Abstract: A classifier engine provides cell morphology identification and cell classification in computer-automated systems, methods and diagnostic tools. The classifier engine performs multispectral segmentation of thousands of cellular images acquired by a multispectral imaging flow cytometer. As a function of imaging mode, different ones of the images provide different segmentation masks for cells and subcellular parts. Using the segmentation masks, the classifier engine iteratively optimizes model fitting of different cellular parts. The resulting improved image data has increased accuracy of location of cell parts in an image and enables detection of complex cell morphologies in the image. The classifier engine provides automated ranking and selection of most discriminative shape based features for classifying cell types.

Abstract: A medical image processing apparatus including processing circuitry configured to: obtain from medical imaging measurements, observations of one or more vector or tensor valued fields as projected from one or more 2D acquisition planes; use an optimisation procedure to determine from the observations a superset of 3D fields (which may be scalar, vector, or tensor) via a solution ansatz constrained by a system of partial differential equations, and output the plurality of these fields.

Abstract: This invention belongs to measurement methods that can be used in light industry, when measuring the shape and size of the human body parts. Disclosed is a method, over the course of which, based on a series of photographs an image of a flat object of known shape and size is identified on each photograph. The body part area is isolated from the background in the image, and the area of an arbitrary body that does not belong to the projection of the human body part is cut out. Also disclosed is a method for searching an image of a flat object of known shape and size, its projection, and the camera location and orientation, over the course of which the predicted image of the flat object is compared to the real on. Here, the particle dynamics technique is used for isolating a human body part from the image background.

Abstract: Techniques are provided for determining a cell count within a whole slide pathology image. The image is segmented using a global threshold value to define a tissue area. A plurality of patches comprising the tissue area are selected. Stain intensity vectors are determined within the plurality of patches to generate a stain intensity image. The stain intensity image is iteratively segmented to generate a cell mask using a local threshold value that is and gradually reduced after each iteration. A chamfer distance transform is applied to the cell mask to generate a distance map. Cell seeds are determined on the distance map. Cell segments are determined using a watershed transformation, and a whole cell count is calculated for the plurality of patches based on the cell segments. A client device may be configured for real-time cell counting based on the whole cell count.

Abstract: Various embodiments of the present disclosure relate generally to systems and methods for drone-based systems and methods for capturing a multi-media representation of an entity. In some embodiments, the multi-media representation is digital, or multi-view, or interactive, and/or the combinations thereof. According to particular embodiments, a drone having a camera is controlled or operated to obtain a plurality of images having location information. The plurality of images, including at least a portion of overlapping subject matter, are fused to form multi-view interactive digital media representations.

Abstract: Provided are a three-dimensional reconstruction method, apparatus and system of a dynamic scene, a server and a medium. The method includes: acquiring multiple continuous depth image sequences of the dynamic scene, where the multiple continuous depth image sequences are captured by an array of drones equipped with depth cameras; fusing the multiple continuous depth image sequences to establish a three-dimensional reconstruction model of the dynamic scene; obtaining target observation points of the array of drones through calculation according to the three-dimensional reconstruction model and current poses of the array of drones; and instructing the array of drones to move to the target observation points to capture, and updating the three-dimensional reconstruction model according to multiple continuous depth image sequences captured by the array of drones at the target observation points.

Abstract: A ripple push method for a graph cut includes: obtaining an excess flow ef(v) of a current node v; traversing four edges connecting the current node v in top, bottom, left and right directions, and determining whether each of the four edges is a pushable edge; calculating, according to different weight functions, a maximum push value of each of the four edges by efw=ef(v)*W, where W denotes a weight function; and traversing the four edges, recording a pushable flow of each of the four edges, and pushing out a calculated flow. The ripple push method explores different push weight functions, and significantly improves the actual parallelism of the push-relabel algorithm.

Abstract: Provided are a method and an apparatus for interlocking a lesion location between a 2D medical image and 3D tomosynthesis images including a plurality of 3D image slices.

Abstract: Apparatuses, systems and methods are provided for generating and transmitting data representative of a vehicle operation mode. More particularly, apparatuses, systems and methods are provided for generating data representative of a vehicle operation mode based on vehicle interior image data.

Abstract: Described herein is a detector for determining a position of at least one object. The detector includes at least one sensor element having a matrix of optical sensors, the optical sensors each having a light-sensitive area, wherein the sensor element is configured to determine a reflection image of the object. The detector also includes an evaluation device configured to select a reflection feature of the reflection image, and determine a distance estimate of the selected reflection feature of the reflection image by optimizing at least one blurring function fa, wherein the distance estimate is given by a longitudinal coordinate z and an error interval ±?. The evaluation device is adapted to determine at least one displacement region in at least one reference image corresponding to the distance estimate, and to match the selected reflection feature with at least one reference feature within the displacement region.

Abstract: A method for adaptive treatment planning is provided. The method may include obtaining a planning image volume of a subject, a treatment image volume of the subject, and a first treatment plan related to the planning image volume of the subject, each of the planning image volume and the treatment image volume including an ROI of the subject. The method may also include registering the planning image volume and the treatment image volume, and determining a first contour of the ROI in the registered planning image volume and a second contour of the ROI in the registered treatment image volume. The method may also include evaluating whether an error exists in at least one of the registration or the contour determination based on the first contour and the second contour, and determining a second treatment plan with respect to the treatment image volume based on the evaluation result.

