KR-20260064944-A - Method, device, and system for providing an image processing-based examination solution using an artificial intelligence model enhanced through additional learning

KR20260064944AKR 20260064944 AKR20260064944 AKR 20260064944AKR-20260064944-A

Abstract

According to one embodiment, in a method for providing an image processing-based screening solution utilizing an artificial intelligence model enhanced through additional learning, image data is acquired based on a patient's body part and the purpose of the screening; the acquired image data is preprocessed to be input into an artificial intelligence model, and resolution adjustment, noise removal, and image normalization are performed; the preprocessed image data is input into the artificial intelligence model to analyze specific screening indicators, abnormal signs, or patterns; the risk is evaluated by comparing the analysis results with preset reference values; screening results are generated through the artificial intelligence model; the screening results are visualized and provided through a user interface; and recommendations for additional screening or treatment can be transmitted to the user's terminal.

Inventors

하성욱

Assignees

(주)살루스케어
하성욱

Dates

Publication Date: 20260508
Application Date: 20241030

Claims (3)

In a method for providing an image processing-based diagnostic solution utilizing an artificial intelligence model enhanced through additional learning, performed by a device, A step of acquiring image data based on the patient's body part and the purpose of the examination; A step of performing resolution adjustment, noise removal, and image normalization of the data so that the acquired image data can be input into an artificial intelligence model by preprocessing the data; A step of inputting the above-mentioned preprocessed image data into the above-mentioned artificial intelligence model to analyze specific screening indicators, abnormal signs, or patterns; A step of evaluating the risk level by comparing the above analysis results with a preset reference value; and The method is characterized by including the step of generating a medical examination result through the artificial intelligence model, providing the medical examination result by visualizing it through a user interface, and transmitting recommendations for additional examination or treatment to a user's terminal. Method for providing an image processing-based screening solution utilizing an artificial intelligence model enhanced through additional learning.
In paragraph 1, The step of acquiring the above image data is, A step of setting a preset optimal image shooting angle for each body part of the above patient, A step of adjusting the resolution and frame rate of image capture based on the above examination purpose, A step of generating an original image by photographing the body part of the patient based on preset image shooting conditions, A step of inspecting the quality of the original image to determine whether it is suitable for examination, and Characterized by including the step of storing only images confirmed to be suitable for examination so that they can be input into the artificial intelligence model. Method for providing an image processing-based screening solution utilizing an artificial intelligence model enhanced through additional learning.
In paragraph 1, The method further includes the step of additionally training the artificial intelligence model by adding new screening data to improve the performance of the artificial intelligence model, and The step of further training the above artificial intelligence model is, A step of classifying the above examination data into a specific dataset associated with examination indicators, A step of adjusting the learning parameters of the artificial intelligence model based on the above classified dataset, A step of retraining the artificial intelligence model using the adjusted learning parameters, A step of evaluating whether performance has improved by comparing the performance of the retrained model with a preset threshold value, and Characterized by including the step of repeating additional training of the artificial intelligence model or saving it as a final model depending on whether the above performance is improved. Method for providing an image processing-based screening solution utilizing an artificial intelligence model enhanced through additional learning.

Description

Method, device, and system for providing an image processing-based examination solution using an artificial intelligence model enhanced through additional learning The following embodiments relate to a method, apparatus, and system for providing an image processing-based screening solution utilizing an artificial intelligence model enhanced through additional learning. In modern medical systems, various image processing technologies are utilized to diagnose diseases and evaluate health status based on patient imaging data. In particular, the analysis of medical imaging data obtained from various diagnostic devices, such as computed tomography (CT), magnetic resonance imaging (MRI), and ultrasound, contributes to the early diagnosis of diseases and the provision of accurate diagnostic results. While these image processing technologies play a crucial role in enhancing the precision and efficiency of medical diagnosis, they often have the following limitations. First, screening solutions utilizing general artificial intelligence (AI) models rely on initially trained data, which limits their responsiveness to new screening data and makes it difficult to provide detailed screening results tailored to various patient characteristics. Second, if the initial learning model is not continuously further trained, performance improvement is limited, which may affect the accuracy and consistency of screening indicators. Third, some existing screening systems are not optimized for specific screening purposes or body parts, making it difficult to provide customized screenings for each patient. The present invention was designed to overcome these limitations. Specifically, the present invention aims to significantly improve the accuracy and flexibility of medical examinations by continuously enhancing the performance of existing artificial intelligence models through additional learning and by providing the ability to acquire and process optimal image data according to the patient's body part and the purpose of the examination. Therefore, a method, device, and system for providing an image processing-based screening solution utilizing an artificial intelligence model enhanced through additional learning are required. FIG. 1 is a schematic diagram showing the configuration of a system according to one embodiment. FIG. 2 is a flowchart illustrating a method for providing an image processing-based diagnostic solution using an artificial intelligence model according to one embodiment. FIG. 3 is a flowchart illustrating the process of acquiring image data according to one embodiment. FIG. 4 is a flowchart illustrating the process of additionally training an artificial intelligence model according to one embodiment. FIG. 5 is an example diagram of the configuration of a device according to one embodiment. Hereinafter, embodiments are described in detail with reference to the attached drawings. However, various modifications may be made to the embodiments, and thus the scope of the patent application is not limited or restricted by these embodiments. It should be understood that all modifications, equivalents, and substitutions to the embodiments are included within the scope of the rights. Specific structural or functional descriptions of the embodiments are disclosed for illustrative purposes only and may be modified and implemented in various forms. Accordingly, the embodiments are not limited to the specific disclosed forms, and the scope of this specification includes modifications, equivalents, or substitutions that fall within the technical concept. Terms such as "first" or "second" may be used to describe various components, but these terms should be interpreted solely for the purpose of distinguishing one component from another. For example, the first component may be named the second component, and similarly, the second component may be named the first component. When it is stated that a component is "connected" to another component, it should be understood that it may be directly connected to or joined to that other component, or that there may be other components in between. The terms used in the embodiments are for illustrative purposes only and should not be interpreted as intended to be limiting. Singular expressions include plural expressions unless the context clearly indicates otherwise. In this specification, terms such as "comprising" or "having" are intended to indicate the existence of the features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof. Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by those skilled in the art to which the embodiments pertain. Terms such as those defined in commonly used diction