A system for capturing and analyzing image data of a target

The location of the area of ​​interest in the fundus color illumination is determined through the image analysis unit of the image data system, and the problem of blind scanning and detection time in the prior art is solved, and efficient and accurate identification of fundus lesions is achieved.

CN113947592BActive Publication Date: 2024-11-15ZHONGSHAN OPHTHALMIC CENT SUN YAT SEN UNIV
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202111284291.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-11-01
Publication Date
2024-11-15
Estimated Expiration
2041-11-01

AI Technical Summary

Technical Problem

The existing fundus color examination system cannot determine the location of the region of interest in other areas of the retina, resulting in blindness in the scan and long detection time.

Method used

A system of image data to capture and analyze targets is designed, including an image acquisition unit, an image preprocessing unit, an image analysis unit and a lesion scanning unit. By establishing a coordinate system and analyzing the clarity of the blood vessel edge, the location of the region of interest is determined and based on Preset standards are compared and classified, and high-risk areas are preferred.

Benefits of technology

Improves the accuracy and flexibility of the scan, saves detection time, and ensures accurate identification and rapid response to fundus lesions.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113947592B_ABST
    Figure CN113947592B_ABST
Patent Text Reader

Abstract

The present invention relates to a system for capturing and analyzing image data of a target, comprising: an image acquisition unit, used for acquiring a color fundus photograph; an image preprocessing unit, used for preprocessing the color fundus photograph; an image analysis unit, used for analyzing whether an area of ​​interest exists in the color fundus photograph, the image analysis unit establishing a coordinate system on the color fundus photograph to determine the position of the area of ​​interest, and when the position of the area of ​​interest is determined, the image analysis unit sends the position of the area of ​​interest to a lesion scanning unit; the lesion scanning unit is used for scanning the positions of each area of ​​interest in the color fundus photograph to determine each area of ​​interest for scanning; a storage unit, used for storing data of each stage; the present invention can more accurately determine whether an area of ​​interest exists, and then accurately scan the marked area of ​​interest, thereby improving the accuracy and flexibility of scanning the fundus, and further saving the scanning time of the system of the present invention.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of image recognition, and in particular to a system for capturing and analyzing image data of a target. Background Art

[0002] Fundus color photography is a way to examine the fundus. It can be used to see the tissue structure of the fundus, analyze the normal and abnormal structure of the fundus, and determine whether there are problems with the optic disc, blood vessels, retina or choroid of the fundus. The existing inspection system can only scan the macula and optic disc of the fundus at fixed points. Without knowing whether there are lesions in other retinal areas, scanning other retinal areas cannot determine the location of the area of ​​interest. The scanning is blind and the inspection time is long. Summary of the invention

[0003] To this end, the present invention provides a system for capturing and analyzing image data of a target, so as to overcome the problems in the prior art that the location of an area of ​​interest cannot be determined, the scanning is blind, and the detection time is long.

[0004] To achieve the above object, the present invention provides a system for capturing and analyzing image data of a target, comprising:

[0005] An image acquisition unit, used for acquiring a color fundus photograph;

[0006] An image preprocessing unit connected to the image processing unit and used for preprocessing the fundus color photograph. When a black frame exists on the outermost side of the fundus color photograph, the image processing unit will remove the black frame on the outermost side of the fundus color photograph.

[0007] An image analysis unit connected to the image preprocessing unit is used to analyze whether there is a region of interest in the fundus color photograph according to the clarity D of the blood vessel edge in the fundus color photograph, and the image analysis unit establishes a coordinate system on the fundus color photograph to determine the position of the region of interest. When the position of the region of interest is determined, the image analysis unit sends the position of the region of interest to the lesion scanning unit;

[0008] The lesion scanning unit is connected to the image analysis unit and is used to scan the positions of the regions of interest in the fundus color photograph to determine the regions of interest for scanning;

[0009] A storage unit is connected to the image acquisition unit, the image preprocessing unit, the image analysis unit and the lesion scanning unit, and is used to store data at each stage.

