Real-time cervical imaging assistance system based on computer vision algorithm and artificial intelligence

Abstract

The present invention relates to a real-time cervical imaging assistance system based on a computer vision algorithm and artificial intelligence and, more specifically, to a real-time cervical imaging assistance system based on a computer vision algorithm and artificial intelligence, the system being characterized by comprising: an image brightness analysis unit which acquires a real-time camera image captured from a cervical imaging device and performs image brightness analysis through analysis processing of the acquired real-time camera image; a cervical position and focus detection unit which detects the position and focus of the cervix in the real-time camera image captured by the cervical imaging device; and a display which provides visualization of the analysis results of the image brightness analysis unit and the cervical position and focus detection unit.

Description

Real-time cervical imaging assistance system based on computer vision algorithms and artificial intelligence

[0001] The present invention relates to a real-time cervical imaging assistance system based on computer vision algorithms and artificial intelligence. More specifically, it relates to a real-time cervical imaging assistance system based on computer vision algorithms and artificial intelligence that analyzes in real-time whether there are brightness anomalies, cervical position anomalies, and focus anomalies through a real-time cervical imaging assistance system that is mounted on and executed on a device and captures real-time camera images captured by a cervical imaging device, and visualizes and provides the analysis results.

[0002] The content described in this section merely provides background information regarding an embodiment of the present invention and does not constitute prior art.

[0003] Cervical cancer, which is the second most common cancer among women worldwide, is a cancer that can be diagnosed early through regular screenings. Although the most basic screening method for cervical cancer is the cytology test, it has a high rate of misdiagnosis with a sensitivity of 50–60%, so a screening method that can complement this is needed.

[0004] Currently, to complement cytology, a method of interpreting images by observing the presence or absence of morphological abnormalities in the cervix is ​​used; however, this method has limitations as it relies on the human eye to diagnose captured cervical images, being subjective and not immediate. Recently, with the advancement of artificial intelligence technology, research is underway to apply deep learning techniques to cervical image interpretation. However, there are still no significant research results, and sufficient accuracy has not yet been secured. Furthermore, due to a lack of consideration for use in medically underserved regions such as Africa and India, the technology is not being utilized as effectively as expected. Therefore, there is a need to develop a system that assists in the proper imaging of the cervix to improve the accuracy of cervical image interpretation and enable effective use in medically underserved areas.

[0005] Furthermore, a cervical imaging device, which is a standard piece of gynecological medical equipment, is designed to magnify and photograph a woman's cervix to visually assess the condition of uterine diseases. Since the inside of the uterus is dark due to its anatomical structure, lighting plays a crucial role in clearly photographing the interior. Thus, while a cervical imaging device requires a properly captured image of the cervix for accurate image interpretation, conventional devices capture images without analyzing the captured video in real-time to adjust brightness, precise position, and focus. Consequently, it is difficult to obtain an accurate image of the cervix through visual analysis alone, which presents a limitation that makes accurate diagnosis of the cervix difficult. Korean Patent Publication No. 10-2011-0108905 is disclosed as a prior art document.

[0006] The aforementioned background technology is technical information that the inventor possessed for the derivation of the present invention or acquired during the process of deriving the present invention, and it cannot be considered as publicly known technology disclosed to the general public prior to the filing of the present invention.

[0007] The present invention is proposed to solve the aforementioned problems of previously proposed methods, and aims to provide a real-time cervical imaging assistance system based on computer vision algorithms and artificial intelligence, which includes an image brightness analysis unit that acquires a real-time camera image captured by a cervical imaging device and performs image brightness analysis through analysis processing of the acquired real-time camera image, a cervical position and focus detection unit that performs cervical position and focus detection within the real-time camera image captured by the cervical imaging device, and a display that provides visualization of the analysis results of the image brightness analysis unit and the cervical position and focus detection unit.

[0008] In addition, another objective of the present invention is to provide a real-time cervical imaging assistance system based on computer vision algorithms and artificial intelligence, which analyzes in real-time whether there are abnormalities in brightness, cervical position, and focus through a real-time cervical imaging assistance system that is mounted on and executed on a device and analyzes the real-time camera images captured by a cervical imaging device, and visualizes and provides the analysis results, thereby enabling the user to properly photograph the cervix by adjusting the camera and lighting of the cervical imaging device based on the analysis results.

