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: The switching converter equipped with negative current tracking control includes a switching transistor whose drain is connected to an input power supply, a rectifying transistor whose drain is connected to a source of the switching transistor and whose source is connected to a ground, an inductor having one end connected to the source of the switching transistor and the drain of the rectifying transistor, an output capacitor having a first end connected to the other end of the inductor and a second end connected to a ground, a PWM controller that outputs a PWM control signal to a gate of the switching transistor and a gate of the rectifying transistor, a zero current detector that detects zero crossing of an inductor current flowing through the inductor, and a negative current tracking controller that variably adjusts an offset of the zero current detector.

Abstract: 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.

Abstract: A lesion diagnosing method includes inputting medical data into first and second neural network models to detect an object region for lesion diagnosis from the medical data, and detect at least one finding region related to a specific lesion; calculating a volume and location for at least one finding region included in the object region; and generating result information for the medical data based on a volume and a location for the finding region.

Abstract: The present disclosure relates to a method for improving reproduction performance of a deep neural network model trained using a group of learning data so that the deep neural network model can exhibit excellent reproduction performance even for target data having a quality pattern different from that of the group, and a device using same. According to the method of the present disclosure, a computing device acquires the target data, retrieves at least one piece of candidate data having a highest similarity to the target data from a learning data representative group including reference data selected from the learning data, performs adaptive pattern transformation on the target data to enable adaptation to the candidate data, and supports transfer of transformed data, which is a result of the adaptive pattern transformation, to the deep neural network model so as to acquire an output value from the deep neural network model.

Abstract: 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.

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 computer program stored in a computer readable storage medium. When the computer program is executed by one or more processors, the computer program provides a user interface for displaying a lesion readings result, and the user interface may include: lesion information comprised in medical data; and one or more findings related to the lesion information and displayed in response to a user interaction with the lesion information.

Abstract: An integrated circuit includes an internal circuit and an attack detection circuit including at least one sensor configured to sense at least one abnormal condition of the internal circuit. The at least one abnormal condition is a parameter of the internal circuit that is outside of a predetermined range. The attack detection circuit is configured to sense an external attack on the internal circuit based on the at least one abnormal condition. The attack detection circuit further includes a security built-in-self-test (BIST) circuit configured to sense a physical attack on the attack detection circuit.