[0010] Further, when the image analysis unit analyzes the fundus color photograph, the image analysis unit determines the blood vessel edge position coordinates through the coordinate system, obtains the blood vessel edge clarity D corresponding to the actual blood vessel edge position coordinates, and compares D with the preset standard blood vessel edge clarity D0 to determine whether there is an area of ​​interest at the coordinates;

[0011] The preset standard blood vessel edge clarity D0 includes a first preset standard blood vessel edge clarity D1 and a second preset standard blood vessel edge clarity D2, wherein D1<D2;

[0012] When D<D1, the image analysis unit determines that the blood vessel edge clarity corresponding to the actual blood vessel edge position coordinates meets the standard and there is no region of interest;

[0013] When D1≤D≤D2, the image analysis unit determines that it is impossible to determine whether there is a region of interest at the coordinates according to the blood vessel edge clarity D corresponding to the actual blood vessel edge position coordinates;

[0014] When D>D2, the image analysis unit determines that the blood vessel edge clarity corresponding to the actual blood vessel edge position coordinates does not meet the standard and there is a region of interest; when the determination is completed, the image analysis unit marks the position of the region of interest and sends the marked position to the lesion scanning unit.

[0015] Further, when the image analysis unit determines that it is impossible to determine whether there is an area of ​​interest at the coordinates based on the blood vessel edge clarity D corresponding to the actual blood vessel edge position coordinates, the image analysis unit calculates the actual user health score R to correct the actual blood vessel edge clarity D. The image analysis unit records the corrected actual blood vessel edge clarity as Da, and sets Da=D×(R / R0), where R0 is the preset user health score.

[0016] Furthermore, the user health score R is calculated using the following formula:

[0017] R = (Q / 25) / (W×0.43+P);

[0018] Among them, Q is the user's age, W is the user's smoking age, and P is the number of stages of diabetes for the user.

[0019] Further, when the image analysis unit determines that the blood vessel edge clarity corresponding to the actual blood vessel edge position coordinates does not meet the standard and there is a region of interest, the image analysis unit calculates the actual blood vessel edge clarity difference △D, sets △D=D-D2, and when the calculation is completed, the image analysis unit compares △D with the preset blood vessel edge clarity difference to classify the region of interest;

[0020] The preset blood vessel edge clarity difference includes a first preset blood vessel edge clarity difference △D1, a second preset blood vessel edge clarity difference △D2 and a third preset blood vessel edge clarity difference △D3, wherein △D1<△D2<△D3;

[0021] When △D<△D1, the image analysis unit determines that the ROI is a primary ROI;

[0022] When △D1≤△D<△D2, the image analysis unit determines that the ROI is a secondary ROI;

[0023] When △D2≤△D<△D3, the image analysis unit determines that the ROI is a third-level ROI;

[0024] When △D≥△D3, the image analysis unit determines that the ROI is a level 4 ROI;

[0025] When the lesion scanning unit scans the region of interest, the region of interest is scanned in a priority order, wherein the priority order is fourth-level region of interest>third-level region of interest>second-level region of interest>first-level region of interest.

[0026] Further, when the image analysis unit determines that the blood vessel edge clarity corresponding to the actual blood vessel edge position coordinates meets the standard and there is no region of interest, the image analysis unit calculates the blood vessel width A according to the blood vessel edge coordinates, and compares A with the preset blood vessel width A0 to determine whether the blood vessel width meets the standard;

[0027] When A>A0, the image analysis unit determines that the blood vessel width does not meet the standard, and obtains the coordinates of the location and marks it as a region of interest;

[0028] When A≤A0, the image analysis unit determines that the blood vessel width meets the standard and there is no region of interest.

[0029] Further, when the image processing unit calculates the blood vessel width, the image processing unit obtains the user's myopia degree F, and compares F with a preset myopia degree F0 to determine whether to correct the blood vessel width A;

[0030] When F≤F0, the image processing unit determines that the blood vessel width A does not need to be corrected;

[0031] When F>F0, the image processing unit determines that the blood vessel width A needs to be corrected, and the image processing unit records the corrected blood vessel width as Aa, and sets Aa=A×(1+(F / F0)×0.015).