[0009] In addition, another objective of the present invention is to provide a real-time cervical imaging assistance system based on computer vision algorithms and artificial intelligence, which assists the user in properly imaging the cervix by adjusting the camera and lighting of the cervical imaging device, thereby enabling real-time cervical imaging based on computer vision algorithms and artificial intelligence, and enabling the capture of high-quality cervical images by assisting in proper cervical imaging.

[0010] However, the technical problem that the present invention aims to solve is not limited to the technical problem described above, and other technical problems may exist.

[0011] A real-time cervical imaging assistance system based on a computer vision algorithm and artificial intelligence according to the features of the present invention for achieving the above-mentioned purpose,

[0012] As a real-time cervical imaging assistance system based on computer vision algorithms and artificial intelligence,

[0013] An image brightness analysis unit that acquires real-time camera images captured from a cervical imaging device and performs image brightness analysis through analysis processing of the acquired real-time camera images;

[0014] A cervical position and focus detection unit that performs cervical position and focus detection within a real-time camera image captured from the above-mentioned cervical imaging device; and

[0015] The configuration is characterized by including a display that provides a visualization of the analysis results of the image brightness analysis unit and the cervical position and focus detection unit.

[0016] Preferably, the image brightness analysis unit is,

[0017] It may be configured as a brightness anomaly detection model that performs image brightness analysis through analysis processing of real-time camera images captured from the above-mentioned cervical imaging device.

[0018] More preferably, the brightness anomaly detection model is,

[0019] It is possible to analyze whether there is an abnormality in the brightness of the above real-time camera image and provide the image brightness analysis result so that the user can check it through the above display.

[0020] Preferably, the cervical position and focus detection unit is,

[0021] It may be configured as a cervical position and focus detection model that performs cervical position and focus detection within a real-time camera image captured from the above-mentioned cervical imaging device.

[0022] More preferably, the cervical position and focus detection model is,

[0023] The analysis results of detecting the position and focus of the cervix within the real-time camera image captured by the above-mentioned cervical imaging device can be visualized and provided on the display through analysis result visualization processing.

[0024] Even more preferably, the above-mentioned cervical position and focus detection model is,

[0025] It can be trained using data from the DB regarding cervical location and focus status and an object detection deep learning model training algorithm.

[0026] Even more preferably, the real-time cervical imaging assistance system is,

[0027] It is mounted on the above-mentioned cervical imaging device and can function to assist in cervical imaging by adjusting the camera and lighting of the cervical imaging device based on detection analysis of whether there is an abnormality in the brightness of the real-time camera image, the position of the cervix, and whether there is focus.

[0028] According to the real-time cervical imaging assistance system based on computer vision algorithms and artificial intelligence proposed in the present invention, by comprising an image brightness analysis unit that acquires a real-time camera image captured from a cervical imaging device and performs image brightness analysis through analysis processing of the acquired real-time camera image, a cervical position and focus detection unit that performs cervical position and focus detection within the real-time camera image captured from the cervical imaging device, and a display that provides visualization of the analysis results of the image brightness analysis unit and the cervical position and focus detection unit, it is possible to analyze whether there are brightness abnormalities, cervical position abnormalities, or focus abnormalities in real time and to provide visualization of the analysis results through the real-time cervical imaging assistance system that is mounted on and executed on the device with the real-time camera image captured from the cervical imaging device.

[0029] In addition, according to the real-time cervical imaging assistance system based on the computer vision algorithm and artificial intelligence of the present invention, real-time camera images captured by a cervical imaging device are mounted on the device and executed to analyze in real-time whether there are abnormalities in brightness, cervical position, or focus, and to provide visualized analysis results. This enables assistance in enabling the user to properly photograph the cervix by adjusting the camera and lighting of the cervical imaging device based on the analysis results.

[0030] Furthermore, according to the real-time cervical imaging assistance system based on the computer vision algorithm and artificial intelligence of the present invention, by assisting the user to properly image the cervix through the adjustment of the camera and lighting of the cervical imaging device, it is possible to capture cervical images of excellent quality by assisting in proper cervical imaging while capturing the cervix in real-time based on the computer vision algorithm and artificial intelligence.