Abstract: A multispectral inspection (MSI) device for analyzing an electronic item having a printed circuit board (PCB). An electronic power supply powers the electronic item in accordance with one or more test vectors. An optical imaging scanner, terahertz (THz) imaging scanner, and a functional imaging scanner are each operative to scan the electronic item. An electronic processor is programmed to scan the various scanners and control the power supply to acquire optical, THz, and functional images of the electronic item. The images are combined to form a standard three-dimensional (3D) signature and artificial intelligence (AI) classifiers are applied to the 3D signature to perform non-destructive analyses of the electronic item.

Abstract: A respiratory status classifying method is for classifying as one of at least two respiratory statuses and includes an original physiological parameter inputting step, an original chest image inputting step, a characteristic physiological parameter generating step, a characteristic chest image generating step, a training step and a classifier generating step. The characteristic chest image generating step includes processing at least a part of the original chest images, segmenting images of a left lung, a right lung and a heart from each of the original chest images that are processed, and enhancing image data of the images being segmented, so as to generate a plurality of characteristic chest images. The training step includes training two respiratory status classifiers using a plurality of characteristic physiological parameters and the characteristic chest images by at least one machine learning algorithm.

Abstract: Systems and methods of tumor segmentation are receiving data having dimensions of a first size and a first kernel size. A residual volume is produced from the input volume. A first, second, and third intermediate volume are produced by from convolving a first, second, and third dimension volume of the residual volume to 1. A first global volume is produced from sums of the residual volumes. A downsampled volume is produced from the input volume. A residual downsampled volume is produced from the downsampled volume. A first, second, and third intermediate downsampled volume is produced from convolving a first, second, and third dimension volume of the downsampled volume to 1. A second global volume is produced from sums of the intermediate downsampled volumes. The second global volume is upsampled. An output volume is produced from integrating the first global volume and the second global volume.

Abstract: An animation system wherein a machine learning model is adopted to learn a transformation relationship between facial muscle movements and skin surface movements. For example, for the skin surface representing “smile,” the transformation model derives movement vectors relating to what facial muscles are activated, what are the muscle strains, what is the joint movement, and/or the like. Such derived movement vectors may be used to simulate the skin surface “smile.”.

Abstract: The current disclosure provides methods and systems for increasing an accuracy and/or suitability of an automated measurement of a medical image. In one embodiment, the current disclosure provides for a method comprising: receiving one or more user-selected measurement points for an automated measurement of an anatomical feature of a medical image from a user; predicting one or more additional measurement points for the automated measurement based on the one or more user-selected measurement points and based on a comparison of the anatomical feature of the medical image with a plurality of images of the anatomical feature via a trained network; and performing the automated measurement of the anatomical feature based at least on the one or more additional measurement points.

Abstract: A deep learning (DL) network corrects/performs sinogram completion in computed tomography (CT) images based on complementary high- and low-kV projection data generated from a sparse (or fast) kilo-voltage (kV)-switching CT scan. The DL network is trained using inputs and targets, which respectively generated with and without kV switching. Another DL network can be trained to correct sinogram-completion errors in the projection data after a basis/material decomposition. A third DL network can be trained to correct sinogram-completion errors in reconstructed images based on the kV-switching projection data. Performance of the DL network can be improved by dividing a 3D convolutional neural network (CNN) into two steps performed by respective 2D CNNs. Further, the projection data and DLL can be divided into high- and low-frequency components to improve performance.

Abstract: An apparatus for sign detection includes a point cloud analysis module, an image analysis module, a frustum comparison module, and a sign detector. The point cloud analysis module is configured to receive point cloud data associated with a geographic region and classify at least one point neighborhood in the point cloud data as planar and a sign position candidate. The image analysis module is configured to receive image data associated with the geographic region and calculate a sighting frustum from the image data. The frustum comparison module is configured to perform a comparison of the sighting frustum to the sign position candidate having at least one point neighborhood classified as planar. The sign detector is configured to provide a location for the sign detection in response to the comparison of the sighting frustum to the sign position candidate.

Abstract: A method is proposed for identifying (“segmenting”) at least one portion of the skin of an animal which is a region of interest (e.g. a portion which is subject to an abnormality such as a tumor). The method uses at least a temperature dataset obtained by measuring the temperature of each of a plurality of points of a region of the skin. An initial segmentation may be performed using the temperature data based on a statistical model, in which each point is segmented based on its temperature and optionally that of its neighbors. The initial segmentation based on the temperature data may be improved using a three-dimensional model of the profile of the skin, and the enhanced segmentation may be used to improve the three-dimensional model.

Abstract: Disclosed is a fundus image quality evaluation method based on multi-source and multi-scale feature fusion, comprising following steps: S1, acquiring multi-source fundus images, labeling the multi-source fundus images with four evaluation dimensions of brightness, blur, contrast and overall image quality, and forming training samples with the fundus image and labeling labels; S2, constructing a fundus image quality evaluation network including a feature extraction module, a fusion module, an attention module and an evaluation module; S3, training the fundus image quality evaluation network by using training samples to obtain a fundus image quality evaluation model; and S4: inputting fundus images to be measured into the fundus image quality evaluation model, and outputting quality evaluation results through calculation. Also provided is a fundus image quality evaluation device based on above method.