Image processing methods and apparatuses, storage media and electronic devices

Abstract

This application provides an image processing method, apparatus, storage medium, and electronic device, relating to the field of fundus image processing technology. The image processing method provided in this application includes: determining each fundus blood vessel contained in a target fundus image; determining pre-intersection points of each fundus blood vessel; removing two-dimensional intersection points of arteries and veins from the pre-intersection points to obtain fundus blood vessel intersection points; for each fundus blood vessel intersection point, determining the vessel angle corresponding to the intersection point based on the intersection point and the corresponding fundus blood vessel; and determining the vessel angle of the target fundus image based on the vessel angles corresponding to each fundus blood vessel intersection point contained in the target fundus image. The image processing method provided in this application can automatically calculate the vessel angle of a target fundus image, and the calculation results are objective, improving the accuracy and efficiency of the vessel angle calculation results.

Description

Technical Field

[0001] This application relates to the field of fundus image processing technology, specifically to an image processing method and apparatus, storage medium and electronic device. Background Technology

[0002] The angle between blood vessels is one of the important morphological features of blood vessels, which can reflect the structural changes of blood vessels. As the blood vessels in the fundus are part of the human body, the angle between blood vessels in the fundus can reflect the structural changes of the blood vessels in the fundus.

[0003] However, current measurements of fundus vascular angles are mostly performed manually, by manually marking the intersection of the two vessels in the vascular arch to calculate the angle, or by machine-assisted manual measurement. Both methods are highly subjective and uncertain, failing to guarantee the objectivity and accuracy of the fundus vascular angle measurements. Therefore, automated measurement of fundus vascular angles has become an urgent problem to be solved. Summary of the Invention

[0004] To address the aforementioned technical problems, this application is proposed. Embodiments of this application provide an image processing method and apparatus, a storage medium, and an electronic device.

[0005] In a first aspect, one embodiment of this application provides an image processing method, which includes: determining each fundus blood vessel contained in the target fundus image based on a target fundus image; determining pre-intersection points of each fundus blood vessel; removing two-dimensional intersection points of arterial and venous vessels from the pre-intersection points to obtain fundus blood vessel intersection points; for each fundus blood vessel intersection point, determining the vascular angle corresponding to the fundus blood vessel intersection point based on the fundus blood vessel intersection point and the fundus blood vessel corresponding to the fundus blood vessel intersection point; and determining the vascular angle of the target fundus image based on the vascular angles corresponding to each fundus blood vessel intersection point contained in the target fundus image.

[0006] In conjunction with the first aspect, in some implementations of the first aspect, the angle of the retinal vessels corresponding to the intersection of retinal vessels is determined based on the intersection of retinal vessels and the corresponding retinal vessels, including: determining the fitted line of the retinal vessels corresponding to the intersection of retinal vessels based on the intersection of retinal vessels and the corresponding retinal vessels; and determining the angle of the retinal vessels corresponding to the intersection of retinal vessels based on the fitted line of the corresponding retinal vessels.

[0007] In conjunction with the first aspect, in some implementations of the first aspect, the fitting line of the fundus blood vessel corresponding to the fundus blood vessel intersection point is determined based on the fundus blood vessel intersection point and the fundus blood vessel corresponding to the fundus blood vessel intersection point, including: based on the fundus blood vessel intersection point, performing a straight line fitting operation or a tangent fitting operation on the fundus blood vessel corresponding to the fundus blood vessel intersection point to obtain the fitting line of the fundus blood vessel corresponding to the fundus blood vessel intersection point.

[0008] In conjunction with the first aspect, in some implementations of the first aspect, after determining the fundus vessels contained in the target fundus image based on the target fundus image, the method further includes: determining the main fundus vessels contained in the target fundus image based on the diameter of the fundus vessels contained in the target fundus image; generating a first arc with the optic disc center point as the center and based on a first preset radius; determining the intersection point of the first arc with the main fundus vessels; performing a curve fitting operation on the main fundus vessels based on the optic disc center point, the intersection point of the first arc with the main fundus vessels, to obtain the main vascular arch corresponding to the main fundus vessels; determining the angle corresponding to the main vascular arch based on the main vascular arch corresponding to the main fundus vessels; and determining the vascular angle of the target fundus image based on the vascular angles corresponding to the intersection points of the fundus vessels contained in the target fundus image, including: determining the vascular angle of the target fundus image based on the angle corresponding to the main vascular arch.

[0009] In conjunction with the first aspect, in some implementations of the first aspect, the main retinal vessels include the aorta and the main vein, and the intersection of retinal vessels includes the intersection of the aorta and the main vein corresponding to the main vessels; based on the intersection of the optic disc center point, the first arc line, and the main retinal vessels, a curve fitting operation is performed on the main retinal vessels to obtain the main vascular arch corresponding to the main retinal vessels, including: based on the intersection of the optic disc center point, the first arc line, and the aorta, a curve fitting operation is performed on the aorta to obtain the aortic vascular arch corresponding to the aorta; based on the intersection of the optic disc center point, the first arc line, and the main vein, a curve fitting operation is performed on the main vein to obtain the main venous vascular arch corresponding to the main vein.

[0010] In conjunction with the first aspect, in some implementations of the first aspect, the angle of the retinal vessels corresponding to the intersection of the retinal vessels and the corresponding retinal vessels is determined, including: generating at least one second arc with the center of the optic disc as the center and based on a second preset radius; for each second arc, the angle corresponding to the main venous arch and the angle corresponding to the aortic arch are determined based on the intersection of the main vessels, the intersection of the second arc with the main venous arch, and the aortic arch, respectively; and the angle corresponding to the main venous arch is determined based on the angle of the aortic arch and the angle of the main venous arch.