[0032] Further, when the image analysis unit determines that the blood vessel width does not meet the standard and obtains the coordinates of the location as a region of interest, the image analysis unit calculates the blood vessel width difference △A, sets △A=A-A0, and when the calculation is completed, the image analysis unit compares △A with the preset blood vessel width difference to classify the region of interest;

[0033] The preset blood vessel width difference includes a first preset blood vessel width difference △A1, a second preset blood vessel width difference △A2 and a third preset blood vessel width difference △A3, wherein △A1<△A2<△A3;

[0034] When △A<△A1, the image analysis unit determines that the ROI is a primary ROI;

[0035] When △A1≤△A<△A2, the image analysis unit determines that the ROI is a secondary ROI;

[0036] When △A2≤△A<△A3, the image analysis unit determines that the ROI is a level 3 ROI;

[0037] When △A≥△A3, the image analysis unit determines that the ROI is a level 4 ROI;

[0038] When the lesion scanning unit scans the region of interest, the region of interest is scanned in a priority order, wherein the priority order is fourth-level region of interest>third-level region of interest>second-level region of interest>first-level region of interest.

[0039] Furthermore, the image processing unit obtains the brightness S of each coordinate point in the fundus color photograph, and compares S with a preset brightness S0 to determine whether there is an area of ​​interest;

[0040] When S≥S0, the image processing unit determines that there is a region of interest, and sends the coordinates of the region of interest to the lesion scanning unit;

[0041] When S<S0, the image processing unit determines that there is no region of interest.

[0042] Furthermore, the lesion scanning unit is an OCT scanning device.

[0043] Compared with the prior art, the beneficial effect of the present invention lies in that the present invention analyzes the acquired fundus color photograph in advance through the image analysis unit to determine whether there is a region of interest in the fundus reference, establishes a coordinate system in the image acquisition unit to determine the position of the region of interest and marks it, and quickly marks the position of the region of interest through the image analysis unit, so that the lesion scanning unit can accurately scan the marked region of interest, thereby improving the accuracy and flexibility of the system of the present invention in scanning the fundus, and further saving the scanning time of the system of the present invention.

[0044] Furthermore, a standard blood vessel edge clarity D0 is preset in the image analysis unit of the present invention. When analyzing the fundus color photograph, the image analysis unit obtains the clarity of each blood vessel edge in real time, and compares the actual blood vessel edge clarity with the preset standard blood vessel edge clarity D0 to quickly determine whether the blood vessel edge clarity meets the preset standard. When the blood vessel edge clarity does not meet the preset standard, the image analysis unit marks the blood vessel edge position coordinates and sends them to the lesion scanning unit to scan the position to determine whether a lesion occurs at the position. By quickly marking the position of the region of interest through the image analysis unit, the lesion scanning unit can accurately scan the marked region of interest, thereby improving the accuracy and flexibility of the system of the present invention in scanning the fundus, and further saving the scanning time of the system of the present invention.

[0045] Furthermore, the image analysis unit of the present invention also presets a blood vessel edge clarity difference, and the real-time blood vessel edge clarity of the image acquisition unit is used to calculate the actual blood vessel edge clarity difference, and △D is compared with the preset blood vessel edge clarity difference to classify the region of interest, so that the lesion scanning unit can scan each region of interest more accurately, thereby improving the accuracy and flexibility of the system of the present invention in scanning the fundus, and further saving the scanning time of the system of the present invention.

[0046] Furthermore, a blood vessel width A0 is preset in the image scanning unit of the present invention. When the image analysis unit determines that the blood vessel edge clarity corresponding to the actual blood vessel edge position coordinates meets the standard and there is no region of interest, the image analysis unit calculates the blood vessel width A based on the blood vessel edge coordinates, and compares A with the preset blood vessel width A0 to determine whether the blood vessel width meets the standard. By judging the blood vessel width, the position of the region of interest can be determined more accurately, and the lesion scanning unit can then accurately scan the marked region of interest, thereby improving the accuracy and flexibility of the system of the present invention in scanning the fundus, and further saving the scanning time of the system of the present invention.

[0047] Furthermore, a myopia degree F0 is preset in the image processing unit of the present invention. When the image processing unit calculates the blood vessel width, the image processing unit obtains the user's myopia degree F and compares F with the preset myopia degree F0 to determine whether to correct the blood vessel width A. By obtaining the user's myopia degree through the image processing unit, the blood vessel width can be grasped more accurately, and whether there is an area of ​​interest can be determined more accurately, so that the lesion scanning unit can accurately scan the marked area of ​​interest, thereby improving the accuracy and flexibility of the system of the present invention in scanning the fundus, and further saving the scanning time of the system of the present invention.