[0031] Furthermore, the various and beneficial advantages and effects of the present invention are not limited to those described above and may be more easily understood in the process of explaining specific embodiments of the present invention.

[0032] FIG. 1 is a diagram illustrating the overall conceptual configuration of a real-time cervical imaging assistance system based on a computer vision algorithm and artificial intelligence according to an embodiment of the present invention.

[0033] FIG. 2 is a diagram illustrating the configuration of a real-time cervical imaging assistance system based on a computer vision algorithm and artificial intelligence according to an embodiment of the present invention in functional blocks.

[0034] FIG. 3 is a conceptual block diagram of a real-time cervical imaging assistance system based on a computer vision algorithm and artificial intelligence according to an embodiment of the present invention.

[0035] FIG. 4 is a diagram illustrating the structure of a cervical position and focus detection model of a real-time cervical imaging assistance system based on a computer vision algorithm and artificial intelligence according to an embodiment of the present invention.

[0036] FIG. 5 is a diagram illustrating an example of visualization of the analysis results of a cervical position and focus detection unit of a real-time cervical imaging assistance system based on a computer vision algorithm and artificial intelligence according to an embodiment of the present invention.

[0037] Embodiments of the present invention are described below with reference to the attached drawings so that those skilled in the art can easily implement the invention. However, the present invention may be embodied in various different forms and is not limited to the embodiments described herein. Furthermore, in order to clearly explain the present invention in the drawings, parts unrelated to the explanation have been omitted, and similar parts throughout the specification are denoted by similar reference numerals.

[0038] Throughout the specification, when a part is described as being "connected" to another part, this includes not only cases where they are "directly connected" but also cases where they are "indirectly connected" with other elements interposed between them. Furthermore, when a part is described as "including" a component, this means that, unless specifically stated otherwise, it does not exclude other components but rather allows for the inclusion of additional components; it should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0039] The following examples are detailed descriptions to aid in understanding the present invention and are not intended to limit the scope of the present invention. Accordingly, inventions within the same scope that perform the same function as the present invention will also fall within the scope of the present invention.

[0040] In addition, each component, process, procedure, or method included in each embodiment of the present invention may be shared within a scope that is not technically contradictory to one another.

[0041] FIG. 1 is a diagram illustrating the overall conceptual configuration of a real-time cervical imaging assistance system based on a computer vision algorithm and artificial intelligence according to an embodiment of the present invention, FIG. 2 is a diagram illustrating the configuration of a real-time cervical imaging assistance system based on a computer vision algorithm and artificial intelligence according to an embodiment of the present invention in functional blocks, and FIG. 3 is a diagram illustrating a conceptual block diagram of a real-time cervical imaging assistance system based on a computer vision algorithm and artificial intelligence according to an embodiment of the present invention. As illustrated in FIGS. 1 to 3, a real-time cervical imaging assistance system (100) based on a computer vision algorithm and artificial intelligence according to an embodiment of the present invention may be configured to include: an image brightness analysis unit (110) that acquires a real-time camera image captured from a cervical imaging device (101) and performs image brightness analysis through analysis processing of the acquired real-time camera image; a cervical position and focus detection unit (120) that performs cervical position and focus detection within a real-time camera image captured from a cervical imaging device (101); and a display (130) that provides visualization of the analysis results of the image brightness analysis unit (110) and the cervical position and focus detection unit (120). Hereinafter, the specific configuration of a real-time cervical imaging assistance system based on a computer vision algorithm and artificial intelligence according to an embodiment of the present invention will be described in detail with reference to the attached drawings.

[0042] FIG. 4 is a diagram illustrating the structure of a cervical position and focus detection model of a real-time cervical imaging assistance system based on a computer vision algorithm and artificial intelligence according to an embodiment of the present invention, and FIG. 5 is a diagram illustrating an example of visualization of the analysis results of a cervical position and focus detection unit of a real-time cervical imaging assistance system based on a computer vision algorithm and artificial intelligence according to an embodiment of the present invention.

[0043] The image brightness analysis unit (110) is configured to acquire a real-time camera image captured from a cervical imaging device (101) and perform image brightness analysis through analysis processing of the acquired real-time camera image. This image brightness analysis unit (110) may be configured as a brightness abnormality detection model that performs image brightness analysis through analysis processing of a real-time camera image captured from a cervical imaging device (101). Here, the brightness abnormality detection model analyzes whether there is a brightness abnormality in the real-time camera image and can provide the image brightness analysis results so that the user can check them through a display (130).