[0011] In conjunction with the first aspect, in certain implementations of the first aspect, the fundus vascular intersections include the main vascular arch intersections and the bifurcation vessels of the main vascular arch corresponding to the main vascular arch intersections. Based on the fundus vascular intersections and the corresponding fundus vessels, the vascular angles corresponding to the fundus vascular intersections are determined, including: determining the fitted line of the fundus vessels corresponding to the main vascular arch intersections based on the main vascular arch intersections and the corresponding fundus vessels; determining the vascular angles corresponding to the main vascular arch intersections based on the fitted line of the fundus vessels corresponding to the main vascular arch intersections; and determining the vascular angles of the target fundus image based on the vascular angles corresponding to each fundus vascular intersection included in the target fundus image, including: determining the vascular angles of the target fundus image based on the vascular angles corresponding to the main vascular arch intersections.

[0012] Secondly, one embodiment of this application provides an image processing apparatus, which includes: a first determining module, configured to determine each fundus vessel contained in the target fundus image based on the target fundus image; a second determining module, configured to determine the pre-intersection points of each fundus vessel; a removing module, configured to remove the two-dimensional intersection points of arterial and venous vessels in the pre-intersection points to obtain fundus vessel intersection points; a third determining module, configured to determine the vessel angle corresponding to each fundus vessel intersection point based on the fundus vessel intersection point and the fundus vessel corresponding to the fundus vessel intersection point; and a fourth determining module, configured to determine the vessel angle of the target fundus image based on the vessel angles corresponding to each fundus vessel intersection point contained in the target fundus image.

[0013] Thirdly, one embodiment of this application provides a computer-readable storage medium storing a computer program for performing the image processing method mentioned in any of the above embodiments.

[0014] Fourthly, one embodiment of this application provides an electronic device, which includes: a processor; a memory for storing processor-executable instructions; the processor being used to perform the image processing method mentioned in any of the above embodiments.

[0015] The image processing method provided in this application includes: determining each fundus vessel contained in the target fundus image based on the target fundus image; determining the pre-intersection points of each fundus vessel; removing the two-dimensional intersection points of arteries and veins from the pre-intersection points to obtain fundus vessel intersection points; for each fundus vessel intersection point, determining the vessel angle corresponding to the fundus vessel intersection point based on the fundus vessel intersection point and the corresponding fundus vessel; and determining the vessel angle of the target fundus image based on the vessel angles corresponding to each fundus vessel intersection point contained in the target fundus image. The image processing method provided in this application can automatically calculate the vessel angle of the target fundus image without manual intervention, which can greatly save time and labor costs and improve measurement efficiency and accuracy. At the same time, this method can eliminate the errors and uncertainties of manual calibration in traditional methods by fitting the fundus vessel morphology, thereby improving measurement accuracy. Furthermore, this method is applicable to various types and degrees of fundus vessel changes, such as vessel branches and abnormal vessel tortuosity, and can effectively identify and measure them. The calculation results are objective, improving the accuracy and efficiency of the vessel angle calculation results. Attached Figure Description

[0016] The above and other objects, features, and advantages of this application will become more apparent from the more detailed description of the embodiments of this application in conjunction with the accompanying drawings. The drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the embodiments of this application to explain this application and do not constitute a limitation thereof. In the drawings, the same reference numerals generally represent the same components or steps.

[0017] Figure 1 The diagram shown is a flowchart illustrating an exemplary embodiment of the image processing method provided in this application.

[0018] Figure 2 The image shown is a schematic diagram of a target fundus image provided in an exemplary embodiment of this application.

[0019] Figure 3 The diagram shown is a schematic flowchart of an exemplary embodiment of this application, which describes the process of determining the angle of a retinal blood vessel intersection based on the intersection of retinal blood vessels and the corresponding retinal blood vessels.

[0020] Figure 4 The image shown is a schematic diagram of a target fundus image provided in an exemplary embodiment of this application.

[0021] Figure 5 The image shown is a schematic diagram of a target fundus image provided in an exemplary embodiment of this application.

[0022] Figure 6 The image shown is a schematic diagram of a target fundus image provided in an exemplary embodiment of this application.

[0023] Figure 7a The diagram shown is a flowchart of an image processing method provided in another exemplary embodiment of this application.

[0024] Figure 7b As shown Figure 7a The diagram shows the target fundus image corresponding to the process shown.

[0025] Figure 7c The image shown is a schematic diagram of a target fundus image provided in an exemplary embodiment of this application.

[0026] Figure 8a The diagram shown is a schematic flowchart of an exemplary embodiment of this application, which describes the process of determining the angle of a retinal blood vessel intersection based on the intersection of retinal blood vessels and the corresponding retinal blood vessels.

[0027] Figure 8b As shown Figure 8a The diagram shows the target fundus image corresponding to the process shown.

[0028] Figure 9a The diagram shown is a schematic flowchart of an exemplary embodiment of this application, which describes the process of determining the angle of a retinal blood vessel intersection based on the intersection of retinal blood vessels and the corresponding retinal blood vessels.

[0029] Figure 9b As shown Figure 9a The diagram shows the target fundus image corresponding to the process shown.

[0030] Figure 10 The diagram shown is a flowchart of an image processing method provided in another exemplary embodiment of this application.

[0031] Figure 11 The diagram shown is a schematic representation of the structure of an image processing apparatus provided in an exemplary embodiment of this application.

