Abstract: Provided is an artificial intelligence (AI) system that mimics functions, such as recognition and determination by human brains, by utilizing a machine learning algorithm, such as deep learning, and applications of the AI system.

Abstract: According to one embodiment, a data compression apparatus includes processing circuitry. The processing circuitry generates reconstructed data by performing reconstruction processing on data. The processing circuitry generates decompressed reconstructed data by performing the reconstruction processing on decompressed data obtained by decompressing compressed data that is generated by performing compression processing on the data. The processing circuitry determines a parameter relating to a compression ratio of the data based on comparison between the reconstructed data and the decompressed reconstructed data.

Abstract: A system for searching for a pathological image includes: an autoencoder having an encoder for receiving an original pathological image and extracting a feature of the original pathological image, and a decoder for receiving the feature of the original pathological image extracted by the encoder and generating a reconstructed pathological image corresponding to the original pathological image; a diagnostic neural network for receiving the reconstructed pathological image generated by the autoencoder that has received the original pathological image, and outputting a diagnosis result of a predetermined disease; and a training module for training the autoencoder and the diagnostic neural network by inputting a plurality of training pathological images, each labeled with a diagnosis result, into the autoencoder. The autoencoder is trained by reflecting the diagnosis result of the reconstructed pathological image output from the diagnostic neural network.

Abstract: Embodiments of the disclosure disclose a method, an apparatus, a computer device, and a storage medium for inpainting an image. In an embodiment, an image inpainting method includes: determining, from a target image, a first region to be inpainted and a second region that is not to be inpainted; performing feature extraction on the second region based on different receptive fields and spatial resolutions, to obtain feature information of a plurality of scales; generating a texture of the first region based on the feature information of the plurality of scales; and filling the first region in the target image with the generated texture, to obtain an inpainted image.

Abstract: Embodiments of this application disclose an image processing method and apparatus, a device, and a storage medium. The method includes: inputting an original image to a decoder network according to an image transformation instruction, to obtain a first feature map of the original image; inputting the first feature map sequentially to a plurality of transformer networks, each transformer network corresponding to at least one piece of transformation requirement information associated with the original image, to obtain a second feature map, each of the transformer networks being configured to perform image transformation to a respective region of the first feature map; and inputting the second feature map to a reconstruction network, to obtain a target image, the reconstruction network being configured to reconstruct an inputted feature map into a two-dimensional image.

Abstract: A learning assistance device acquires a plurality of learned discriminators obtained by causing learning discriminators provided in a plurality of respective terminal devices to perform learning using image correct answer data, acquires a plurality of discrimination results obtained by causing a plurality of learned discriminators to discriminate the same input image, determines the correct answer data of the input image on the basis of the plurality of discrimination results, causes the discriminator to perform learning the input image and the correct answer data, and outputs a result thereof as a new learning discriminator to each terminal device.

Abstract: A three-dimensional (3D) image-based facial verification method and apparatus is provided. The facial verification method may include capturing a facial image of a 3D face of a user, determining an occluded region in the captured facial image by comparing the captured facial image and an average facial image, generating a synthetic image by synthesizing the captured facial image and the average facial image based on the occluded region, and verifying the user based on the synthetic image.

Abstract: Disclosed is an image processing method and apparatus. The image processing method includes extracting a content latent code and a style latent code for each of a plurality of input images, obtaining a content feature vector by calculating a weighted sum of content latent codes extracted from the input images based on a morphing control parameter, obtaining a style feature vector by calculating a weighted sum of style latent codes extracted from the input images based on the morphing control parameter, and generating a morphing image based on the content feature vector and the style feature vector.

Abstract: Systems and methods are disclosed for verifying slide and block quality for testing. The method may comprise receiving a collection of one or more digital images at a digital storage device. The collection may be associated with a tissue block and corresponding to an instance. The method may comprise applying a machine learning model to the collection to identify a presence or an absence of an attribute, determining an amount or a percentage of tissue with the attribute from a digital image in the collection that indicates the presence of the attribute, and outputting a quality score corresponding to the determined amount or percentage.

Abstract: A system provides an end-to-end solution for invoice processing which includes reading files (such as pdfs and images), extracting key relevant information from the files, organizing the relevant information in a structured template as a key-value pair, and comparing files based on the similarities between different file fields to identify potential duplicate files.

Abstract: For medical imaging such as MRI, machine training is used to train a network for segmentation using both the imaging data and protocol data (e.g., meta-data). The network is trained to segment based, in part, on the configuration and/or scanner, not just the imaging data, allowing the trained network to adapt to the way each image is acquired. In one embodiment, the network architecture includes one or more blocks that receive both types of data as input and output both types of data, preserving relevant features for adaptation through at least part of the trained network.