[0048] Furthermore, the image analysis unit of the present invention also presets a blood vessel width difference, and the real-time blood vessel width of the image acquisition unit is used to calculate the actual blood vessel width difference, and △A is compared with the preset blood vessel width difference to classify the region of interest, so that the lesion scanning unit can scan each region of interest more accurately, thereby improving the accuracy and flexibility of the system of the present invention in scanning the fundus, and further saving the scanning time of the system of the present invention.

[0049] Furthermore, in the present invention, by setting a preset brightness S0, when analyzing the fundus color photograph, the image processing unit obtains the brightness S of each coordinate point in the fundus color photograph, and compares S with the preset brightness S0 to see whether there is a region of interest. By marking the high-brightness area, the lesion scanning unit can scan each region of interest more accurately, thereby improving the accuracy and flexibility of the system of the present invention in scanning the fundus, and further saving the scanning time of the system of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 A structural block diagram of a system for capturing and analyzing image data of a target according to the present invention. DETAILED DESCRIPTION

[0051] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0052] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0053] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0054] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0055] See also Figure 1 As shown, it is a structural block diagram of the system for capturing and analyzing the image data of the target according to the invention, comprising:

[0056] An image acquisition unit, used for acquiring a color fundus photograph;

[0057] An image preprocessing unit connected to the image processing unit and used for preprocessing the fundus color photograph. When a black frame exists on the outermost side of the fundus color photograph, the image processing unit will remove the black frame on the outermost side of the fundus color photograph.

[0058] An image analysis unit connected to the image preprocessing unit is used to analyze whether there is a region of interest in the fundus color photograph according to the clarity D of the blood vessel edge in the fundus color photograph, and the image analysis unit establishes a coordinate system on the fundus color photograph to determine the position of the region of interest. When the position of the region of interest is determined, the image analysis unit sends the position of the region of interest to the lesion scanning unit;

[0059] Specifically, when the image analysis unit analyzes the fundus color photograph, the image analysis unit marks each blood vessel in a clockwise direction as the 1st blood vessel, the 2nd blood vessel, ..., the nth blood vessel. After marking, the image analysis unit establishes the upper edge starting point coordinates n(x1, y1), the upper edge ending point coordinates n(xj, yj), the lower edge starting point coordinates n'(x'1, y'1) and the lower edge ending point coordinates n'(x'j, y'j+1) of the blood vessel from the growth position of the nth blood vessel along the growth direction of the blood vessel.

[0060] Specifically, the image analysis unit obtains the actual blood vessel edge clarity corresponding to each actual blood vessel edge coordinate corresponding to the edge coordinate of the starting point of the first blood vessel to the edge coordinate of the ending point of the first blood vessel to analyze whether there is a region of interest in the fundus color photograph;

[0061] The image analysis unit obtains the actual blood vessel edge clarity corresponding to each actual blood vessel edge coordinate corresponding to the edge coordinate of the starting point of the second blood vessel to the edge coordinate of the ending point of the second blood vessel to analyze whether there is a region of interest in the fundus color photograph;

[0062] The image analysis unit obtains the actual blood vessel edge clarity corresponding to each actual blood vessel edge coordinate corresponding to the edge coordinate of the starting point of the nth blood vessel to the edge coordinate of the ending point of the nth blood vessel to analyze whether there is an area of ​​interest in the fundus color photograph.

[0063] The lesion scanning unit is connected to the image analysis unit and is used to scan the positions of the regions of interest in the fundus color photograph to determine the regions of interest for scanning; wherein the lesion scanning unit may be an OCT scanning device or other scanning devices capable of identifying lesions;

[0064] A storage unit is connected to the image acquisition unit, the image preprocessing unit, the image analysis unit and the lesion scanning unit, and is used to store data at each stage.

[0065] Specifically, the present invention uses an image analysis unit to pre-analyze the acquired fundus color photograph to determine whether there is a region of interest in the fundus reference, establishes a coordinate system in the image acquisition unit to determine the position of the region of interest and marks it, and uses the image analysis unit to quickly mark the position of the region of interest, so that the lesion scanning unit can accurately scan the marked region of interest, thereby improving the accuracy and flexibility of the system of the present invention in scanning the fundus, and further saving the scanning time of the system of the present invention.