[0032] Figure 12 The diagram shown is a structural schematic of an electronic device provided in an exemplary embodiment of this application. Detailed Implementation

[0033] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0034] Figure 1 The diagram shown is a flowchart illustrating an exemplary embodiment of the image processing method provided in this application. Figure 1As shown in the embodiments of this application, the image processing method includes the following steps.

[0035] Step S101: Based on the target fundus image, determine each fundus blood vessel contained in the target fundus image.

[0036] In one embodiment of this application, the fundus vessels include the main fundus vessels, secondary fundus vessels, bifurcations of the main fundus vessels, and bifurcations of the secondary fundus vessels. The main fundus vessels include the aorta and the main vein, and the secondary fundus vessels include the secondary arteries and secondary veins. Typically, the largest vessel in the temporal region is the main fundus vessel, and the largest vessel in the nasal region is the secondary fundus vessel.

[0037] In one embodiment of this application, arteries and veins are identified based on characteristics such as the pairing of arteries and veins, the larger diameter of veins and the smaller diameter of arteries, the whiter color of arteries and the redder color of veins.

[0038] In one embodiment of this application, the retinal blood vessels are eroded to obtain the retinal blood vessel centerline, which includes the arterial blood vessel centerline and the venous blood vessel centerline.

[0039] Step S102: Determine the pre-crossing points of each fundus blood vessel.

[0040] Preferably, the pre-crossing points of retinal blood vessels are determined based on the eight-neighborhood algorithm.

[0041] Step S103: Remove the two-dimensional intersections of arterial and venous vessels in the pre-intersection points to obtain the fundus vessel intersections.

[0042] like Figure 2 As shown, by removing the intersections of arteries and veins such as I1 and I2 from the pre-intersection points, the intersection points of fundus vessels are obtained, reducing interference in the calculation results and improving the accuracy of the fundus vessel intersection points, thereby improving the accuracy of the calculated vessel angle.

[0043] In one embodiment of this application, the intersection of fundus vessels includes the intersection of two fundus vessels, such as the intersection of the main fundus vessel and a branch of the main fundus vessel, or the intersection of a secondary fundus vessel and a branch of the secondary fundus vessel.

[0044] Step S104: For each intersection of fundus vessels, determine the angle of the vessels corresponding to the fundus vessel intersection based on the fundus vessel intersection and the corresponding fundus vessels.

[0045] In one embodiment of this application, the fundus blood vessel corresponding to the intersection of fundus blood vessels is the two fundus blood vessels that intersect at the intersection of fundus blood vessels.

[0046] In one embodiment of this application, the angle between the two retinal blood vessels at the intersection of the retinal blood vessels is the angle between the two retinal blood vessels at the intersection of the retinal blood vessels.

[0047] Step S105: Determine the vascular angles of the target fundus image based on the vascular angles corresponding to the intersections of the fundus vessels contained in the target fundus image.

[0048] In one embodiment of this application, the target fundus image includes multiple fundus blood vessel intersections. The average value of the blood vessel angles corresponding to each of the multiple fundus blood vessel intersections is calculated, and the average value is the blood vessel angle of the target fundus image to reflect the morphological characteristics of blood vessels in the target fundus image.

[0049] The image processing method provided in this application embodiment can automatically calculate the vascular angle of the target fundus image. The calculation result is objective, which improves the accuracy and efficiency of the vascular angle calculation result.

[0050] Figure 3 The diagram shown is a schematic flowchart illustrating an exemplary embodiment of this application, illustrating the process of determining the angle between retinal blood vessel intersections based on the intersections and the corresponding retinal blood vessels. In this application... Figure 1 This application extends from the embodiments shown. Figure 3 The illustrated embodiment will be described in detail below. Figure 3 The illustrated embodiments and Figure 1 The differences between the embodiments shown are not repeated here, and the similarities are not repeated here.

[0051] like Figure 3 As shown, in the image processing method provided in this application embodiment, the step of determining the angle of the retinal blood vessel intersection based on the retinal blood vessel intersection and the corresponding retinal blood vessel includes the following steps.

[0052] Step S301: Based on the intersection of fundus blood vessels and the corresponding fundus blood vessels, determine the fitting line of the fundus blood vessels corresponding to the intersection of fundus blood vessels.

[0053] In one embodiment of this application, a fitting operation is performed on the two retinal blood vessels based on the intersection point of the two retinal blood vessels to obtain the fitting line of the two retinal blood vessels.

[0054] Step S302: Based on the fitted line of the fundus blood vessels corresponding to the intersection of fundus blood vessels, determine the angle of the blood vessels corresponding to the intersection of fundus blood vessels.

[0055] In one embodiment of this application, the angle between the fitted lines of the two fundus vessels is calculated to obtain the angle between the two fundus vessels corresponding to the intersection point of the fundus vessels.

[0056] The image processing method provided in this application provides a calculation basis for determining the vascular angle by determining the fitting line of the retinal blood vessels, and also improves the accuracy of the vascular angle calculation results.

[0057] Figure 4 The image shown is a schematic diagram of a target fundus image provided in an exemplary embodiment of this application. Figure 3 This application extends from the embodiments shown. Figure 4 The illustrated embodiment will be described in detail below. Figure 4 The illustrated embodiments and Figure 3 The differences between the embodiments shown are not repeated here, and the similarities are not repeated here.

[0058] In the image processing method provided in this application embodiment, the step of determining the fitting line of the fundus blood vessels corresponding to the fundus blood vessel intersection point based on the fundus blood vessel intersection point and the fundus blood vessels corresponding to the fundus blood vessel intersection point includes the following steps.

