Abstract: A network is machine trained to estimate flow by spatial location based on input of anatomy information. A medical scan of tissue may be used to generate flow information without the delay or difficulty of performing a medical scan configured for flow imaging or CFD. Anatomy imaging is used to provide flow estimates with the speed provided by the machine-learned network.

Abstract: A method and system for virtual percutaneous valve implantation is disclosed. A patient-specific anatomical model of a heart valve is estimated based on 3D cardiac medical image data and an implant model representing a valve implant is virtually deployed into the patient-specific anatomical model of the heart valve. A library of implant models, each modeling geometrical properties of a corresponding valve implant, is maintained. The implant models maintained in the library are virtually deployed into the patient specific anatomical model of the heart valve to select an implant type and size and deployment location and orientation for percutaneous valve implantation.

Abstract: Intelligent multi-scale image parsing determines the optimal size of each observation by an artificial agent at a given point in time while searching for the anatomical landmark. The artificial agent begins searching image data with a coarse field-of-view and iteratively decreases the field-of-view to locate the anatomical landmark. After searching at a coarse field-of view, the artificial agent increases resolution to a finer field-of-view to analyze context and appearance factors to converge on the anatomical landmark. The artificial agent determines applicable context and appearance factors at each effective scale.

Abstract: A learning-based magnetic resonance fingerprinting (MRF) reconstruction method for reconstructing an MR image of a tissue space in an MR scan subject for a particular MR sequence is disclosed. The method involves using a machine-learning algorithm that has been trained to generate a set of tissue parameters from acquired MR signal evolution without using a dictionary or dictionary matching.

Abstract: Embodiments can provide a method for atlas-based contouring, comprising constructing a relevant atlas database; selecting one or more optimal atlases from the relevant atlas database; propagating one or more atlases; fusing the one or more atlases; and assessing the quality of one or more propagated contours.

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: A method and system for anatomical landmark detection in medical images using deep neural networks is disclosed. For each of a plurality of image patches centered at a respective one of a plurality of voxels in the medical image, a subset of voxels within the image patch is input to a trained deep neural network based on a predetermined sampling pattern. A location of a target landmark in the medical image is detected using the trained deep neural network based on the subset of voxels input to the trained deep neural network from each of the plurality of image patches.

Abstract: A network is machine trained to estimate flow by spatial location based on input of anatomy information. A medical scan of tissue may be used to generate flow information without the delay or difficulty of performing a medical scan configured for flow imaging or CFD. Anatomy imaging is used to provide flow estimates with the speed provided by the machine-learned network.

Abstract: Systems and methods for non-invasive assessment of an arterial stenosis, comprising include segmenting a plurality of mesh candidates for an anatomical model of an artery including a stenosis region of a patient from medical imaging data. A hemodynamic index for the stenosis region is computed in each of the plurality of mesh candidates. It is determined whether a variation among values of the hemodynamic index for the stenosis region in each of the plurality of mesh candidates is significant with respect to a threshold associated with a clinical decision regarding the stenosis region.

Abstract: A method and apparatus for deep learning based fine-grained body part recognition in medical imaging data is disclosed. A paired convolutional neural network (P-CNN) for slice ordering is trained based on unlabeled training medical image volumes. A convolutional neural network (CNN) for fine-grained body part recognition is trained by fine-tuning learned weights of the trained P-CNN for slice ordering. The CNN for fine-grained body part recognition is trained to calculate, for an input transversal slice of a medical imaging volume, a normalized height score indicating a normalized height of the input transversal slice in the human body.

Abstract: For three-dimensional segmentation from two-dimensional intracardiac echocardiography imaging, the three-dimension segmentation is output by a machine-learnt multi-task generator. Rather than the brute force approach of training the generator from 2D ICE images to output a 2D segmentation, the generator is trained from 3D information, such as a sparse ICE volume assembled from the 2D ICE images. Where sufficient ground truth data is not available, computed tomography or magnetic resonance data may be used as the ground truth for the sample sparse ICE volumes. The generator is trained to output both the 3D segmentation and a complete volume (i.e., more voxels represented than in the sparse ICE volume). The 3D segmentation may be further used to project to 2D as an input with an ICE image to another network trained to output a 2D segmentation for the ICE image. Display of the 3D segmentation and/or 2D segmentation may guide ablation of tissue in the patient.