[0066] Specifically, when the image analysis unit analyzes the fundus color photograph, the image analysis unit determines the blood vessel edge position coordinates through the coordinate system, obtains the blood vessel edge clarity D corresponding to the actual blood vessel edge position coordinates, and compares D with the preset standard blood vessel edge clarity D0 to determine whether there is an area of ​​interest at the coordinates;

[0067] The preset standard blood vessel edge clarity D0 includes a first preset standard blood vessel edge clarity D1 and a second preset standard blood vessel edge clarity D2, wherein D1<D2;

[0068] When D<D1, the image analysis unit determines that the blood vessel edge clarity corresponding to the actual blood vessel edge position coordinates meets the standard and there is no region of interest;

[0069] When D1≤D≤D2, the image analysis unit determines that it is impossible to determine whether there is a region of interest at the coordinates according to the blood vessel edge clarity D corresponding to the actual blood vessel edge position coordinates;

[0070] When D>D2, the image analysis unit determines that the blood vessel edge clarity corresponding to the actual blood vessel edge position coordinates does not meet the standard and there is a region of interest; when the determination is completed, the image analysis unit marks the position of the region of interest and sends the marked position to the lesion scanning unit.

[0071] Specifically, a standard blood vessel edge clarity D0 is preset in the image analysis unit of the present invention. When the image analysis unit analyzes the fundus color photograph, the image analysis unit obtains the clarity of each blood vessel edge in real time, and compares the actual blood vessel edge clarity with the preset standard blood vessel edge clarity D0 to quickly determine whether the blood vessel edge clarity meets the preset standard. When the blood vessel edge clarity does not meet the preset standard, the image analysis unit marks the blood vessel edge position coordinates and sends them to the lesion scanning unit to scan the position to determine whether a lesion occurs at the position. By quickly marking the position of the region of interest through the image analysis unit, the lesion scanning unit can accurately scan the marked region of interest, thereby improving the accuracy and flexibility of the system of the present invention in scanning the fundus, and further saving the scanning time of the system of the present invention.

[0072] Specifically, when the image analysis unit determines that it is impossible to determine whether there is an area of ​​interest at the coordinates based on the blood vessel edge clarity D corresponding to the actual blood vessel edge position coordinates, the image analysis unit calculates the actual user health score R to correct the actual blood vessel edge clarity D. The image analysis unit records the corrected actual blood vessel edge clarity as Da, and sets Da = D×(R / R0), where R0 is the preset user health score.

[0073] Specifically, the image analysis unit of the present invention also presets a user health score R0. When determining the region of interest, the image analysis unit obtains the user's previous diagnostic information to determine the user's age, smoking years, diabetes severity or other information, and calculates the user's health score through the user's previous diagnostic information, thereby further determining whether the blood vessel edge clarity meets the preset standard. By correcting the actual blood vessel edge clarity D, it can be more accurately determined whether there is a region of interest, and then the lesion scanning unit can accurately scan the marked region of interest, thereby improving the accuracy and flexibility of the system of the present invention in scanning the fundus, and further saving the scanning time of the system of the present invention.

[0074] Specifically, the user health score R is calculated using the following formula:

[0075] R = (Q / 25) / (W×0.43+P);

[0076] Among them, Q is the user's age, W is the user's smoking age, and P is the number of stages of diabetes for the user.

[0077] Specifically, when the image analysis unit determines that the blood vessel edge clarity corresponding to the actual blood vessel edge position coordinates does not meet the standard and there is a region of interest, the image analysis unit calculates the actual blood vessel edge clarity difference △D, sets △D=D-D2, and when the calculation is completed, the image analysis unit compares △D with the preset blood vessel edge clarity difference to classify the region of interest;

[0078] The preset blood vessel edge clarity difference includes a first preset blood vessel edge clarity difference △D1, a second preset blood vessel edge clarity difference △D2 and a third preset blood vessel edge clarity difference △D3, wherein △D1<△D2<△D3;

[0079] When △D<△D1, the image analysis unit determines that the ROI is a primary ROI;

[0080] When △D1≤△D<△D2, the image analysis unit determines that the ROI is a secondary ROI;

[0081] When △D2≤△D<△D3, the image analysis unit determines that the ROI is a third-level ROI;

[0082] When △D≥△D3, the image analysis unit determines that the ROI is a level 4 ROI;

[0083] When the lesion scanning unit scans the region of interest, the region of interest is scanned in a priority order, wherein the priority order is fourth-level region of interest>third-level region of interest>second-level region of interest>first-level region of interest.

