Abstract: Techniques are provided for generating enhanced image representations from original X-ray images using deep learning techniques. In one embodiment, a system is provided that includes a memory storing computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can include a reception component, an analysis component, and an artificial intelligence component. The analysis component analyzes the original X-ray image using an AI-based model with respect to a set of features of interest. The AI component generates a plurality of enhanced image representations. Each enhanced image representation highlights a subset of the features of interest and suppresses remaining features of interest in the set that are external to the subset.

Abstract: Techniques are described for domain adaptation of image processing models using post-processing model correction According to an embodiment, a method comprises training, by a system operatively coupled to a processor, a post-processing model to correct an image-based inference output of a source image processing model that results from application of the source image processing model to a target image from a target domain that differs from a source domain, wherein the source image processing model was trained on source images from the source domain. In one or more implementations, the source imaging processing model comprises an organ segmentation model and the post-processing model can comprise a shape-autoencoder. The method further comprises applying, by the system, the source image processing model and the post-processing model to target images from the target domain to generate optimized image-based inference outputs for the target images.

Abstract: A system includes a memory unit comprising a classifier network and a detector network. The classifier network is configured to perform a classification of a scan image among maternal images. The detector network is configured to determine a placenta condition in the scan image. The system further includes a data acquisition unit communicatively coupled to an ultrasound scanner and configured to receive maternal images from a maternal scanning procedure. The system also includes an image processing unit communicatively coupled to the memory unit and the data acquisition unit and configured to select a sagittal image from the maternal images using the classifier network. The image processing unit is further configured to determine a placenta condition based on the selected sagittal image using the detector network. The image processing unit is also configured to provide a recommendation to a medical professional based on the placenta condition.

Abstract: The present approach relates, in some aspects, to a multi-level and a multi-channel frame work for segmentation using model-based or “shallow” classification (i.e. learning processes such as linear regression, clustering, support vector machines, and so forth) followed by deep learning. This framework starts with a very low resolution version of the multi-channel data and constructs an shallow classifier with simple features to generate a coarser level tissue mask that in turn is used to crop patches from the high-resolution volume. The cropped volume is then processed using the trained convolution network to perform a deep learning based segmentation within the slices.

Abstract: The present approach relates, in some aspects, to a multi-level and a multi-channel frame work for segmentation using model-based or “shallow” classification (i.e. learning processes such as linear regression, clustering, support vector machines, and so forth) followed by deep learning. This framework starts with a very low resolution version of the multi-channel data and constructs an shallow classifier with simple features to generate a coarser level tissue mask that in turn is used to crop patches from the high-resolution volume. The cropped volume is then processed using the trained convolution network to perform a deep learning based segmentation within the slices.

Abstract: Identification of an optimal monochromatic energy for displaying monochromatic images is disclosed. In certain embodiments, determination of an optimal monochromatic energy may be performed by generating histograms for various monochromatic images generated based on a set of acquired multi-energy projections and by evaluating the histogram dispersion for the respective histograms.

Abstract: A method includes receiving a Computed Tomography (CT) image comprising a head of a subject from a CT scanner and detecting a first and a second petrous bone of the head in the CT image. The method further includes determining a nasion of the head in the CT image based on the first and the second petrous bone. The method also includes generating a reference plane of the head based on the nasion and the first and the second petrous bone.

Abstract: A method includes receiving a monochromatic image comprising a head of a subject from a Computed Tomography (CT) scanner and detecting a petrous bone of the head in the monochromatic image. The method further includes determining a linear attenuation coefficient of at least one petrous voxel representing the petrous bone and calculating a mass attenuation coefficient of the petrous voxel based on the linear attenuation coefficient and a density of the petrous bone. The method also includes computing a monochromatic energy level of the monochromatic image based on the mass attenuation coefficient of the petrous voxel and recalibrating the monochromatic image corresponding to the computed monochromatic energy level to the desired monochromatic energy level.

Abstract: A method includes receiving a Computed Tomography (CT) image comprising a head of a subject from a CT scanner and detecting a first and a second petrous bone of the head in the CT image. The method further includes determining a nasion of the head in the CT image based on the first and the second petrous bone. The method also includes generating a reference plane of the head based on the nasion and the first and the second petrous bone.

Abstract: A method includes receiving a monochromatic image comprising a head of a subject from a Computed Tomography (CT) scanner and detecting a petrous bone of the head in the monochromatic image. The method further includes determining a linear attenuation coefficient of at least one petrous voxel representing the petrous bone and calculating a mass attenuation coefficient of the petrous voxel based on the linear attenuation coefficient and a density of the petrous bone. The method also includes computing a monochromatic energy level of the monochromatic image based on the mass attenuation coefficient of the petrous voxel and recalibrating the monochromatic image corresponding to the computed monochromatic energy level to the desired monochromatic energy level.

Abstract: A hierarchical multi-object active appearance model (AAM) framework is disclosed for processing image data, such as localizer or scout image data. In accordance with this approach, a hierarchical arrangement of models (e.g., a model pyramid) maybe employed where a global or parent model that encodes relationships across multiple co-located structures is used to obtain an initial, coarse fit. Subsequent processing by child sub-models add more detail and flexibility to the overall fit.

