A method for performing a computer-aided diagnosis (CAD) includes: acquiring a medical image set; generating a three-dimensional (3D) tumor distance map corresponding to the medical image set, each voxel of the tumor distance map representing a distance from the voxel to a nearest boundary of a primary tumor present in the medical image set; and performing neural-network processing of the medical image set to generate a predicted probability map to predict presence and locations of oncology significant lymph nodes (OSLNs) in the medical image set, wherein voxels in the medical image set are stratified and processed according to the tumor distance map.

Techniques for calibrating cameras and displays are disclosed. An image of a target is captured using a camera. The target includes a tessellation having a repeated structure of tiles. The target further includes unique patterns superimposed onto the tessellation. Matrices are formed based on pixel intensities within the captured image. Each of the matrices includes values each corresponding to the pixel intensities within one of the tiles. The matrices are convolved with kernels to generate intensity maps. Each of the kernels is generated based on a corresponding unique pattern of the unique patterns. An extrema value is identified in each of the intensity maps. A location of each of the unique patterns within the image is determined based on the extrema value for each of the intensity maps. A device calibration is performed using the location of each of the unique patterns.

A segmentation method for tumor regions in a pathological image of clear cell renal cell carcinoma based on deep learning includes data acquisition and pre-processing, building and training of a classification network SENet and prediction of tumor regions. The present invention studies clear cell renal cell carcinoma based on pathological images, yielding results with higher reliability than judgments made based on CT or MRI images. The present invention overcomes the drawback that the previous research on clear cell renal cell carcinoma is only limited to judgment on presence by being able to visually provide the position and size of tumor regions, which is convenient for the medical profession to better study the pathogenesis and directions to the treatment of clear cell renal cell carcinoma.

This invention relates to a method for training a neural network, comprising detecting a hole in each training image of a plurality of training images; transforming each training image into a transformed image, to suppress non-crack information in the training image; and training a neural network using the transformed images, to detect cracks in images (i.e. in objects in images).

A computer-implemented method for sampling and analyzing data from at least one image frame from at least one series of image frames captured by at least one sensor, comprises: defining at least one sampling model, wherein the sampling model is defined in a virtual 3D-vector space and is based on one or more predetermined shapes in the virtual 3D-vector space, applying the at least one sampling model to at least one part of the at least one image frame of the at least one series of image frames, wherein applying of the at least one sampling model defines at least one area of the at least one image frame from which data is to be extracted, extracting data from the at least one area of the at least one image frame defined by the sampling model, and analyzing the extracted data.

A safety belt detection method, apparatus, computer device and computer readable storage medium are disclosed. The safety belt detection method includes the steps as follows. An image to be detected is obtained. The image to be detected is inputted into a detection network which includes a global dichotomous branch network and a grid classification branch network. A dichotomous result, which indicates whether a driver is wearing a safety belt and is output from the global dichotomous branch network, is obtained. A grid classification diagram, which indicates a position information of the safety belt and is output from the grid classification branch network, is obtained based on image classification. A detection result of the safety belt, indicating whether the driver is wearing the safety belt normatively, is obtained based on the dichotomous result and the grid classification diagram.

Disclosed is a 3D reconstruction method for obtaining, from a 2D colour image of a human face with a visible toothed portion (1), a single reconstructed 3D surface of the toothed portion and of the facial portion (4) without toothed portion. The method comprises segmenting the 2D image into a first part (22) corresponding to the toothed portion (1) and a second part corresponding to the facial portion (4) without said toothed portion, enhancing the first part of the 2D image in order to modify the photometric characteristics, and generating a 3D surface of the face reconstructed from the enhanced first part of the 2D image and from the second part of the 2D image. The obtained 3D surface of the face is suitable for simulating a dental treatment, by substituting on the area of the 3D surface corresponding to the toothed portion (1), another 3D surface corresponding to the toothed portion after the projected treatment.

A method is provided. The method includes: determining, by one or more computers, a name of a target region, wherein the name of the target region is determined based on geometry attribute information of the target region; and determining, by one or more computers, region attribute information of the target region based on the name of the target region

A mixed reality (MR) providing device is disclosed. The MR providing device includes: a camera, a communication unit comprising circuitry configured to communicate with an electronic device providing video, an optical display unit comprising a display configured to simultaneously display real space within a preset range of viewing angle and a virtual image, and a processor. The processor is configured to: capture the preset range of viewing angle through the camera to acquire an image, identify at least one semantic anchor spot of the acquired image in which an object may be positioned, transmit characteristic information of the semantic anchor spot related to the object that may be positioned to the electronic device through the communication unit, receive an object region including the object corresponding to the characteristic information and included in an image frame of the video from the electronic device through the communication unit, and control the optical display unit to display the received object region on the semantic anchor spot.

The technology employs a patch-based multi-scale Transformer (300) that is usable with various imaging applications. This avoids constraints on image fixed input size and predicts the quality effectively on a native resolution image. A native resolution image (304) is transformed into a multi-scale representation (302), enabling the Transformer's self-attention mechanism to capture information on both fine-grained detailed patches and coarse-grained global patches. Spatial embedding (316) is employed to map patch positions to a fixed grid, in which patch locations at each scale are hashed to the same grid. A separate scale embedding (318) is employed to distinguish patches coming from different scales in the multiscale representation. Self-attention (508) is performed to create a final image representation. In some instances, prior to performing self-attention, the system may prepend a learnable classification token (322) to the set of input tokens.