[0084] Specifically, the image analysis unit of the present invention also presets a blood vessel edge clarity difference, and the real-time blood vessel edge clarity of the image acquisition unit is used to calculate the actual blood vessel edge clarity difference, and △D is compared with the preset blood vessel edge clarity difference to classify the region of interest, so that the lesion scanning unit can scan each region of interest more accurately, thereby improving the accuracy and flexibility of the system of the present invention in scanning the fundus, and further saving the scanning time of the system of the present invention.

[0085] Specifically, when the image analysis unit determines that the blood vessel edge clarity corresponding to the actual blood vessel edge position coordinates meets the standard and there is no region of interest, the image analysis unit calculates the blood vessel width A according to the blood vessel edge coordinates, and compares A with the preset blood vessel width A0 to determine whether the blood vessel width meets the standard;

[0086] When A>A0, the image analysis unit determines that the blood vessel width does not meet the standard, and obtains the coordinates of the location and marks it as a region of interest;

[0087] When A≤A0, the image analysis unit determines that the blood vessel width meets the standard and there is no region of interest.

[0088] Specifically, the image scanning unit of the present invention also presets a blood vessel width A0. When the image analysis unit determines that the blood vessel edge clarity corresponding to the actual blood vessel edge position coordinates meets the standard and there is no region of interest, the image analysis unit calculates the blood vessel width A based on the blood vessel edge coordinates, and compares A with the preset blood vessel width A0 to determine whether the blood vessel width meets the standard. By judging the blood vessel width, the position of the region of interest can be determined more accurately, and the lesion scanning unit can then accurately scan the marked region of interest, thereby improving the accuracy and flexibility of the system of the present invention in scanning the fundus, and further saving the scanning time of the system of the present invention.

[0089] Specifically, when the image processing unit calculates the blood vessel width, the image processing unit obtains the user's myopia degree F, and compares F with a preset myopia degree F0 to determine whether to correct the blood vessel width A;

[0090] When F≤F0, the image processing unit determines that the blood vessel width A does not need to be corrected;

[0091] When F>F0, the image processing unit determines that the blood vessel width A needs to be corrected, and the image processing unit records the corrected blood vessel width as Aa, and sets Aa=A×(1+(F / F0)×0.015).

[0092] Specifically, a myopia degree F0 is preset in the image processing unit of the present invention. When the image processing unit calculates the blood vessel width, the image processing unit obtains the user's myopia degree F and compares F with the preset myopia degree F0 to determine whether to correct the blood vessel width A. By obtaining the user's myopia degree through the image processing unit, the blood vessel width can be grasped more accurately, and whether there is an area of ​​interest can be determined more accurately, so that the lesion scanning unit can accurately scan the marked area of ​​interest, thereby improving the accuracy and flexibility of the system of the present invention in scanning the fundus, and further saving the scanning time of the system of the present invention.

[0093] Specifically, when the image analysis unit determines that the blood vessel width does not meet the standard and obtains the coordinates of the location as a region of interest, the image analysis unit calculates the blood vessel width difference △A, sets △A=A-A0, and when the calculation is completed, the image analysis unit compares △A with the preset blood vessel width difference to classify the region of interest;

[0094] The preset blood vessel width difference includes a first preset blood vessel width difference △A1, a second preset blood vessel width difference △A2 and a third preset blood vessel width difference △A3, wherein △A1<△A2<△A3;

[0095] When △A<△A1, the image analysis unit determines that the ROI is a primary ROI;

[0096] When △A1≤△A<△A2, the image analysis unit determines that the ROI is a secondary ROI;

[0097] When △A2≤△A<△A3, the image analysis unit determines that the ROI is a level 3 ROI;

[0098] When △A≥△A3, the image analysis unit determines that the ROI is a level 4 ROI;

[0099] When the lesion scanning unit scans the region of interest, the region of interest is scanned in a priority order, wherein the priority order is fourth-level region of interest>third-level region of interest>second-level region of interest>first-level region of interest.

