Abstract: Disclosed are an optimization method and system for a personalized contrast test based on deep learning, in which a contrast medium optimized for each individual patient is injected to implement optimum pharmacokinetic characteristics in a process of acquiring a medical image, the method including: obtaining drug information of a contrast medium and body information of a patient, in a contrast enhanced computed tomography (CT) scan; generating injection information of the drug to be injected into the patient by a predefined algorithm based on the drug information and the body information; injecting the drug into the patient based on the injection information, and acquiring a medical image by scanning the patient; and amplifying a contrast component in the medical image by inputting the medical image to a deep learning model trained in advance.

Abstract: Disclosed are a motion compensation processing apparatus and method of medical images, in which motion of organs is corrected, the method including: acquiring the medical image and combining an organ motion component into the medical image; training at least one deep learning model based on the medical image combined with the organ motion component so that the deep learning model can remove the organ motion component; and acquiring a processing medical image, selecting a deep learning model corresponding to an organ included in the processing medical image, and removing a motion component for the organ.

Abstract: Provided is a deep learning based contrast-enhanced (CE) CT image contrast amplifying method and the deep learning based CE CT image contrast amplifying method includes extracting at least one component CT image between a CE component and a non-CE component for an input CE CT image with the input CE CT image as an input to a previously trained deep learning model; and outputting a contrast-amplified CT image with respect to the CE CT image based on the input CE CT image and the at least one extracted component CT image.

Abstract: Provided is a deep learning based accelerated MRI image quality restoring method. The deep learning based accelerated MRI image quality restoring method includes extracting test information from an input accelerated MRI image, selecting at least one deep learning model corresponding to the test information, among a plurality of previously trained deep learning models, and outputting an MRI image with a restored image quality for the input accelerated MRI image with the input accelerated MRI image as an input of at least one selected deep learning model.