[0059] Step S401: Based on the intersection of fundus blood vessels, perform a straight line fitting operation on the fundus blood vessels corresponding to the intersection of fundus blood vessels to obtain the fitting line of the fundus blood vessels corresponding to the intersection of fundus blood vessels.

[0060] like Figure 4 As shown, at the intersection point O1 of the fundus vessels, based on a preset step size, a straight line fitting operation is performed on the fundus vessels intersecting at intersection point O1 to obtain the fitting lines L1 and L1' corresponding to the fundus vessels intersecting at intersection point O1. Further, the angle α between the fitting lines L1 and L1' is the vessel angle of the fundus vessels intersecting at intersection point O1. This embodiment does not elaborate on the fitting lines for fundus vessels corresponding to other fundus vessel intersection points.

[0061] It should be noted that the fundus vessel intersections mentioned in step S401 may include all fundus vessel intersections contained in the target fundus image.

[0062] The image processing method provided in this application embodiment obtains the fitting line of fundus blood vessels through a relatively simple straight line fitting operation, saving the workload of the fitting operation.

[0063] Figure 5 The image shown is a schematic diagram of a target fundus image provided in an exemplary embodiment of this application. Figure 3 This application extends from the embodiments shown. Figure 5 The illustrated embodiment will be described in detail below. Figure 5 The illustrated embodiments and Figure 3 The differences between the embodiments shown are not repeated here, and the similarities are not repeated here.

[0064] In the image processing method provided in this application embodiment, the step of determining the fitting line of the fundus blood vessels corresponding to the fundus blood vessel intersection point based on the fundus blood vessel intersection point and the fundus blood vessels corresponding to the fundus blood vessel intersection point includes the following steps.

[0065] Step S501: Based on the intersection of fundus blood vessels, perform tangent fitting operation on the fundus blood vessels corresponding to the intersection of fundus blood vessels to obtain the fitting line of the fundus blood vessels corresponding to the intersection of fundus blood vessels.

[0066] like Figure 5 As shown, at the intersection point O2 of the fundus vessels, a tangent fitting operation is performed on the fundus vessels intersecting at intersection point O2 to obtain the fitting lines L2 and L2' corresponding to the fundus vessels intersecting at intersection point O2. Further, the angle b between the fitting lines L2 and L2' is the vessel angle of the fundus vessels intersecting at intersection point O2. This application embodiment does not elaborate on the fitting lines for fundus vessels corresponding to other fundus vessel intersection points.

[0067] It should be noted that the fundus vessel intersections mentioned in step S501 may include all fundus vessel intersections contained in the target fundus image.

[0068] The image processing method provided in this application provides another fitting operation method, which obtains the fitting line of the fundus blood vessels.

[0069] Figure 6 The image shown is a schematic diagram of a target fundus image provided in an exemplary embodiment of this application. Figure 3 This application extends from the embodiments shown. Figure 6 The illustrated embodiment will be described in detail below. Figure 6 The illustrated embodiments and Figure 3 The differences between the embodiments shown are not repeated here, and the similarities are not repeated here.

[0070] In the image processing method provided in this application embodiment, the step of determining the fitting line of the fundus blood vessels corresponding to the fundus blood vessel intersection point based on the fundus blood vessel intersection point and the fundus blood vessels corresponding to the fundus blood vessel intersection point includes the following steps.

[0071] Step S601: Based on the intersection of the main vessels and the aorta and main vein, determine the fitting lines of the aorta and main vein corresponding to the intersection of the main vessels.

[0072] Specifically, the main blood vessels in the fundus include the aorta and the main vein, and the intersections of these vessels include the corresponding intersections of the aorta and the main vein. These intersections are the three-dimensional points where the aorta and the main vein intersect. The fundus vascular intersections also include aortic intersections and main venous intersections. An aortic intersection is the point where the aorta intersects with its bifurcation; this intersection must be located on the aorta. Similarly, a main venous intersection is the point where the aorta intersects with its bifurcation; this intersection must be located on the main vein.

[0073] like Figure 6 As shown, at the intersection point O1 of the main retinal vessels, a straight line fitting operation is performed on the retinal vessels intersecting at intersection point O1 to obtain fitting lines L1 and L1' corresponding to the retinal vessels intersecting at intersection point O1. Further, the angle α between fitting lines L1 and L1' is the vascular angle of the retinal vessels intersecting at intersection point O1. Similarly, at the intersection point O3 of the main retinal vessels, a straight line fitting operation is performed on the retinal vessels intersecting at intersection point O3 to obtain fitting lines L3 and L3' corresponding to the retinal vessels intersecting at intersection point O3. Further, the angle c between fitting lines L3 and L3' is the vascular angle of the retinal vessels intersecting at intersection point O3. The average value of angles α and c is the vascular angle of the retinal vessels intersecting at the main retinal vessels. This application embodiment does not elaborate on the fitting lines for retinal vessels corresponding to other intersection points of the main retinal vessels.

[0074] It should be noted that the intersection of retinal blood vessels also includes the intersection of secondary blood vessels (including the intersection of secondary arteries and secondary veins). In summary, the retinal blood vessel angles within any region of the target retinal image can be calculated according to the needs of calculating the vascular angles.

[0075] The image processing method provided in this application determines the fitting line of the fundus blood vessels corresponding to the intersection of the main fundus blood vessels, thereby obtaining the angle between the main fundus blood vessels and the bifurcation vessels of the main fundus blood vessels, providing another reference indicator for reflecting the morphological characteristics of fundus blood vessels.