[0044] Additionally, the brightness anomaly detection model of the image brightness analysis unit (110) can be generated through an image brightness analysis algorithm. This brightness anomaly detection model can be generated as a model that statistically analyzes the pixel value distribution of the image based on a database of captured cervical images to determine a threshold for classifying dark images and bright images, and detects whether there is an anomaly in the brightness of the image based on the determined threshold.

[0045] Additionally, the brightness anomaly detection model of the image brightness analysis unit (110) can function to convert the brightness level of an image from a real-time camera image into a numerical value through computer vision technology. This brightness anomaly detection model can determine whether the current brightness of the cervical imaging device (101) is suitable for imaging, and can provide this analysis result information through a display (130) to enable the user to adjust the lighting of the cervical imaging device (101).

[0046] The cervical position and focus detection unit (120) is configured to perform position and focus detection of the cervix within a real-time camera image captured from a cervical imaging device (101). This cervical position and focus detection unit (120) may be configured as a cervical position and focus detection model that performs position and focus detection of the cervix within a real-time camera image captured from a cervical imaging device (101). Here, the cervical position and focus detection model may provide the analysis results of the position and focus detection of the cervix within the real-time camera image captured from the cervical imaging device (101) by visualizing them on the display (130) through an analysis result visualization processing operation.

[0047] Additionally, the cervical location and focus detection model can be trained using data from the cervical location and focus DB (121) and an object detection deep learning model training algorithm. Here, the cervical location and focus DB (121) is a database containing tens of thousands of captured cervical images and information regarding the cervical location and focus abnormality of each image. Furthermore, the object detection deep learning model training algorithm uses a YOLO (You Only Look Once) based structure and selects and uses a model with a parameter size capable of real-time detection among various parameters. At this time, the object detection model is designed based on a CNN (Convolutional Neural Network), which demonstrates excellent performance in the field of vision among deep learning models, and enables the detection of the location of objects included in the image and the classification of the types of objects. Figure 4 shows the structure of the YOLO model.

[0048] Additionally, the cervical position and focus detection model of the cervical position and focus detection unit (120) can function to detect the position of the cervix and classify whether there is an abnormality in the focus of the image by learning an object detection deep learning model based on a database included in the cervical position and focus detection DB (121) containing cervical position information and whether there is an abnormality in the focus. That is, the cervical position and focus detection model is trained as an artificial intelligence model using deep learning technology to detect the position of the cervix within the image and classify whether there is an abnormality in the focus of the image, and through the trained artificial intelligence model, it is possible to visualize the real-time cervical position and whether there is an abnormality in the focus through the display (130) and assist the user in correctly photographing the cervix.

[0049] The display (130) is configured to provide a visualization of the analysis results of the image brightness analysis unit (110) and the cervical position and focus detection unit (120). This display (130) can function to provide the user with the analysis results of the image brightness analysis unit (110) and the cervical position and focus detection unit (120) in real time so that the user can properly photograph the cervix. Here, the analysis information including conditions provided through the display (130) is designed through UI / UX to display and convey information using blue for normal cases and red for abnormal cases, and the location information can be provided as a visualization by rendering it on the screen.

[0050] In this way, a real-time cervical imaging assistance system (100) based on a computer vision algorithm and artificial intelligence, comprising an image brightness analysis unit (110) that acquires a real-time camera image captured from a cervical imaging device (101) and performs image brightness analysis through analysis processing of the acquired real-time camera image, a cervical position and focus detection unit (120) that performs cervical position and focus detection within a real-time camera image captured from a cervical imaging device (101), and a display (130) that provides visualization of the analysis results of the image brightness analysis unit (110) and the cervical position and focus detection unit (120), is mounted on the cervical imaging device (101) as an on-device and can function to assist in cervical imaging by adjusting the camera and lighting of the cervical imaging device (101) based on the detection analysis of whether there is an abnormality in the brightness of the real-time camera image, the position of the cervix, and the focus.

