Abstract: The disclosure relates to a method for determining a boundary about an area of interest in an image set. The includes obtaining the image set from an imaging modality and processing the image set in a convolutional neural network. The convolutional neural network is trained to perform the acts of predicting an inverse distance map for the actual boundary in the image set; and deriving the boundary from the inverse distance map. The disclosure also relates to a method of training a convolutional neural network for use in such a method, and a medical imaging arrangement.

Abstract: A monitoring system and a method for operating the monitoring system in an inmate tracking system in a controlled environment is disclosed. The monitoring system receives video and audio data from devices located within the controlled environment and organizes the video and audio data within profiles that allow for searches of the video and audio to be performed. The monitoring system analyzes the video and audio data and generates the profiles to include identified objects associated with the video and audio data.

Abstract: Systems can be configured for detecting license plates and recognizing characters in license plates. In an example, a system can receive an image and identify one or more regions in the image that include a license plate. Character recognition can be performed in the one or more regions to determine contents of a candidate license plate. Location-specific information about a license plate format can be used together with the determined contents of the candidate license plate to determine if the recognized characters are valid.

Abstract: A 3-D convolutional autoencoder for low-dose CT via transfer learning from a 2-D trained network is described, A machine learning method for low dose computed tomography (LDCT) image correction is provided. The method includes training, by a training circuitry, a neural network (NN) based, at least in part, on two-dimensional (2-D) training data. The 2-D training data includes a plurality of 2-D training image pairs. Each 2-D image pair includes one training input image and one corresponding target output image. The training includes adjusting at least one of a plurality of 2-D weights based, at least in part, on an objective function. The method further includes refining, by the training circuitry, the NN based, at least in part, on three-dimensional (3-D) training data. The 3-D training data includes a plurality of 3-D training image pairs. Each 3-D training image pair includes a plurality of adjacent 2-D training input images and at least one corresponding target output image.

Abstract: The present disclosure is directed, among other things, to automated systems and methods for analyzing, storing, and/or retrieving information associated with biological objects having irregular shapes. In some embodiments, the systems and methods partition an input image into a plurality of sub-regions based on localized colors, textures, and/or intensities in the input image, wherein each sub-region represents biologically meaningful data.

Abstract: Embodiments of this application provide an image reconstruction method and device. The method includes: inputting a first image into a newly constructed super-resolution model to obtain a reconstructed second image, where a resolution of the second image is higher than that of the first image. The newly constructed super-resolution model is obtained by training an initial super-resolution model by using an error loss. The error loss includes a pixel mean square error and an image feature mean square error. The image feature in the image feature mean square error includes at least one of a texture feature, a shape feature, a spatial relationship feature, and an image high-level semantic feature. According to the embodiments of this application, the quality of a reconstructed image can be improved.

Abstract: A method and apparatus of a device that classifies a mesothelioma image is described. In an exemplary embodiment, the device segments the mesothelioma image into a region of interest that includes information useful for classification, and a background region, by applying a first convolutional neural network. In addition, the device tiles the region of interest into a set of tiles. For each tile, the device extracts a feature vector of that tile by applying a second convolutional neural network, where the features of the feature vectors represent local descriptors of the tile. Furthermore, the device processes the extracted feature vectors of the set of tiles to classify the image.

Abstract: The present disclosure discloses a method and a system for generating a composite PET-CT image based on a non-attenuation-corrected PET image. The method includes: constructing a first generative adversarial network and a second generative adversarial network; obtaining a mapping relationship between a non-attenuation-corrected PET image and an attenuation-corrected PET image by training the first generative adversarial network; obtaining a mapping relationship between the attenuation-corrected PET image and a CT image by training the second generative adversarial network; and generating the composite PET-CT image by utilizing the obtained mapping relationships. According to the present disclosure, a high-quality PET-CT image can be directly composited from a non-attenuation-corrected PET image, and medical costs can be reduced for patients, and radiation doses applied to the patients in examination processes can be minimized.

Abstract: A method includes obtaining, using at least one processor, first and second input image frames, where the first and second input image frames are associated with first and second image planes, respectively. The method also includes obtaining, using the at least one processor, a depth map associated with the first input image frame. The method further includes producing another version of the depth map by performing one or more times: (a) projecting, using the at least one processor, the first input image frame to the second image plane in order to produce a projected image frame using (i) the depth map and (ii) information identifying a conversion from the first image plane to the second image plane and (b) adjusting, using the at least one processor, at least one of the depth map and the information identifying the conversion from the first image plane to the second image plane.

Abstract: A gamma-ray spectrum classification apparatus, comprising circuitry configured: to provide a denoising autoencoder to receive gamma-ray spectrum data representing a gamma-ray spectrum of a material to be classified and to determine feature data indicative of one or more features representative of the gamma-ray spectrum data; and to provide a classification neural network to receive the feature data and to classify the material to be classified as one of a plurality of predetermined classifications using the feature data.

