VUNO Inc.

A method for a computing device to predict an action mechanism of a drug from medical images of a subject is disclosed. The method includes, from a plurality of medical images obtained in time series, outputting first compressed data corresponding to the plurality of medical images, each of the first compressed data having a smaller size than a corresponding medical image, estimating second compressed data corresponding to a medical image at a next time point to time points at which the plurality of medical images have been captured, based on the first compressed data, and predicting the action mechanism of the drug for the subject by inputting the second compressed data to a neural network predicting the action mechanism of the drug.

According to an exemplary embodiment of the present disclosure, a medical image processing method performed by a computing device is disclosed. The medical image processing method includes: detecting a region of interest in a medical image by using a pre-trained deep learning model; determining contour information for the region of interest; and generating, based on the contour information, format information defining elements that determine representation of the medical image.

A method and an apparatus for aiding visualization of lesions in a medical image are provided. In detail, the apparatus may receive a user input for selecting a single point in the medical image to modify a lesion mask representing a lesion area in the medical image, may determine a modified lesion mask corresponding to the received user input among a plurality of pre-generated plurality of candidate lesion masks, and may provide the modified lesion mask with the medical image.

A deep neural network pre-training method for classifying electrocardiogram (ECG) data and a device for the same are disclosed. A method for training an ECG feature extraction model may include receiving a ECG signal, extracting one or more first features related to the ECG signal by inputting the ECG signal to a rule-based feature extractor or a neural network model, extracting at least one second feature corresponding to the at least one first feature by inputting the ECG signal to an encoder, and pre-training the ECG feature extraction model by inputting the at least one second feature into at least one of a regression function and a classification function to calculate at least one output value. The pre-training of the ECG feature extraction model may include training the encoder to minimize a loss function that is determined based on the at least one output value and the at least one first feature.

According to an embodiment of the present disclosure, disclosed is a method for predicting a bio event. Specifically, according to the present disclosure, a computing device obtains bio information of a patient; and generates a first output indicating an expected time of occurrence of the bio event based on the bio information by using a pre-trained artificial neural network model.

Disclosed is a method for analyzing a medical image based on deep learning, which is performed by a computing device. The method may include: obtaining position information of stained cells present in a medical image by using a pre-trained neural network model; and calculating a staining ratio of the stained cells in a bounding box including the stained cells corresponding to the position information.

According to an embodiment of the present disclosure, an image analysis method is disclosed. The image analysis method may include: receiving a body medical image; detecting one or more lesions from the received body medical image using a lesion detection model; generating anatomical location information for the one or more lesions using an anatomical analysis model, based on the received body medical image and the detection result for the one or more lesions; and generating a diagnosis result for the received body medical image, based on the anatomical location information for the one or more lesions.

Disclosed is a method, performed by a computing device, for analyzing electrocardiogram (ECG) data according to an embodiment of the present disclosure. The method may include the steps of: using a first model that uses, as input, ECG data acquired from an ECG measurement device, and determining whether an event related to at least one of atrial fibrillation or atrial flutter is found in the acquired ECG data; generating a first diagnosis result for the acquired ECG data when the event is found in the acquired ECG data; and when the event is not found in the acquired ECG data, generating a second diagnosis result estimating the risk level for at least one of atrial fibrillation or atrial flutter by using a second model that uses the acquired ECG data as input.

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.

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.