[0100] Specifically, the image analysis unit of the present invention also presets a blood vessel width difference, and the real-time blood vessel width of the image acquisition unit is used to calculate the actual blood vessel width difference, and △A is compared with the preset blood vessel width difference to classify the region of interest, so that the lesion scanning unit can scan each region of interest more accurately, thereby improving the accuracy and flexibility of the system of the present invention in scanning the fundus, and further saving the scanning time of the system of the present invention.

[0101] Specifically, the image processing unit obtains the brightness S of each coordinate point in the fundus color photograph, and compares S with a preset brightness S0 to determine whether there is an area of ​​interest;

[0102] When S≥S0, the image processing unit determines that there is a region of interest, and sends the coordinates of the region of interest to the lesion scanning unit;

[0103] When S<S0, the image processing unit determines that there is no region of interest.

[0104] Specifically, in the present invention, by setting a preset brightness S0, when analyzing the fundus color photograph, the image processing unit obtains the brightness S of each coordinate point in the fundus color photograph, and compares S with the preset brightness S0 to see whether there is a region of interest. By marking the high-brightness area, the lesion scanning unit can scan each region of interest more accurately, thereby improving the accuracy and flexibility of the system of the present invention in scanning the fundus, and further saving the scanning time of the system of the present invention.

[0105] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0106] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A system for capturing and analyzing image data of a target, characterized in that: include: An image acquisition unit, used for acquiring a color fundus photograph; An image preprocessing unit connected to the image acquisition unit and used for preprocessing the fundus color photograph. When a black frame exists on the outermost side of the fundus color photograph, the image processing unit will remove the black frame on the outermost side of the fundus color photograph. An image analysis unit connected to the image preprocessing unit is used to analyze whether there is a region of interest in the fundus color photograph according to the clarity D of the blood vessel edge in the fundus color photograph, and the image analysis unit establishes a coordinate system on the fundus color photograph to determine the position of the region of interest. When the position of the region of interest is determined, the image analysis unit sends the position of the region of interest to the lesion scanning unit; The lesion scanning unit is connected to the image analysis unit and is used to scan the positions of the regions of interest in the fundus color photograph to determine the regions of interest for scanning; A storage unit connected to the image acquisition unit, the image preprocessing unit, the image analysis unit and the lesion scanning unit, and used to store data at each stage; When the image analysis unit analyzes the fundus color photograph, the image analysis unit determines the blood vessel edge position coordinates through the coordinate system, obtains the blood vessel edge clarity D corresponding to the actual blood vessel edge position coordinates, and compares D with the preset standard blood vessel edge clarity D0 to determine whether there is an area of ​​interest at the coordinates; The preset standard blood vessel edge clarity D0 includes a first preset standard blood vessel edge clarity D1 and a second preset standard blood vessel edge clarity D2, wherein D1<D2; When D<D1, the image analysis unit determines that the blood vessel edge clarity corresponding to the actual blood vessel edge position coordinates meets the standard and there is no region of interest; When D1≤D≤D2, the image analysis unit determines that it is impossible to determine whether there is a region of interest at the coordinates according to the blood vessel edge clarity D corresponding to the actual blood vessel edge position coordinates; When D>D2, the image analysis unit determines that the blood vessel edge clarity corresponding to the actual blood vessel edge position coordinates does not meet the standard and there is a region of interest; when the determination is completed, the image analysis unit marks the position of the region of interest and sends the marked position to the lesion scanning unit; When the image analysis unit determines that it is impossible to determine whether there is an area of ​​interest at the coordinates based on the blood vessel edge clarity D corresponding to the actual blood vessel edge position coordinates, the image analysis unit calculates the actual user health score R to correct the actual blood vessel edge clarity D. The image analysis unit records the corrected actual blood vessel edge clarity as Da, and sets Da=D×(R / R0), where R0 is the preset user health score.