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: A method and system for determining fractional flow reserve (FFR) for a coronary artery stenosis of a patient is disclosed. In one embodiment, medical image data of the patient including the stenosis is received, a set of features for the stenosis is extracted from the medical image data of the patient, and an FFR value for the stenosis is determined based on the extracted set of features using a trained machine-learning based mapping. In another embodiment, a medical image of the patient including the stenosis of interest is received, image patches corresponding to the stenosis of interest and a coronary tree of the patient are detected, an FFR value for the stenosis of interest is determined using a trained deep neural network regressor applied directly to the detected image patches.

Abstract: Methods and systems for artificial intelligence based medical image segmentation are disclosed. In a method for autonomous artificial intelligence based medical image segmentation, a medical image of a patient is received. A current segmentation context is automatically determined based on the medical image and at least one segmentation algorithm is automatically selected from a plurality of segmentation algorithms based on the current segmentation context. A target anatomical structure is segmented in the medical image using the selected at least one segmentation algorithm.

Abstract: Systems and methods are provided for automatic segmentation of a vessel. A sequence of image slices containing a vessel is acquired. Features maps are generated for each of the image slices using a trained fully convolutional neural network. A trained bi-directional recurrent neural network generates a segmented image based on the feature maps.

Abstract: A method and system for determining fractional flow reserve (FFR) for a coronary artery stenosis of a patient is disclosed. In one embodiment, medical image data of the patient including the stenosis is received, a set of features for the stenosis is extracted from the medical image data of the patient, and an FFR value for the stenosis is determined based on the extracted set of features using a trained machine-learning based mapping. In another embodiment, a medical image of the patient including the stenosis of interest is received, image patches corresponding to the stenosis of interest and a coronary tree of the patient are detected, an FFR value for the stenosis of interest is determined using a trained deep neural network regressor applied directly to the detected image patches.

Abstract: Systems and methods for generating synthesized images are provided. An input medical image of a patient in a first domain is received. A synthesized image in a second domain is generated from the input medical image of the patient in the first domain using a first generator. The first generator is trained based on a comparison between segmentation results of a training image in the first domain from a first segmentor and segmentation results of a synthesized training image in the second domain from a second segmentor. The synthesized training image in the second domain is generated by the first generator from the training image in the first domain. The synthesized image in the second domain is output.

Abstract: A method and apparatus for machine learning based detection of vessel orientation tensors of a target vessel from a medical image is disclosed. For each of a plurality of voxels in a medical image, such as a computed tomography angiography (CTA), features are extracted from sampling patches oriented to each of a plurality of discrete orientations in the medical image. A classification score is calculated for each of the plurality of discrete orientations at each voxel based on the features extracted from the sampling patches oriented to each of the plurality of discrete orientations using a trained vessel orientation tensor classifier. A vessel orientation tensor at each voxel is calculated based on the classification scores of the plurality of discrete orientations at that voxel.

Abstract: A method and apparatus for extracting centerline representations of vascular structures in medical images is disclosed. A vessel orientation tensor for each of a plurality of voxels associated with the target vessel, such as a coronary artery, in a medical image, such as a coronary tomography angiography (CTA) image, using a trained vessel orientation tensor classifier. A flow field is estimated for the plurality of voxels associated with the target vessel in the medical image based on the vessel orientation tensor estimated for each of the plurality of voxels. A centerline of the target vessel is extracted based on the estimated flow field for the plurality of vessels associated with the target vessel in the medical image by detecting a path that carries maximum flow.

Abstract: A method and apparatus for automatically performing medical image analysis tasks using deep image-to-image network (DI2IN) learning. An input medical image of a patient is received. An output image that provides a result of a target medical image analysis task on the input medical image is automatically generated using a trained deep image-to-image network (DI2IN). The trained DI2IN uses a conditional random field (CRF) energy function to estimate the output image based on the input medical image and uses a trained deep learning network to model unary and pairwise terms of the CRF energy function. The DI2IN may be trained on an image with multiple resolutions. The input image may be split into multiple parts and a separate DI2IN may be trained for each part. Furthermore, the multi-scale and multi-part schemes can be combined to train a multi-scale multi-part DI2IN.