[0076] Figure 7a The diagram shown is a flowchart of an image processing method provided in another exemplary embodiment of this application. Figure 7b As shown Figure 7a A schematic diagram of the target fundus image corresponding to the illustrated process. In this application... Figure 1 This application extends from the embodiments shown. Figure 7a and Figure 7b The illustrated embodiment will be described in detail below. Figure 7a and Figure 7b The illustrated embodiments and Figure 1 The differences between the embodiments shown are not repeated here, and the similarities are not repeated here.

[0077] like Figure 7aAs shown, in the image processing method provided in this application embodiment, after determining each fundus blood vessel contained in the target fundus image based on the target fundus image, the following steps are also included.

[0078] Step S701: Based on the diameter of the retinal blood vessels contained in the target retinal image, determine the main retinal blood vessels contained in the target retinal image.

[0079] In one embodiment of this application, the blood vessel with the largest diameter passing through the center point of the optic disc in the target fundus image is identified as the main fundus vessel; or, the blood vessel with the largest diameter passing through the center point of the optic disc in the target fundus image and satisfying preset color characteristics is identified as the main fundus vessel. The main fundus vessels include the aorta and the main vein.

[0080] Step S702: Using the center point of the viewing disk as the center, generate a first arc line based on a first preset radius.

[0081] In one embodiment of this application, the first preset radius is greater than the radius of the viewing disc.

[0082] Step S703: Determine the intersection of the first arc line and the main blood vessel in the fundus.

[0083] Step S704: Based on the intersection of the optic disc center point, the first arc line and the fundus main blood vessel, perform curve fitting operation on the fundus main blood vessel to obtain the main vascular arch corresponding to the fundus main blood vessel, and determine the included angle corresponding to the main vascular arch based on the fundus main blood vessel.

[0084] Step S705: Determine the vascular angle of the target fundus image based on the angle corresponding to the main vascular arch.

[0085] It should be noted that because the main blood vessels in the fundus are approximately arch-shaped, they are called the main vascular arch, which includes the aortic arch and the main venous arch. Furthermore, the main vascular arch and the secondary vascular arches form an "X"-like shape. Alternatively, the aortic arch and the main venous arch can be fitted separately using the methods described above, and then the main vascular arch can be calculated by combining the results of the aortic arch and the main venous arch.

[0086] In one embodiment of this application, the main retinal vessels include the aorta and the main vein, and the intersection of the retinal vessels includes the intersection of the aorta and the main vein corresponding to the main vessels. Based on the intersection of the optic disc center point, the first arc line, and the main retinal vessels, a curve fitting operation is performed on the main retinal vessels to obtain the main vascular arch corresponding to the main retinal vessels. This includes: based on the intersection of the optic disc center point, the first arc line, and the aorta, performing a curve fitting operation on the aorta to obtain the aortic vascular arch corresponding to the aorta; and based on the intersection of the optic disc center point, the first arc line, and the main vein, performing a curve fitting operation on the main vein to obtain the main venous vascular arch corresponding to the main vein.

[0087] like Figure 7b As shown, with the optic disc center point O as the center, a first arc C1 is generated based on a first preset radius. The first arc C1 intersects the main vein at intersection points O4 and O4'. Based on the optic disc center point O, intersection points O4 and O4', a curve fitting operation is performed on the main vein to obtain the corresponding main vein arch G1. Additionally, the first arc C1 intersects the aorta at intersection points O10 and O10'. Based on the optic disc center point O, intersection points O10 and O10', a curve fitting operation is performed on the aorta to obtain the corresponding aorta arch G2. This embodiment does not limit the curve fitting formula, as long as the obtained main arch G approximates the morphology of the fundus main vessels.

[0088] In one embodiment of this application, the main vascular arch corresponding to the main retinal vessels can also be obtained with the intersection of the aorta and the main vein as the center. Because other operational steps are similar to... Figure 7a and Figure 7b The embodiments shown are similar and will not be described again here.

[0089] It should be noted that, based on the actual structure of the fundus, the vascular arch should ideally be fitted using the intersection of the aorta and the main vein. However, in actual fundus images, it may be impossible to accurately locate the intersection of the aorta and the main vein. Furthermore, because the optic disc region is relatively bright, the center point of the optic disc is relatively easy to determine. Therefore, the vascular arch is usually fitted using the center point of the optic disc. Understandably, fitting the vascular arch using the intersection of the aorta and the main vein yields a more accurate result, while fitting it using the center point of the optic disc is more convenient.

[0090] In other embodiments, the main vascular arch corresponding to the main retinal vessels can also be obtained by the following method. Specifically, after performing step S701, the following steps are also included:

[0091] Step S706: Using the center point of the viewing disk as the center, generate a third arc based on the third preset radius.

[0092] In one embodiment of this application, the third preset radius is greater than the viewing disk radius.

[0093] Step S707: Determine the intersection points of the third arc with the aorta and the main vein, respectively.

[0094] Step S708: Based on the center point of the optic disc, the intersection of the third arc line and the aortic vessel, and the intersection of the third arc line and the main vein, a curve fitting operation is performed on the fundus main vessels to obtain the main vascular arch corresponding to the fundus main vessels.

