KR-20260065473-A - METHOD, APPARATUS AND PROGRAM FOR INDIRECT MEDICAL IMAGE ANALYSIS

KR20260065473AKR 20260065473 AKR20260065473 AKR 20260065473AKR-20260065473-A

Abstract

A method for analyzing indirect medical images according to various embodiments of the present invention is disclosed. The method comprises: a step of acquiring an indirect medical image in which a medical image displayed on a monitor is captured; and a step of inputting the indirect medical image into a pre-trained image analysis model to generate analysis information for the medical image; wherein the image analysis model may be pre-trained based on training data consisting of an original medical image and a noisy medical image in which monitor noise is included in the original medical image.

Inventors

조용석
권혁찬
임병희

Assignees

피노키오랩 주식회사
메디너스 인코포레이티드

Dates

Publication Date: 20260508
Application Date: 20250411

Claims (10)

A method performed by a computing device comprising at least one processor, A step of acquiring an indirect medical image in which a medical image displayed on a monitor is captured; and A step of inputting the above indirect medical image into a pre-trained image analysis model to generate analysis information for the medical image; Includes, The above image analysis model is, Pre-trained based on training data consisting of an original medical image and a noisy medical image containing monitor noise in the original medical image, Indirect medical image analysis method.
In Article 1, The above method is, A step of acquiring the original medical image; A step of capturing a monitor to obtain a monitor noise image; and A step of generating the noise medical image by synthesizing the original medical image and the monitor noise image; including, Indirect medical image analysis method.
In Article 2, The step of generating the noise medical image by synthesizing the original medical image and the monitor noise image is: A step of adjusting the brightness level of the original medical image; and A step of obtaining the noise medical image by synthesizing the monitor noise image and the original medical image with the brightness level adjusted; including, Indirect medical image analysis method.
In Article 2, The step of generating the noise medical image by synthesizing the original medical image and the monitor noise image is: When multiple monitor noise images are acquired, a step of extracting a noise layer from each of the multiple monitor noise images; A step of recognizing a noise pattern included in each of a plurality of noise layers and classifying the plurality of noise layers by pattern; A step of adjusting the brightness level of the original medical image and synthesizing each of different noise patterns to the original medical image with the adjusted brightness level to generate a plurality of noise medical images; including, Indirect medical image analysis method.
In Article 1, The above method is, A step of detecting and labeling four vertices corresponding to each of a plurality of bones included in an image constituting the above training data; and A step of pre-training the image analysis model based on the above-mentioned labeled training data; including, Indirect medical image analysis method.
In Article 5, The above image analysis model is, The upper two points among the four vertices corresponding to each of the plurality of bones are recognized as the upper line of each of the plurality of bones, and Recognizing the bottom two points among the four vertices corresponding to each of the plurality of bones as the bottom line of each of the plurality of bones, Indirect medical image analysis method.
In Article 5, The above method is, A step of providing labeling information in which four vertices corresponding to each of the plurality of bones are labeled; A step of obtaining adjustment input information for four vertices corresponding to each of the plurality of bones; and A step of retraining the image analysis model by reflecting the adjustment input information in the above training data; including, Indirect medical image analysis method.
In Article 1, The above image analysis model is, When the above indirect medical image is input, at least two or more bones among a plurality of bones included in the above indirect medical image are detected, and Recognizing the distance and positional relationship between at least two of the above bones, Outputting the distance between the above bones and the above positional relationship, Indirect medical image analysis method.
Memory for storing one or more instructions; and A processor that executes one or more instructions stored in the memory. Including, The above processor executes the above one or more instructions, A device that performs the method of claim 1.
A computer program stored on a computer-readable recording medium that is combined with a computer, which is hardware, to perform the method of claim 1.

Description

Method, apparatus and program for indirect medical image analysis The present invention relates to a method, apparatus, and program for analyzing indirect medical images, and specifically to a method, apparatus, and program for analyzing an indirect medical image captured on a monitor displaying an original medical image. Medical image analysis plays a crucial role in modern medicine and is utilized for diagnosis and treatment planning using various medical images, such as X-rays, CT scans, and MRIs. In particular, medical image analysis is essential for the early diagnosis of diseases or the evaluation of pre- and post-operative conditions through the accurate interpretation and reading of medical images. Today, most medical images are managed through Picture Archiving and Communication Systems (PACS), which medical professionals use to review and diagnose images. However, PACS systems are limited in that they primarily focus on storing and retrieving medical images, lacking analytical capabilities. In particular, analyzing medical images requires extracting them from the PACS system, a process that presents various practical challenges, such as inter-system connectivity issues and compliance with personal data protection regulations. Due to these constraints, it is not easy to freely utilize images in the medical field. Furthermore, while embedding analysis software into medical devices could be considered, this approach faces practical difficulties due to issues such as device performance limitations, the complexity of system integration, and increased maintenance costs. Installing software within medical devices can place a burden on the device's processing capabilities and requires various software updates and security management. Due to these practical constraints, there is a demand in the industry for a method of indirectly capturing and analyzing medical images displayed on a monitor. In this regard, Korean Registered Patent Publication No. 10-2063492 discloses a method and system for filtering learning noise from medical image data for machine learning. FIG. 1 is a drawing illustrating a system according to one embodiment of the present invention. FIG. 2 is a hardware configuration diagram of a computing device according to one embodiment of the present invention. FIGS. 3 to 7 are drawings for explaining an indirect medical image analysis method according to an embodiment of the present invention. Various embodiments are now described with reference to the drawings. In this specification, various descriptions are provided to facilitate an understanding of the invention. However, it is evident that these embodiments can be practiced without such specific descriptions. As used herein, terms such as “component,” “module,” “system,” etc. refer to computer-related entities, hardware, firmware, software, combinations of software and hardware, or executions of software. For example, a component may be, but is not limited to, a procedure executed on a processor, a processor, an object, an execution thread, a program, and/or a computer. For example, both an application executed on a computing device and the computing device itself may be a component. One or more components may reside within a processor and/or an execution thread. A component may be localized within a single computer. A component may be distributed among two or more computers. Additionally, these components may be executed from various computer-readable media having various data structures stored therein. Components may communicate through local and/or remote processes, for example, according to signals having one or more data packets (e.g., data from a component interacting with another component in a local system or distributed system, and/or data transmitted through signals to other systems and networks such as the Internet). Furthermore, the term "or" is intended to mean an implicit "or" rather than an exclusive "or." That is, unless otherwise specified or evident from the context, "X uses A or B" is intended to mean one of the natural implicit substitutions. In other words, if X uses A; if X uses B; or if X uses both A and B, "X uses A or B" may apply to any of these cases. Additionally, the term "and/or" as used herein should be understood to refer to and include all possible combinations of one or more of the enumerated related items. Additionally, the terms “comprising” and/or “comprising” should be understood to mean that such features and/or components are present. However, the terms “comprising” and/or “comprising” should be understood not to exclude the presence or addition of one or more other features, components and/or groups thereof. Furthermore, unless otherwise specified or clearly evident from the context to indicate a singular form, the singular in this specification and claims should generally be interpreted to mean “one or more.” Those skilled in the art should recognize that the various exemplary logical blocks, config