Abstract: Provided are a computerized image interpretation method and a device for analyzing a medical image. The image interpretation method may include receiving, at a processor, a medical image, and receiving report information including a healthcare worker's judgement result of the medical image. The method may also include generating, at the processor, result information representing correspondence between first lesion information, which is related to a lesion in the medical image acquired on the basis of the medical image, and second lesion information, which is related to a lesion in the medical image acquired on the basis of the report information, by applying the first lesion information and the second lesion information to a third analysis model. The method may further include outputting, at the processor, the result information.

Abstract: This disclosure relates to a computerized method to perform a machine learning on a relationship between medical images and metadata using a neural network and acquiring metadata by applying a machine learning model to medical images, and a method thereof. The apparatus and method may include training a prediction model for predicting metadata of medical images based on multiple medical images for learning and metadata matched with each of multiple medical images and predicting metadata of input medical image.

Abstract: A method of recalibrating a feature data of each channel generated by a convolution layer of a convolution neural network is provided. According to some embodiments, since an affine transformation is applied to the feature data of each channel independently of the feature data of the other channel, the overall number of parameters defining the affine transformation is minimized. As a result, the amount of computations required in performing the feature data recalibration can be reduced.

Abstract: There is provided an anomaly detection method, apparatus, and system that can improve the accuracy and reliability of a detection result using GAN (Generative Adversarial Networks). An anomaly detection apparatus according to some embodiments includes a memory that stores a GAN-based image translation model and an anomaly detection model, and a processor that translates a learning image with a low-difficulty level into a learning image with a high-difficulty level and learns the anomaly detection model using the translated learning image. The anomaly detection apparatus can improve the detection performance by learning the anomaly detection model with the learning image with the high-difficulty level in which it is difficult detect the anomaly.

Abstract: A semantic segmentation method and apparatus for improving an accuracy of a segmentation result are provided. The semantic segmentation method inputs a labeled image into a segmentation neural network to obtain segmentation information for the image, and back-propagates a segmentation loss for the segmentation information to update the segmentation neural network. The segmentation neural network is updated by further back-propagating an edge loss for the segmentation information.

Abstract: The present disclosure provides a method for training a neural network that extracts a feature of an image by using data related to a difference between image, and an apparatus using the same. A neural network training method performed by a computing device according to an exemplary embodiment of the present disclosure includes: acquiring a reference image photographed with a first setting with respect to an object and a first comparison image photographed with a second setting with respect to the object; acquiring feature data of the reference image from a first neural network trained by using the reference image; acquiring feature data of a first extract image from a second neural network, wherein the second neural network is trained by using the first extract image formed from data related to a difference between the reference image and the first comparison image; and training a third neural network by using the feature data of the reference image and the feature data of the first extracted image.

Abstract: Provided are an object recognition method and apparatus which determine an object of interest included in a recognition target image using a trained machine learning model and determine an area in which the object of interest is located in the recognition target image. The object recognition method based on weakly supervised learning, performed by an object recognition apparatus, includes extracting a plurality of feature maps from a training target image given classification results of objects of interest, generating an activation map for each of the objects of interest by accumulating the feature maps, calculating a representative value of each of the objects of interest by aggregating activation values included in a corresponding activation map, determining an error by comparing classification results determined using the representative value of each of the objects of interest with the given classification results and updating a CNN-based object recognition model by back-propagating the error.

Abstract: The present invention relates to a classification apparatus for pathologic diagnosis of a medical image and a pathologic diagnosis system using the same. According to the present invention, there is provided a classification apparatus for pathologic diagnosis of a medical image, including: a feature extraction unit configured to extract feature data for an input image using a feature extraction variable; a feature vector transformation unit configured to transform the extracted feature data into a feature vector using a vector transform variable; and a vector classification unit configured to classify the feature vector using a classification variable, and to output the results of the classification of pathologic diagnosis for the input image; wherein the feature extraction unit, the feature vector transformation unit and the vector classification unit are trained based on a first tagged image, a second tagged image, and an image having no tag information.

Abstract: The present invention relates to a classification apparatus for pathologic diagnosis of a medical image and a pathologic diagnosis system using the same. According to the present invention, there is provided a classification apparatus for pathologic diagnosis of a medical image, including: a feature extraction unit configured to extract feature data for an input image using a feature extraction variable; a feature vector transformation unit configured to transform the extracted feature data into a feature vector using a vector transform variable; and a vector classification unit configured to classify the feature vector using a classification variable, and to output the results of the classification of pathologic diagnosis for the input image; wherein the feature extraction unit, the feature vector transformation unit and the vector classification unit are trained based on a first tagged image, a second tagged image, and an image having no tag information.

Abstract: The present invention relates to a cloud-based pathological analysis system and method. The present invention provides a cloud-based pathological analysis system, including: a client device coupled to a microscope, and configured to acquire an image for a tissue sample via the microscope and generate a sample image; and a cloud server coupled to the client device over a network, and configured to receive sample image data from the client device over the network and store the sample image data; wherein the cloud server analyzes the received sample image data, and transmits analysis information to the client device.