Abstract: A machine learning predictor model is trained to generate a prediction of the appearance of a tissue sample stained with a special stain such as an IHC stain from an input image that is either unstained or stained with H&E. Training data takes the form of thousands of pairs of precisely aligned images, one of which is an image of a tissue specimen stained with H&E or unstained, and the other of which is an image of the tissue specimen stained with the special stain. The model can be trained to predict special stain images for a multitude of different tissue types and special stain types, in use, an input image, e.g., an H&E image of a given tissue specimen at a particular magnification level is provided to the model and the model generates a prediction of the appearance of the tissue specimen as if it were stained with the special stain. The predicted image is provided to a user and displayed, e.g., on a pathology workstation.

Abstract: The present disclosure concerns a method for processing a light field image comprising a set of image views.

Abstract: An endoscopic inspection system comprises: a switchable light source device for alternately providing first illumination light and second illumination light to illuminate an inspection location; an endoscope device for acquiring first image data of the inspection location under the illumination of the first illumination light, and acquiring second image data of the inspection location under the illumination of the second illumination light; a processor communicatively connected to the switchable light source device and the endoscope device, wherein the processor determines, according to the first image data and/or the second image data, whether the first image data and/or the second image data contains an abnormal region, and further generates determination data associated with the first image data and/or the second image data; and a display device communicatively connected to the processor for displaying the first image data and the second image data respectively according to a first display instruction and

Abstract: For medical imaging such as MRI, machine training is used to train a network for segmentation using both the imaging data and protocol data (e.g., meta-data). The network is trained to segment based, in part, on the configuration and/or scanner, not just the imaging data, allowing the trained network to adapt to the way each image is acquired. In one embodiment, the network architecture includes one or more blocks that receive both types of data as input and output both types of data, preserving relevant features for adaptation through at least part of the trained network.

Abstract: An x-ray image laterality detection system is provided. The x-ray image laterality detection system includes a detection computing device. The processor of the computing device is programmed to execute a neural network model for analyzing x-ray images, wherein the neural network model is trained with training x-ray images as inputs and observed laterality classes associated with the training x-ray images as outputs. The process is also programmed to receive an unclassified x-ray image, analyze the unclassified x-ray image using the neural network model, and assign a laterality class to the unclassified x-ray image. If the assigned laterality class is not target laterality, the processor is programmed to adjust the unclassified x-ray image to derive a corrected x-ray image having the target laterality and output the corrected x-ray image. If the assigned laterality class is the target laterality, the processor is programmed to output the unclassified x-ray image.

Abstract: Systems and techniques that facilitate real-time and/or offline de-identification of facial regions from regular and/or occluded color video streams obtained during diagnostic medical procedures are provided. A detection component can generate a bounding box substantially around a person in a frame of a video stream, can generate a heatmap showing key points or anatomical masks of the person based on the bounding box, and can localize a face or facial region of the person based on the key points or anatomical masks. An anonymization component can anonymize pixels in the frame that correspond to the face or facial region. A tracking component can track the face or facial region in a subsequent frame based on a structural similarity index between the frame and the subsequent frame being above a threshold.

Abstract: A deep learning model learning device is proposed, including: a parametric MRI image input part inputting an image corresponding to a diagnosis region, inputting at least one parametric MRI image constructed on the basis of parameters different from each other, and constructing and providing an MRI moving image by using the at least one parametric MRI image; a cancer detection model learning part receiving an input of the at least one parametric MRI image and the MRI moving image corresponding to the diagnosis region, and learning a deep learning model on the basis of information labeling the cancer region; a labeling reference information providing part providing at least one reference information contributing to the labeling of the cancer region; and a labeling processing part checking the cancer region input on the basis of the at least one reference information and processing the labeling of the checked cancer region.

Abstract: Described herein are means for learning semantics-enriched representations via self-discovery, self-classification, and self-restoration in the context of medical imaging. Embodiments include the training of deep models to learn semantically enriched visual representation by self-discovery, self-classification, and self-restoration of the anatomy underneath medical images, resulting in a collection of semantics-enriched pre-trained models, called Semantic Genesis. Other related embodiments are disclosed.

Abstract: Methods and systems for automated target and tissue segmentation using multi-modal imaging and ensemble machine learning models are provided herein. In some embodiments, a method comprises: receiving a plurality of medical images, wherein each of the plurality of medical images includes a target and normal tissue; combining the plurality of medical images to align the target and normal tissue across the plurality of medical images; inputting the combined medical images into each of a plurality of machine learning models; receiving, in response to the input, an output from each of the plurality of machine learning models; combining the results of the plurality of machine learning models; generating a final segmentation image based on the combined results of the plurality of machine learning models; assigning a score to each segmented target and normal tissue; and sorting the segmented targets and normal tissues based on the scores.