Abstract: A medical image analysis method according to an embodiment of the present application comprises the steps of: acquiring a medical image to be analyzed; acquiring a knee detection model that has been trained; acquiring a first feature region related to a first knee from the medical image through the knee detection model; acquiring a second feature region related to a second knee from the medical image through the knee detection model; and acquiring a first knee image to be analyzed, related to the first knee, and a second knee image to be analyzed, related to the second knee, on the basis of the first feature region and the second feature region of the medical image.
Abstract: A bone growth stage analysis method according to an embodiment of the present application includes acquiring a medical image including a bone region, detecting regions of interest in the medical image, calculating a skeletal maturity index for each of the regions of interest, calculating a temporary growth stage on the basis of the skeletal maturity index, calculating a bone age from an entire area of the medical image, acquiring correlation information between bone ages and bone growth stages and calculating a reference growth stage corresponding to the calculated bone age using the correlation information, and calculating final bone growth stage information on the basis of the temporary growth stage and the reference growth stage.
Abstract: Provided is a medical image analysis method including acquiring a target medical image, detecting a target joint spacing region from the target medical image, acquiring a first value related to a width of a joint part from the target medical image, acquiring a second value related to joint spacing from the target joint spacing region, and calculating a target joint condition indicator indicating a joint condition based on the first value and the second value.
Abstract: An apparatus for a precise analysis of a severity of arthritis includes an image collection unit configured to collect a medical image having captured a joint of a user, a region detection unit configured to detect one or more regions of interest for analyzing arthritis in the medical image through a learned automatic region detection model, an individual analysis unit configured to extract quantitative feature values from the detected regions of interest and derives one or more individual analysis data from among a severity of arthritis, a severity of osteoproliferation, and a severity of hardness of a subchondral bone based on the feature values, and an integrated analysis unit configured to finely classify a severity of degenerative arthritis through an integrated analysis model learned based on the individual analysis data.
Abstract: Provided is a medical image analysis method including acquiring a target medical image, detecting a target joint spacing region from the target medical image, acquiring a first value related to a width of a joint part from the target medical image, acquiring a second value related to joint spacing from the target joint spacing region, and calculating a target joint condition indicator indicating a joint condition based on the first value and the second value.
Abstract: The present disclosure relates to an image analysis method, system, and computer program. The image analysis method of the present disclosure includes: receiving a query image; extracting one or more regions of interest from the query image; calculating a first feature for each of the regions of interest by respectively applying the regions of interest to one or more ROI (region of interest) feature extraction models independently learned in order to extract features of the regions of interest; and calculating analysis values of the query image by applying the first features of the regions of interest to a pre-learned integration analysis model. According to the present disclosure, it is possible to reduce the influence on an analysis model by an error that training data created for map learning of an entire image may have, and it is also possible to increase learning accuracy and objectivity of a deep neural network.