[0051] As described above, a real-time cervical imaging assistance system based on a computer vision algorithm and artificial intelligence according to an embodiment of the present invention comprises: an image brightness analysis unit that acquires a real-time camera image captured by a cervical imaging device and performs image brightness analysis through analysis processing of the acquired real-time camera image; a cervical position and focus detection unit that performs detection of the position and focus of the cervix within the real-time camera image captured by the cervical imaging device; and a display that provides visualization of the analysis results of the image brightness analysis unit and the cervical position and focus detection unit. By enabling the real-time cervical imaging assistance system, which is mounted on and executed on a device, to analyze in real-time whether there are brightness abnormalities, cervical position and focus abnormalities, and to provide visualized analysis results, in particular, by enabling the real-time cervical imaging assistance system, which is mounted on and executed on a device, to analyze in real-time whether there are brightness abnormalities, cervical position and focus abnormalities, and to provide visualized analysis results, the user can correctly image the cervix by adjusting the camera and lighting of the cervical imaging device based on the analysis results. It is possible to provide assistance, and furthermore, by assisting the user in properly photographing the cervix through the adjustment of the camera and lighting of the cervical imaging device, it becomes possible to photograph the cervix in real-time based on computer vision algorithms and artificial intelligence, thereby enabling the capture of high-quality cervical images by assisting in the proper photographing.

[0052] The foregoing description of the present invention is for illustrative purposes only, and those skilled in the art will understand that other specific forms can be easily modified without altering the technical spirit or essential features of the present invention. Therefore, the embodiments described above should be understood as illustrative in all respects and not restrictive. For example, each component described as a single unit may be implemented in a distributed manner, and components described as distributed may likewise be implemented in a combined form.

[0053] The scope of the present invention is defined by the claims set forth below rather than by the detailed description above, and all modifications or variations derived from the meaning and scope of the claims and equivalent concepts thereof should be interpreted as being included within the scope of the present invention.

Claims

1. A real-time cervical imaging assistance system (100) based on computer vision algorithms and artificial intelligence, An image brightness analysis unit (110) that acquires a real-time camera image captured from a cervical imaging device (101) and performs image brightness analysis through analysis processing of the acquired real-time camera image; A cervical position and focus detection unit (120) that performs cervical position and focus detection within a real-time camera image captured from the above cervical imaging device (101); and A real-time cervical imaging assistance system based on computer vision algorithms and artificial intelligence, characterized by including a display (130) that provides visualization of the analysis results of the image brightness analysis unit (110) and the cervical position and focus detection unit (120).

2. In paragraph 1, the image brightness analysis unit (110) is, A real-time cervical imaging assistance system based on computer vision algorithms and artificial intelligence, characterized by being composed of a brightness abnormality detection model that performs image brightness analysis through analysis processing of real-time camera images captured from the above-mentioned cervical imaging device (101).

3. In paragraph 2, the brightness anomaly detection model is, A real-time cervical imaging assistance system based on computer vision algorithms and artificial intelligence, characterized by analyzing whether there is an abnormality in the brightness of the real-time camera image and providing the image brightness analysis result so that the user can check it through the display (130).

4. In any one of paragraphs 1 to 3, the cervical position and focus detection unit (120) is, A real-time cervical imaging assistance system based on computer vision algorithms and artificial intelligence, characterized by being composed of a cervical position and focus detection model that performs cervical position and focus detection within a real-time camera image captured from the above cervical imaging device (101).

5. In paragraph 4, the above-mentioned cervical position and focus detection model is, A real-time cervical imaging assistance system based on computer vision algorithms and artificial intelligence, characterized by providing an analysis result visualized on the display (130) through an analysis result visualization process, in which the position and focus of the cervix are detected within a real-time camera image captured from the cervical imaging device (101).

6. In paragraph 5, the above-mentioned cervical position and focus detection model is, A real-time cervical imaging assistance system based on computer vision algorithms and artificial intelligence, characterized by being trained through data from a cervical position and focus status DB (121) and an object detection deep learning model learning algorithm.

7. In paragraph 6, the real-time cervical imaging assistance system (100) is, A real-time cervical imaging assistance system based on computer vision algorithms and artificial intelligence, characterized by being mounted on the cervical imaging device (101) as an on-device and functioning to assist in cervical imaging by adjusting the camera and lighting of the cervical imaging device (101) based on detection analysis of whether there is an abnormality in the brightness of the real-time camera image, the position of the cervix, and whether there is focus.

Images