[0095] Figure 7cThe image shown is a schematic diagram of a target fundus image provided in an exemplary embodiment of this application. Figure 7c As shown, with the optic disc center point O as the center, a third arc C4 is generated based on a third preset radius. The third arc C4 intersects the aortic vessel D at intersection points O7 and O7', and the third arc C4 intersects the main vein vessel J at intersection points O8 and O8'. Then, the first midpoint O9 of intersection points O7 and O8, and the second midpoint O9' of intersection points O7' and O8' are determined. Then, based on the optic disc center point O, the first midpoint O9, and the second midpoint O9', a curve fitting operation is performed on the fundus main vessels to obtain the main vascular arch G corresponding to the fundus main vessels. This application embodiment does not limit the curve fitting formula, as long as the obtained main vascular arch G approximates the shape of the fundus main vessels.

[0096] One approach is to connect intersection points O7 and O8 with a straight line, and determine the midpoint of the line segment formed by intersection points O7 and O8 as the first intermediate point O9. Similarly, one approach is to connect intersection points O7' and O8' with a straight line, and determine the midpoint of the line segment formed by intersection points O7' and O8' as the second intermediate point O9'.

[0097] Figure 8a The diagram shown is a schematic flowchart of an exemplary embodiment of this application, which describes the process of determining the angle of a retinal blood vessel intersection based on the intersection of retinal blood vessels and the corresponding retinal blood vessels. Figure 8b As shown Figure 8a The diagram shows the target fundus image corresponding to the process shown.

[0098] In the image processing method provided in this application embodiment, the fundus vascular intersection includes the main vascular arch and the bifurcation vessel of the main vascular arch corresponding to the main vascular arch intersection. The step of determining the vascular angle corresponding to the fundus vascular intersection based on the fundus vascular intersection and the fundus vascular corresponding to the fundus vascular intersection includes the following steps.

[0099] Step S801: Based on the intersection of the main vascular arches and the corresponding fundus vessels, determine the fitting line of the fundus vessels corresponding to the intersection of the main vascular arches.

[0100] Step S802: Based on the fitted line of the fundus vessels corresponding to the intersection of the main vascular arches, determine the vascular angle corresponding to the intersection of the main vascular arches.

[0101] Step S803: Determine the vascular angle of the target fundus image based on the vascular angle corresponding to the intersection of the main vascular arches.

[0102] Specifically, the intersection of the main vascular arches refers to the point where the main vascular arch intersects with its bifurcation vessels. Fundus vascular intersections include the intersection of the main vascular arches, specifically the intersection of the aortic arch and the aortic arch. The intersection of the main vascular arches is always located on the main vascular arch. The intersection of the aortic arches is always located on the aortic arch. The intersection of the aortic arches is always located on the aortic arch. The intersection of the aortic arches is always located on the aortic arch.

[0103] like Figure 8b As shown, at the intersection point O5 of the main vascular arches, a straight line fitting operation is performed on the main vascular arch G intersecting at intersection point O5 to obtain the fitting line L4 of the main vascular arch G. Then, a straight line fitting operation is performed on the bifurcation vessels of the fundus main vessels intersecting at intersection point O5 to obtain the fitting line L4'. Further, the angle d between the fitting lines L4 and L4' is the vessel angle between the main vascular arch G intersecting at intersection point O5 and the bifurcation vessels of the main vascular arch G. This embodiment of the application does not elaborate on the fitting lines of fundus vessels corresponding to other main vascular arch intersection points.

[0104] It should be noted that the intersections of fundus vessels also include the intersections of secondary vascular arches (including the intersections of secondary arterial arches and secondary venous arches; the calculation method for secondary vascular arches is the same as that for primary vascular arches, but the opening directions of secondary vascular arches are opposite to those of primary vascular arches. The opening direction of primary vascular arches is consistent with the direction of the macula's center, while the opening direction of secondary vascular arches is away from the macula's center). In summary, the vascular angles of fundus vessels in any region of the target fundus image can be calculated according to the needs of calculating vascular angles. Furthermore, this application does not specifically limit the calculation method for vascular angles of fundus vessels; combinations of other calculation methods can be used in addition to those mentioned in the embodiments. For example, the vascular angles obtained from the above embodiments can be weighted and summed or averaged to improve the accuracy of the calculated vascular angles.

[0105] The image processing method provided in this application determines the fitting line of the fundus vessels corresponding to the intersection of the fundus main vascular arches, thereby obtaining the vascular angle between the fundus main vascular arches and the bifurcation vessels of the fundus main vessels, providing another reference indicator for reflecting the morphological characteristics of fundus vessels. Furthermore, the main vascular arches fit the trend of the fundus main vessels, more closely resembling their shape, thus improving the accuracy of calculating the vascular angle.

[0106] Figure 9a The diagram shown is a schematic flowchart of an exemplary embodiment of this application, which describes the process of determining the angle of a retinal blood vessel intersection based on the intersection of retinal blood vessels and the corresponding retinal blood vessels. Figure 9b As shown Figure 9a A schematic diagram of the target fundus image corresponding to the illustrated process. In this application... Figure 3 This application extends from the embodiments shown. Figure 9a and Figure 9b The illustrated embodiment will be described in detail below. Figure 9a and Figure 9b The illustrated embodiments and Figure 3 The differences between the embodiments shown are not repeated here, and the similarities are not repeated here.

[0107] like Figure 9a As shown, in the image processing method provided in this application embodiment, the step of determining the angle of the retinal blood vessel intersection based on the retinal blood vessel intersection and the corresponding retinal blood vessel includes the following steps.

[0108] Step S901: Using the center point of the viewing disk as the center, generate at least one second arc line based on the second preset radius.

[0109] Step S902: For each second arc, based on the intersection of the main blood vessel, the intersection of the second arc with the main venous arch, and the intersection of the main arc with the aortic arch, determine the included angle corresponding to the main venous arch and the included angle corresponding to the aortic arch, respectively.

