstract: For registration of medical images with deep learning, a neural network is designed to include a diffeomorphic layer in the architecture. The network may be trained using supervised or unsupervised approaches. By enforcing the diffeomorphic characteristic in the architecture of the network, the training of the network and application of the learned network may provide for more regularized and realistic registration.

Abstract: An artificial intelligence agent is machine trained and used to provide physically-based rendering settings. By using deep learning and/or other machine training, settings of multiple rendering parameters may be provided for consistent imaging even in physically-based rendering.

Abstract: A probe pose is detected in fluoroscopy medical imaging. The pose of the probe through a sequence of fluoroscopic images is detected. The detection relies on an inference framework for visual tracking overtime. By applying visual tracking, the pose through the sequence is consistent or the pose at one time guides the detection of the probe at another time. Single frame drop-out of detection may be avoided. Verification using detection of the tip of the probe and/or weighting of possible detections by separate detection of markers on the probe may further improve the accuracy.

Abstract: The disclosure relates to a method of determining a transformation between coordinate frames of sets of image data. The method includes receiving a model of a structure extracted from first source image data, the first source image data being generated according to a first imaging modality and having a first data format, wherein the model has a second data format, different from the first data format. The method also includes determining, using an intelligent agent, a transformation between coordinate frames of the model and first target image data, the first target image data being generated according to a second imaging modality different to the first imaging modality.

Abstract: A method and apparatus for convolutional neural network (CNN) regression based 2D/3D registration of medical images is disclosed. A parameter space zone is determined based on transformation parameters corresponding to a digitally reconstructed radiograph (DRR) generated from the 3D medical image. Local image residual (LIR) features are calculated from local patches of the DRR and the X-ray image based on a set of 3D points in the 3D medical image extracted for the determined parameter space zone. Updated transformation parameters are calculated based on the LIR features using a hierarchical series of regressors trained for the determined parameter space zone. The hierarchical series of regressors includes a plurality of regressors each of which calculates updates for a respective subset of the transformation parameters.

Abstract: Systems and methods are provided for determining a set of imaging parameters for an imaging system. A selection of an image is received from a set of images. A modification of certain quality measures is received for the selected image. The modified selected image is mapped to a set of imaging parameters of an imaging system based on the certain quality measures using a trained Deep Reinforcement Learning (DRL) agent.

Abstract: Systems and methods are provided for identifying pathological changes in follow up medical images. Reference image data is acquired. Follow up image data is acquired. A deformation field is generated for the reference image data and the follow up data using a machine-learned network trained to generate deformation fields describing healthy, anatomical deformation between input reference image data and input follow up image data. The reference image data and the follow up image data are aligned using the deformation field. The co-aligned reference image data and follow up image data are analyzed for changes due to pathological phenomena.

Abstract: A method and system for 3D/3D medical image registration. A digitally reconstructed radiograph (DRR) is rendered from a 3D medical volume based on current transformation parameters. A trained multi-agent deep neural network (DNN) is applied to a plurality of regions of interest (ROIs) in the DRR and a 2D medical image. The trained multi-agent DNN applies a respective agent to each ROI to calculate a respective set of action-values from each ROI. A maximum action-value and a proposed action associated with the maximum action value are determined for each agent. A subset of agents is selected based on the maximum action-values determined for the agents. The proposed actions determined for the selected subset of agents are aggregated to determine an optimal adjustment to the transformation parameters and the transformation parameters are adjusted by the determined optimal adjustment.

Abstract: For three-dimensional rendering, a machine-learnt model is trained to generate representation vectors for rendered images formed with different rendering parameter settings. The distances between representation vectors of the images to a reference are used to select the rendered image and corresponding rendering parameters that provides a consistency with the reference. In an additional or different embodiment, optimized pseudo-random sequences are used for physically-based rendering. The random number generator seed is selected to improve the convergence speed of the renderer and to provide higher quality images, such as providing images more rapidly for training compared to using non-optimized seed selection.

Abstract: Systems and methods are provided for performing medical imaging analysis. Input medical imaging data is received for performing a particular one of a plurality of medical imaging analyses. An output that provides a result of the particular medical imaging analysis on the input medical imaging data is generated using a neural network trained to perform the plurality of medical imaging analyses. The neural network is trained by learning one or more weights associated with the particular medical imaging analysis using one or more weights associated with a different one of the plurality of medical imaging analyses. The generated output is outputted for performing the particular medical imaging analysis.

Abstract: Pose of a probe is detected in x-ray medical imaging. Since the TEE probe is inserted through the esophagus of a patient, the pose is limited to being within the esophagus. The path of the esophagus is determined from medical imaging prior to the intervention. During the intervention, the location in 2D is found from one x-ray image at a given time. The 3D probe location is provided by assigning the depth of the esophagus at that 2D location to be the depth of the probe. A single x-ray image may be used to determine the probe location in 3D, allowing for real-time pose determination without requiring space to rotate a C-arm during the intervention.

Abstract: Methods and systems for image registration using an intelligent artificial agent are disclosed. In an intelligent artificial agent based registration method, a current state observation of an artificial agent is determined based on the medical images to be registered and current transformation parameters. Action-values are calculated for a plurality of actions available to the artificial agent based on the current state observation using a machine learning based model, such as a trained deep neural network (DNN). The actions correspond to predetermined adjustments of the transformation parameters. An action having a highest action-value is selected from the plurality of actions and the transformation parameters are adjusted by the predetermined adjustment corresponding to the selected action. The determining, calculating, and selecting steps are repeated for a plurality of iterations, and the medical images are registered using final transformation parameters resulting from the plurality of iterations.

Abstract: A method and system for deep learning based cardiac electrophysiological model personalization is disclosed. Electrophysiological measurements of a patient, such as an ECG trace, are received. A computational cardiac electrophysiology model is personalized by calculating patient-specific values for a parameter of the computational cardiac electrophysiology model based at least on the electrophysiological measurements of the patient using a trained deep neural network (DNN). The parameter of the computational cardiac electrophysiology model corresponds to a spatially varying electrical cardiac tissue property.

Abstract: An artificial intelligence agent is machine trained and used to provide physically-based rendering settings. By using deep learning and/or other machine training, settings of multiple rendering parameters may be provided for consistent imaging even in physically-based rendering.

Abstract: An artificial intelligence agent is machine trained and used to provide physically-based rendering settings. By using deep learning and/or other machine training, settings of multiple rendering parameters may be provided for consistent imaging even in physically-based rendering.

Abstract: An artificial intelligence agent is machine trained and used to provide physically-based rendering settings. By using deep learning and/or other machine training, settings of multiple rendering parameters may be provided for consistent imaging even in physically-based rendering.