Abstract: The disclosed embodiments relate to determining an amount of a contrast agent in an image. For example, a computer-implemented method of image processing includes generating, from a first polychromatic contrast-enhanced X-ray image obtained at a first energy and a second polychromatic contrast-enhanced X-ray image obtained at a second energy, a simulated first monochromatic contrast-enhanced X-ray image and a simulated second monochromatic contrast-enhanced X-ray image. The simulated first monochromatic contrast-enhanced X-ray image includes first regions of enhanced contrast and the simulated second monochromatic contrast-enhanced includes second regions of enhanced contrast. The method also includes isolating the first and second regions of enhanced contrast from other regions of the image, and determining an amount of the contrast agent within the first and second regions of enhanced contrast based at least on a derived partial signal attributable to the contrast agent.

Abstract: Identification of an optimal monochromatic energy for displaying monochromatic images is disclosed. In certain embodiments, determination of an optimal monochromatic energy may be performed by generating histograms for various monochromatic images generated based on a set of acquired multi-energy projections and by evaluating the histogram dispersion for the respective histograms.

Abstract: An apparatus for multi-energy tissue quantification includes an x-ray imaging system comprises an x-ray source configured to emit a beam of x-rays toward an object to be imaged, a detector configured to receive the x-rays attenuated by the object, and a data acquisition system (DAS) operably coupled to the detector. A computer operably connected to the x-ray source and the DAS is programmed to cause the x-ray source to emit x-rays at each of a first kVp and a second kVp toward the detector, acquire x-ray data from x-rays emitted at the first and second kVp through a region of interest (ROI), and perform a first multi-material decomposition based on the acquired x-ray data. The computer is also programmed to quantify a volume fraction of a first material in the ROI based on the first multi-material decomposition and display the volume fraction of the first material to a user.

Abstract: The disclosed embodiments relate to characterizing or quantifying an element or composition of interest within an imaged volume. In accordance with one embodiment, high and low energy images are acquired of a volume of interest using a polychromatic emission source. The high and low energy images are processed to generate monochromatic images. Based on the observed attenuation within the monochromatic images, one or more elements or compositions of interest are characterized within the imaged volume.

Abstract: A computer-implemented method of post-processing medical image data is provided. The method includes receiving tracked image data representative of multiple blood vessels, generating a binary tree structure for the multiple blood vessels based on a parent-child relationship between branches of the multiple blood vessels, generating a likelihood model for determining a validity of the branches of the multiple blood vessels, and generating a likelihood score for each branch based on the respective branch's compatibility with the likelihood model. The method also includes generating a reconstructed tree for the multiple blood vessels. Compatible branches are included in the reconstructed tree, while invalid branches are not included in the reconstructed tree.

Abstract: An apparatus for multi-energy tissue quantification includes an x-ray imaging system comprises an x-ray source configured to emit a beam of x-rays toward an object to be imaged, a detector configured to receive the x-rays attenuated by the object, and a data acquisition system (DAS) operably coupled to the detector. A computer operably connected to the x-ray source and the DAS is programmed to cause the x-ray source to emit x-rays at each of a first kVp and a second kVp toward the detector, acquire x-ray data from x-rays emitted at the first and second kVp through a region of interest (ROI), and perform a first multi-material decomposition based on the acquired x-ray data. The computer is also programmed to quantify a volume fraction of a first material in the ROI based on the first multi-material decomposition and display the volume fraction of the first material to a user.

Abstract: A computer-implemented method of post-processing medical image data is provided. The method includes receiving tracked image data representative of multiple blood vessels, generating a binary tree structure for the multiple blood vessels based on a parent-child relationship between branches of the multiple blood vessels, generating a likelihood model for determining a validity of the branches of the multiple blood vessels, and generating a likelihood score for each branch based on the respective branch's compatibility with the likelihood model. The method also includes generating a reconstructed tree for the multiple blood vessels. Compatible branches are included in the reconstructed tree, while invalid branches are not included in the reconstructed tree.

Abstract: The disclosed embodiments relate to determining an amount of a contrast agent in an image. For example, a computer-implemented method of image processing includes generating, from a first polychromatic contrast-enhanced X-ray image obtained at a first energy and a second polychromatic contrast-enhanced X-ray image obtained at a second energy, a simulated first monochromatic contrast-enhanced X-ray image and a simulated second monochromatic contrast-enhanced X-ray image. The simulated first monochromatic contrast-enhanced X-ray image includes first regions of enhanced contrast and the simulated second monochromatic contrast-enhanced includes second regions of enhanced contrast. The method also includes isolating the first and second regions of enhanced contrast from other regions of the image, and determining an amount of the contrast agent within the first and second regions of enhanced contrast based at least on a derived partial signal attributable to the contrast agent.

Abstract: A method, system and apparatus for filtering multi-energy images using spectral filtering technique is described. In one embodiment, the method includes obtaining a first image of an anatomical object corresponding to a first radiation energy. In addition, the method includes obtaining at least one additional image, herein called a second image of the anatomical object corresponding to at least one second radiation energy. The at least one second radiation energy is distinct from the first radiation energy. The method also includes determining joint attenuation characteristics of each tissue at the first radiation energy and at the second radiation energy or their derivatives. The method also includes selectively filtering attenuation value in a multi-energy space due to at least one tissue to generate a filtered image from a reference image. The reference image is one of the first image or the second image or their derivatives.