[0110] Step S903: Determine the angle corresponding to the main vascular arch based on the angle between the aortic arch and the main venous arch.

[0111] Specifically, such as Figure 9b As shown, with the optic disc center point O as the center, second arcs C2 and C3 are generated based on a second preset radius. Taking the main vein arch G1 as an example, arc C2 intersects the main vein arch G1 at points O5 and O5'. The optic disc center point O and the intersection point O5 form a straight line L5, and the optic disc center point O and the intersection point O5' form a straight line L5'. Straight lines L5 and L5' are the fitting lines for the fundus vessels (main vein arch G1) corresponding to the main vein intersection points. Additionally, arc C3 intersects the main vein arch G1 at points O6 and O6'. The optic disc center point O and the intersection point O6 form a straight line L6, and the optic disc center point O and the intersection point O6' form a straight line L6'. Straight lines L6 and L6' are the fitting lines for the fundus vessels (main vein arch G1) corresponding to the main vein intersection points. Furthermore, the average of the angle f between fitted lines L5 and L5' and the angle e between fitted lines L6 and L6' is the vascular angle of the main venous arch G1. This application does not elaborate on the intersections of other arcs with the main venous arch G1.

[0112] Similarly, the vascular angle corresponding to the aortic arch G2 is obtained, and the arithmetic mean or weighted average of the vascular angles corresponding to the aortic arch G2 and the main venous arch G1 is calculated to obtain the vascular angle corresponding to the aortic arch.

[0113] The image processing method provided in this application offers another fitting operation method, thereby obtaining the vessel angle corresponding to the main vascular arch, providing another reference indicator for reflecting the morphological characteristics of fundus vessels. Furthermore, the main vascular arch fits the trend of the fundus main vessels, more closely resembling their shape, thus improving the accuracy of calculating the vessel angle.

[0114] In addition, the arithmetic mean or weighted mean of the vascular angles at the intersection points of the main vascular arch G and the vascular angles at the other multiple fundus vessels is the vascular angle of the target fundus image, which reflects the vascular morphological characteristics within the target fundus image.

[0115] Figure 10 The diagram shown is a flowchart illustrating an image processing method provided in another exemplary embodiment of this application. Figure 1 This application extends from the embodiments shown. Figure 10 The illustrated embodiment will be described in detail below. Figure 10 The illustrated embodiments and Figure 1 The differences between the embodiments shown are not repeated here, and the similarities are not repeated here.

[0116] like Figure 10 As shown, in the image processing method provided in this application embodiment, before the step of determining the fundus vessels and fundus vessel intersections contained in the target fundus image based on the target fundus image, the following steps are also included.

[0117] Step S1001: Perform preprocessing on the fundus image to be processed to obtain the target fundus image corresponding to the fundus image to be processed.

[0118] Specifically, preprocessing operations are performed on the fundus images to be processed, including denoising, normalization, and enhancement. Denoising mainly removes noise from the fundus images captured during the imaging process, reducing its interference with the retinal blood vessels. Normalization mainly unifies the differential exposure, color, and brightness of the fundus images to be processed, making the grayscale value range of different fundus images uniform, thereby improving the algorithm's generalization ability to massive images and making the technology commercialization possible. Enhancement mainly increases the difference between the features of interest and the background features, making the features of interest more prominent, facilitating threshold segmentation and feature extraction.

[0119] Figure 11 The diagram shown is a structural schematic of an image processing apparatus provided in an exemplary embodiment of this application. Figure 11 As shown, the image processing apparatus provided in this application embodiment includes:

[0120] The first determining module 101 is used to determine each fundus blood vessel contained in the target fundus image based on the target fundus image;

[0121] The second determining module 102 is used to determine the pre-crossing points of each fundus blood vessel;

[0122] The removal module 103 is used to remove the two-dimensional intersections of arteries and veins in the pre-intersection points to obtain the fundus vascular intersections;

[0123] The third determining module 104 is used to determine the angle of the retinal blood vessel intersection for each retinal blood vessel intersection based on the retinal blood vessel intersection and the retinal blood vessel corresponding to the retinal blood vessel intersection.

[0124] The fourth determining module 105 is used to determine the vascular angle of the target fundus image based on the vascular angles corresponding to the intersections of the fundus vessels contained in the target fundus image.

[0125] In one embodiment of this application, the third determining module 104 is further configured to determine the fitting line of the fundus blood vessel corresponding to the fundus blood vessel intersection point based on the fundus blood vessel intersection point and the fundus blood vessel corresponding to the fundus blood vessel intersection point; and to determine the blood vessel angle corresponding to the fundus blood vessel intersection point based on the fitting line of the fundus blood vessel corresponding to the fundus blood vessel intersection point.

[0126] In one embodiment of this application, the third determining module 104 is further configured to perform a straight line fitting operation or a tangent fitting operation on the fundus blood vessels corresponding to the fundus blood vessel intersection points based on the fundus blood vessel intersection points, so as to obtain the fitting line of the fundus blood vessels corresponding to the fundus blood vessel intersection points.

[0127] It should be understood that Figure 11 The operation and function of the first determining module 101, the second determining module 102, the removing module 103, the third determining module 104, and the fourth determining module 105 in the provided image processing device can be referred to the above. Figures 1 to 10 The image processing methods provided will not be elaborated upon here to avoid repetition.

[0128] Below, for reference Figure 12 This describes an electronic device according to embodiments of the present application. Figure 12 The diagram shown is a structural schematic of an electronic device provided in an exemplary embodiment of this application.