2. The system for capturing and analyzing image data of a target according to claim 1, characterized in that: The user health score R is calculated using the following formula: R = (Q / 25) / (W×0.43+P); Among them, Q is the user's age, W is the user's smoking age, and P is the number of stages of diabetes for the user.

3. The system for capturing and analyzing image data of a target according to claim 2, characterized in that: When the image analysis unit determines that the blood vessel edge clarity corresponding to the actual blood vessel edge position coordinates does not meet the standard and there is a region of interest, the image analysis unit calculates the actual blood vessel edge clarity difference △D, sets △D=D-D2, and when the calculation is completed, the image analysis unit compares △D with the preset blood vessel edge clarity difference to classify the region of interest; The preset blood vessel edge clarity difference includes a first preset blood vessel edge clarity difference △D1, a second preset blood vessel edge clarity difference △D2 and a third preset blood vessel edge clarity difference △D3, wherein △D1<△D2<△D3; When △D<△D1, the image analysis unit determines that the ROI is a primary ROI; When △D1≤△D<△D2, the image analysis unit determines that the ROI is a secondary ROI; When △D2≤△D<△D3, the image analysis unit determines that the ROI is a third-level ROI; When △D≥△D3, the image analysis unit determines that the ROI is a level 4 ROI; When the lesion scanning unit scans the region of interest, the region of interest is scanned in a priority order, wherein the priority order is fourth-level region of interest>third-level region of interest>second-level region of interest>first-level region of interest.

4. The system for capturing and analyzing image data of a target according to claim 1, characterized in that: When the image analysis unit determines that the blood vessel edge clarity corresponding to the actual blood vessel edge position coordinates meets the standard and there is no region of interest, the image analysis unit calculates the blood vessel width A according to the blood vessel edge coordinates, and compares A with the preset blood vessel width A0 to determine whether the blood vessel width meets the standard; When A>A0, the image analysis unit determines that the blood vessel width does not meet the standard, and obtains the coordinates of the location and marks it as a region of interest; When A≤A0, the image analysis unit determines that the blood vessel width meets the standard and there is no region of interest.

5. The system for capturing and analyzing image data of a target according to claim 4, characterized in that: When the image processing unit calculates the blood vessel width, the image processing unit obtains the user's myopia degree F, and compares F with a preset myopia degree F0 to determine whether to correct the blood vessel width A; When F≤F0, the image processing unit determines that the blood vessel width A does not need to be corrected; When F>F0, the image processing unit determines that the blood vessel width A needs to be corrected, and the image processing unit records the corrected blood vessel width as Aa, and sets Aa=A×(1+(F / F0)×0.015).

6. The system for capturing and analyzing image data of a target according to claim 5, characterized in that: When the image analysis unit determines that the blood vessel width does not meet the standard and obtains the coordinates of the location as a region of interest, the image analysis unit calculates the blood vessel width difference △A, sets △A=A-A0, and when the calculation is completed, the image analysis unit compares △A with the preset blood vessel width difference to classify the region of interest; The preset blood vessel width difference includes a first preset blood vessel width difference △A1, a second preset blood vessel width difference △A2 and a third preset blood vessel width difference △A3, wherein △A1<△A2<△A3; When △A<△A1, the image analysis unit determines that the ROI is a primary ROI; When △A1≤△A<△A2, the image analysis unit determines that the ROI is a secondary ROI; When △A2≤△A<△A3, the image analysis unit determines that the ROI is a level 3 ROI; When △A≥△A3, the image analysis unit determines that the ROI is a level 4 ROI; When the lesion scanning unit scans the region of interest, the region of interest is scanned in a priority order, wherein the priority order is fourth-level region of interest>third-level region of interest>second-level region of interest>first-level region of interest.

7. The system for capturing and analyzing image data of a target according to claim 1, characterized in that: The image processing unit obtains the brightness S of each coordinate point in the fundus color photograph, and compares S with a preset brightness S0 to determine whether there is an area of ​​interest; When S≥S0, the image processing unit determines that there is a region of interest, and sends the coordinates of the region of interest to the lesion scanning unit; When S<S0, the image processing unit determines that there is no region of interest.

8. The system for capturing and analyzing image data of a target according to claim 1, characterized in that: The lesion scanning unit is an OCT scanning device.