Abstract: A method of mesoscopic photogrammetry can be carried out using a set of images captured from a camera on a mobile computing device. Upon receiving the set of images, the method generates a composite image, which can include applying homographic rectification to warp all images of the set of images onto a common plane; applying a rectification model to undo perspective distortion in each image of the set of images; and applying an undistortion model for adjusting for camera imperfections of a camera that captured each image of the set of images. A height map is generated co-registered with the composite image, for example, by using an untrained CNN whose weights/parameters are optimized in order to optimize the height map. The height map and the composite image can be output for display.

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: A method of performing computational image contrast from multidimensional data includes receiving a plurality of images of an object, with each image of the plurality of images having more than three dimensions, performing multi-dimensional registration of the plurality of images to generate a multi-dimensional dataspace, reducing dimensionality of the multi-dimensional dataspace to create an enhanced resolution and contrast image of a 3D space of the object using the plurality of images as registered in the multi-dimensional dataspace, and displaying the enhanced resolution and contrast image. In some cases, reducing the dimensionality of the multi-dimensional dataspace to create the enhanced resolution and contrast image of the 3D space of the object comprises utilizing at least one of variance, high-order statistics, entropy, principal component analysis, t-distributed stochastic neighborhood embedding, and neural networks using the plurality of images as registered in the multi-dimensional dataspace.

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: 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: A tomographic 3D imaging system includes a conic-section mirror serving as the imaging objective, a sample holder positioned to hold a sample at a focus (fp) of the conic-section mirror, a light source directing light to the sample, and an array of camera sensors positioned above the conic-section mirror. In some cases, the array of camera sensors is positioned parallel to a directrix of the conic-section mirror. In some cases, the conic-section mirror is a parabolic mirror. In some cases, each camera sensor of the array of camera sensors is positioned facing the sample holder at an inclination angle dictated by a lateral position of the camera sensor according to ?(r)=2 tan?1(r/2fp), where r is the radial entry position across the parabolic mirror.

Abstract: Introduced herein is a technique that reliably measures on-die noise of logic in a chip. The introduced technique places a noise measurement system in partitions of the chip that are expected to cause the most noise. The introduced technique utilizes a continuous free-running clock that feeds functional frequency to the noise measurement circuit throughout the noise measurement scan test. This allows the noise measurement circuit to measure the voltage noise of the logic during a shift phase, which was not possible in the conventional noise measurement method. Also, by being able to measure the voltage noise during a shift phase and hence in both phases of the scan test, the introduced technique can perform a more comprehensive noise measurement not only during ATE testing but as part of IST in the field.

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: For three-dimensional segmentation from two-dimensional intracardiac echocardiography imaging, the three-dimension segmentation is output by a machine-learnt multi-task generator. The machine-learnt multi-task generator is trained from 3D information, such as a sparse ICE volume assembled from the 2D ICE images. The machine-learnt multi-task generator is trained to output both the 3D segmentation and a complete volume. The 3D segmentation may be 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 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: A method of mesoscopic photogrammetry can be carried out using a set of images captured from a camera on a mobile computing device. Upon receiving the set of images, the method generates a composite image, which can include applying homographic rectification to warp all images of the set of images onto a common plane; applying a rectification model to undo perspective distortion in each image of the set of images; and applying an undistortion model for adjusting for camera imperfections of a camera that captured each image of the set of images. A height map is generated co-registered with the composite image, for example, by using an untrained CNN whose weights/parameters are optimized in order to optimize the height map. The height map and the composite image can be output for display.

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: Systems and methods for imaging based on multiple cross-sectional images acquired at different angles are disclosed. According to an aspect, multiple cross-sectional images of an object are acquired at different angles. The method also includes registering the acquired cross-sectional images. Further, the method includes reconstructing an enhanced resolution image of the object based on the registered images. As a result of registering the images, a distortion map is generated that is coregistered with the high-resolution image. The method also includes displaying an image of the object based on the enhanced resolution image and the distortion map.

Abstract: An anatomical structure is detected (110) in a volume of ultrasound data by identifying (150) the anatomical structure in another volume of ultrasound data and generating (155) an image of the anatomical structure and an anatomical landmark. A group of images are generated (130) of the original volume and compared (140) to the image of the other volume. An image of the group of images is selected (150) as including the anatomical structure based on the comparison.

Abstract: A method of visualizing spinal nerves includes receiving a 3D image volume depicting a spinal cord and a plurality of spinal nerves. For each spinal nerve, a 2D spinal nerve image is generated by defining a surface within the 3D volume comprising the spinal nerve. The surface is curved such that it passes through the spinal cord while encompassing the spinal nerve. Then, the 2D spinal nerve images are generated based on voxels on the surface included in the 3D volume. A visualization of the 2D spinal images is presented in a graphical user interface that allows each 2D spinal image to be viewed simultaneously.

Abstract: Systems and methods are provided for automatic detection and quantification for traumatic bleeding. Image data is acquired using a full body dual energy CT scanner. A machine-learned network detects one or more bleeding areas on a bleeding map from the dual energy CT scan image data. A visualization is generated from the bleeding map. The predicted bleeding areas are quantified, and a risk value is generated. The visualization and risk value are presented to an operator.

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 3D sensing depth camera involves a time-frequency multiplexed frequency-modulated continuous wave (FMCW) LiDAR technique. A sample arm of such a system for 3D depth sensing includes a scanner for beam scanning in a first axis and a diffractive optical element for spectrally encoded scanning along a second axis. The sample arm can further include beam shaping optics such as a collimator and a lens. Processing of an interferogram comprising depth information at a different position along the second axis for each frequency sweep of the light source involves applying a windowed spectral estimator at a particular spectral window size with zero-padding and according to a specified lateral sampling approach.

Abstract: An apparatus and method for coupled medical image formation and medical image signal recovery using a dual domain network is disclosed. The dual-domain network includes a first deep neural network (DNN) to perform signal recovery in a sensor signal domain and a second DNN to perform signal recovery in an image domain. A sensor signal is acquired by a sensor of a medical imaging device. A refined sensor signal is generated from the received sensor signal using the first DNN. A first reconstructed medical image is generated from the received sensor signal. A second reconstructed medical image is generated from the refined sensor signal generated by the first DNN. An enhanced medical image is generated based on the both the first reconstructed medical image and the second reconstructed medical image using the second DNN. The enhanced medical image generated by the second DNN is displayed.

Abstract: Methods and apparatus for automated medical image analysis using deep learning networks are disclosed. In a method of automatically performing a medical image analysis task on a medical image of a patient, a medical image of a patient is received. The medical image is input to a trained deep neural network. An output model that provides a result of a target medical image analysis task on the input medical image is automatically estimated using the trained deep neural network. The trained deep neural network is trained in one of a discriminative adversarial network or a deep image-to-image dual inverse network.