Abstract: A method for establishing a three-dimensional tomosynthesis data record of a target volume from two-dimensional projection images recorded with a recording arrangement including an X-ray source and an X-ray detector in different recording geometries is provided. During or after a reconstruction step, a deconvolution technique is used for reducing image artifacts of the tomosynthesis data record occurring due to lacking information. The projection images are recorded along a linear recording trajectory of the X-ray source. The reconstruction and the use of the deconvolution technique take place in a plurality of different two-dimensional reconstruction planes that are spanned by the recording trajectory and, in each case, a definition point in the target volume.

Abstract: Systems, methods and apparatus for image processing for reconstructing a super resolution image from multispectral (MS) images. Receive image data and initialize a fused image using a panchromatic (PAN) image, and estimate a blur kernel between the PAN image and the MS images as an initialization function. Iteratively, fuse a MS image with an associated PAN image of a scene using a fusing algorithm. Each iteration includes: update the blur kernel based on a Second-Order Total Generalized Variation function to regularize a kernel shape; fuse the PAN image and MS images with the updated blur kernel based on a local Laplacian prior function to regularize the high-resolution information to obtain an estimated fused image; compute a relative error between the estimated fused image of the current iteration and a previous estimated fused image from a previous iteration, to a predetermined threshold, to stop iterations stop, to obtain a PAN-sharpened image.

Abstract: According to one implementation, an image enhancement system includes a computing platform including a hardware processor and a system memory storing a software code configured to provide a normalizing flow based generative model trained using an objective function. The hardware processor executes the software code to receive an input image, transform the input image to a latent space representation of the input image using the normalizing flow based generative model, and perform an optimization of the latent space representation of the input image to identify an enhanced latent space representation of the input image. The software code then uses the normalizing flow based generative model to reverse transform the enhanced latent space representation of the input image to an enhanced image corresponding to the input image.

Abstract: An object of the invention is to provide a user with information that serves as a material for determining whether an image generated by processing including a neural network is valid. A reception signal output by an ultrasonic probe that has received an ultrasonic wave from a subject is received, and an ultrasonic image is generated based on the reception signal. A trained neural network receives the reception signal or the ultrasonic image, and outputs an estimated reception signal or an estimated ultrasonic image. A validity information generation unit generates information indicating validity of the estimated reception signal or the estimated ultrasonic image by using one or more of the reception signal, the ultrasonic image, the estimated reception signal, the estimated ultrasonic image, and output of an intermediate layer of the neural network.

Abstract: A method of sorting is described and which includes a step of acquiring a multiplicity of synchronized image signals of a product stream which is to be sorted; generating a multiplicity of fused sensor signals; forming an image model previously acquired from the objects to be sorted; identifying objects in the product stream, and generating object presence and defect signals; determining a spatial orientation of the objects in the product stream; detecting the defects and removing the defects from the product stream.

Abstract: Mechanisms are provided for acceleration of convolutional neural networks on analog arrays. Input ports receive image signals from frames in an input image. Input memory arrays store the image signals received from the input ports into a respective input memory location to create a plurality of image sub-regions in input memory arrays. A distributor associated each of a set of analog array tiles in an analog array to a part of image sub-regions of the input memory arrays, so that one or more of a set of analog memory components is associated with the image signals in a distribution order to create a respective output signal. An assembler stores each of the respective output signals into one of a set of memory outputs in an output order that is determined by the distribution order.

Abstract: An electronic apparatus is provided. The electronic apparatus includes: a memory storing information on an artificial intelligence model including a plurality of layers, and a processor configured to acquire an output image based on processing an input image using the artificial intelligence model. The processor is configured to: identify whether a parameter used in any one layer among the plurality of layers is a fixed parameter or a variable parameter, and provide the parameter to a first operation module or a second operation module included in of the artificial intelligence model of the artificial intelligence model any one layer based on the identification and perform an operation between output data of a previous layer and the parameter.

Abstract: A method for super-resolution image reconstruction may include obtaining an original image that has first resolution and includes a target object. The method may also include generating a first target image by increasing the first resolution of the original image. The method may also include determining first feature points relating to the target object based on the first target image. The method may also include determining first priori information relating to the target object based on the first feature points relating to the target object. The method may also include generating a second target image having second resolution higher than the first resolution based on the first priori information relating to the target object and the first target image.

Abstract: Systems and methods are provided for upsampling low temporal resolution depth maps. This upsampling is performed by obtaining a stereo pair of images of a scene captured at a first timepoint, generating a first depth map of the scene for the first timepoint by performing stereo matching on the stereo pair of images, obtaining a subsequent stereo pair of images captured at a subsequent timepoint to the first timepoint, and generating a subsequent depth map that corresponds to the subsequent timepoint by applying an edge-preserving filter using the first depth map without performing stereo matching on the subsequent stereo pair of images.

Abstract: A learning device includes: a time-series information generation unit that obtains a first image group including a plurality of successive time-series images including a reference image and generates first time-series information based on a difference between the reference image and each of the images in the first image group other than the reference image; and a first learning unit that performs machine learning using the reference image and the first time-series information, thereby obtaining a first learning result used for estimating depth information on a target image, which is an image to be processed, and silhouette information on a subject captured in the target image based on the target image and second time-series information generated from a second image group including a plurality of successive time-series images including the target image.