Abstract: Disclosed is a method for analyzing a lesion based on a medical image, which is performed by a computing device. The method may include: obtaining positional information of a suspicious nodule which exists in the medical image; generating a mask for the suspicious nodule based on a patch of the medical image corresponding to the positional information; and determining a class for a state of the suspicious nodule based on the patch of the medical image and the mask for the suspicious nodule.

Abstract: An embodiment of the present disclosure provides a method of providing a User Interface for serial images analysis in a user equipment, the method including: displaying a first cross-sectional image, a second cross-sectional image, and a third cross-sectional image on a first area of the user interface, which are related to a first image; displaying candidate nodule information related to the first image on at least one of the first cross-sectional image, the second cross-sectional image, and the third cross-sectional image; determining the candidate nodule information related to a user input as first nodule information related to the first image, based on the user input on the user interface; and displaying the first nodule information in such a way that the candidate nodule information related to the user input is replaced with the first nodule information, in which the candidate nodule information may be generated based on a first nodule dataset obtained by inputting the first image to a deep learning algo

Abstract: According to an embodiment of the present disclosure, a method of detecting a white matter lesion based on a medical image performed by a computing device is disclosed. The method may include: receiving a medical image including at least one brain region; and estimating a first white matter lesion and a second white matter lesion based on the medical image using a pre-trained neural network model.

Abstract: According to the embodiment of the present disclosure, a method of analyzing a lesion based on a medical image performed by a computing device is disclosed. The method may include: extracting, by using a pre-trained artificial neural network, a first feature for each tile of a plurality of tiles included in an input image; and extracting, by using the pre-trained artificial neural network, a second feature for an entirety of the input image, based on information about whether the lesion is present for the each tile and information on a pattern of the lesion for the each tile generated based on first features of the plurality of tiles.

Abstract: According to an embodiment of the present disclosure, disclosed is a method to read a chest image. The method includes: determining whether or not to identify presence of cardiomegaly for a chest image; detecting a lung region and a heart region respectively which are included in the chest image, by using a neural network model, when it is determined to identify presence of cardiomegaly of the chest image; and calculating a cardiothoracic ratio of the chest image using the detected lung region and the detected heart region.

Abstract: Disclosed is a method for predicting disease based on a medical image performed by a computing device. The method includes: generating a feature vector related to predictive values of brain disease for each of 2D medical images included in a 3D medical image, using a pre-trained first model; estimating importance indicating prediction accuracy for each of the 2D medical images based on the feature vector, using a pre-trained second model; and selecting at least one model input image suitable for prediction of the brain disease from among the 2D medical images based on the importance.

Abstract: Disclosed is a method for analyzing a thickness of a cortical region, performed by a computing device. The method may include: extracting a plurality of interfaces included in a cortical region based on a mask generated from a medical image including at least one brain region; and estimating a thickness of the cortical region based on the plurality of interfaces.

Abstract: According to an embodiment of the present disclosure, a computer program stored in a computer readable storage medium is disclosed. The computer program includes instructions for causing one or more processors to estimate bone age from a bone image, and the instructions include: estimating a RUS score for each of one or more partial bone images using a partial bone RUS score estimation model comprising one or more layers, and wherein the one or more partial bone images are generated from a whole bone image; and estimating bone age corresponding to the whole bone image using one or more RUS scores estimated for each of the one or more partial bone images, in which the partial bone RUS score estimation model is trained by using a labeled partial bone image as training data, and is trained by adjusting feature values calculated from the one or more layers.

Abstract: According to an embodiment of the present disclosure, a method of assessing bone age by using a neural network performed by a computing device is disclosed. The method includes receiving an analysis image which is a target of bone age assessment; and assessing bone age of the target by inputting the analysis image into a bone age analysis model comprising one or more neural networks. The bone age analysis model, which is trained by supervised learning based on an attention guide label, includes at least one attention module for intensively analyzing a main region of the analysis image.

Abstract: The present invention relates to a method for classifying a fundus image and a device using same. Specifically, according to the method of the present invention, a computing device acquires a fundus image of a subject, generates classification information of the fundus image, generates an interpretation text on the basis of the classification information, and provides the interpretation text to an external entity.

Abstract: Disclosed is a portable electrocardiogram measuring device for calculating one or more electrocardiogram leads according to an embodiment of the present disclosure. The device may include: a main measurement unit comprising a first electrode, a second electrode, and one or more processors; and a sub measurement unit comprising a third electrode, in which the one or more processors measure an electrocardiogram, by receiving electrical signals from at least two electrodes in a measurable state and by calculating different types of electrocardiogram leads based on the number of electrodes in the measurable state and an attachment position of electrodes.

Abstract: The present invention relates to a method for reconstructing an image and an apparatus using the same Particularly, according to the method of the present invention, when a series of first slice images of a subject are inputted in a computing device, the computing device generates, from the first slice images, second slice images having a second slice thickness different from a first thickness, which is the slice thickness of the first slice image, and provides the generated second slice images.

Abstract: The present invention relates to a method for supporting reading of a fundus image of a subject, and a computing device using the same. Specifically, the computing device according to the present invention acquires the fundus image of the subject, extracts attribute information from the fundus image on the basis of a machine learning model for extracting the attribute information of the fundus image, and provides the extracted attribute information to an external entity. In addition, when evaluation information on the extracted attribute information or modification information on the attribute information is acquired, the computing device according to the present invention can also update the machine learning model on the basis of the acquired evaluation information or modification information.

Abstract: A computing apparatus for aiding visualization of lesions in a medical image includes a communicator and a processor. The processor is configured to receive a user input for selecting a single point in the medical image to modify a lesion mask representing a lesion area in them medical image, determine a modified lesion mask corresponding to the received user input among a plurality of pre-generated plurality of candidate lesion masks, and provide the modified lesion mask with the medical image.

Abstract: The present invention relates to a method for generating a prediction result for predicting an occurrence of fatal symptoms of a subject in advance, a method for performing data classification by using data augmentation in mechanical learning for the same, and a computing device using the same. Particularly, the computing device according to the present invention acquires vital signs of the subject, converts the same into individuated data, generates analysis information from the individuated data on the basis of a machine learning model, generates a prediction result by referring to the analysis information, and provides the prediction result to an external entity.

Abstract: An image providing method performed by a computing apparatus includes acquiring a first image group including at least a portion of a series of images generated for continuous volumes with a first slice thickness belonging to a subject, providing, as a current viewing image, one image of the first image group or one image of a second image group including images generated for continuous volumes with a second slice thickness belonging to the subject, and in response to a first specific input of an input device, repeatedly updating an image provided as the current viewing image with an individual image provided for a subsequent viewing based on a directivity given for the first specific input and, in response to a second specific input of the input device, switching the current viewing image between an image of the first image group and an image of the second image group.