[0129] like Figure 12 As shown, the electronic device 20 includes one or more processors 201 and memory 202.

[0130] The processor 201 may be a central processing unit (CPU) or other form of processing unit with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 20 to perform desired functions.

[0131] The memory 202 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 201 may execute the program instructions to implement the image processing methods of the various embodiments of this application described above and / or other desired functions. The computer-readable storage medium may also store various contents such as target fundus images, fundus vessels, and fundus vessel intersections.

[0132] In one example, the electronic device 20 may also include an input device 203 and an output device 204, which are interconnected via a bus system and / or other forms of connection mechanism (not shown).

[0133] The input device 203 may include, for example, a keyboard, a mouse, etc.

[0134] The output device 204 can output various information to the outside, including target fundus images, fundus vessels, and fundus vessel intersections. The output device 504 may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, etc.

[0135] Of course, for the sake of simplicity, Figure 12 Only some of the components of the electronic device 20 relevant to this application are shown in this illustration; components such as buses, input / output interfaces, etc., are omitted. In addition, the electronic device 20 may include any other suitable components depending on the specific application.

[0136] In addition to the methods and apparatus described above, embodiments of this application may also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to perform the steps of the image processing methods according to various embodiments of this application as described above.

[0137] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this application. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0138] Furthermore, embodiments of this application may also be computer-readable storage media storing computer program instructions thereon, which, when executed by a processor, cause the processor to perform the steps in the image processing methods according to various embodiments of this application described above.

[0139] The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may, for example, include, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0140] The basic principles of this application have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this application are merely examples and not limitations, and should not be considered as essential features of each embodiment of this application. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the application to the necessity of employing the aforementioned specific details for implementation.

[0141] The block diagrams of devices, apparatuses, devices, and systems involved in this application are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0142] It should also be noted that in the apparatus, equipment, and methods of this application, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered as equivalent solutions of this application.

[0143] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of this application. Therefore, this application is not intended to be limited to the aspects shown herein, but rather to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0144] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this application to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. An image processing method, characterized by, include: Based on the target fundus image, identify each fundus blood vessel contained in the target fundus image; Determine the pre-crossing points of each of the aforementioned fundus vessels; Remove the two-dimensional intersections of arteries and veins from the pre-intersection points to obtain the fundus vascular intersections; For each of the fundus vessel intersections, the angle between the fundus vessels at the fundus vessel intersections is determined based on the fundus vessel intersection and the corresponding fundus vessel. Based on the vascular angles corresponding to the intersections of retinal vessels in the target fundus image, the vascular angles of the target fundus image are determined. After determining the retinal vessels contained in the target retinal image based on the target retinal image, the method further includes: Based on the diameter of the retinal vessels contained in the target retinal image, the main retinal vessels contained in the target retinal image are determined; A first arc is generated with the center point of the viewing disk as the center and based on a first preset radius; Determine the intersection point of the first arc line and the main blood vessel in the fundus; Based on the center point of the optic disc, the intersection of the first arc and the main retinal blood vessel, a curve fitting operation is performed on the main retinal blood vessel to obtain the main vascular arch corresponding to the main retinal blood vessel, and the included angle corresponding to the main vascular arch is determined based on the main vascular arch corresponding to the main retinal blood vessel. Determining the vascular angles of the target fundus image based on the vascular angles corresponding to the intersections of the fundus vessels contained in the target fundus image includes: determining the vascular angles of the target fundus image based on the angles corresponding to the main vascular arch.

2. The image processing method of claim 1, wherein, The step of determining the angle of the retinal vessels corresponding to the intersection of the retinal vessels and the corresponding retinal vessels includes: Based on the intersection of the fundus vessels and the fundus vessels corresponding to the intersection of the fundus vessels, a fitting line for the fundus vessels corresponding to the intersection of the fundus vessels is determined; Based on the fitted line of the fundus vessels corresponding to the intersection of the fundus vessels, the angle of the vessels corresponding to the intersection of the fundus vessels is determined.

3. The image processing method of claim 2, wherein, The step of determining the fitting line of the fundus blood vessel corresponding to the fundus blood vessel intersection point based on the fundus blood vessel intersection point and the fundus blood vessel corresponding to the fundus blood vessel intersection point includes: Based on the intersection of the fundus vessels, a straight line fitting operation or a tangent fitting operation is performed on the fundus vessels corresponding to the intersection to obtain the fitting line of the fundus vessels corresponding to the intersection.

4. The image processing method of claim 1, wherein, The fundus main blood vessels include the aorta and the main vein, and the fundus blood vessel intersections include the main blood vessel intersections corresponding to the aorta and the main vein; the step of performing curve fitting on the fundus main blood vessels based on the optic disc center point, the intersection of the first arc line and the fundus main blood vessels to obtain the main vascular arch corresponding to the fundus main blood vessels includes: Based on the center point of the optic disc, the intersection of the first arc and the aortic vessel, a curve fitting operation is performed on the aortic vessel to obtain the aortic vascular arch corresponding to the aortic vessel; based on the center point of the optic disc, the intersection of the first arc and the main vein, a curve fitting operation is performed on the main vein to obtain the main vein vascular arch corresponding to the main vein.

5. The image processing method of claim 4, wherein, The step of determining the angle of the retinal vessels corresponding to the intersection of the retinal vessels and the corresponding retinal vessels includes: With the center point of the viewing disk as the center, at least one second arc is generated based on the second preset radius; For each of the second arc lines, based on the intersection of the main blood vessel, the intersection of the second arc line with the main venous arch, and the intersection of the aortic arch, the included angle corresponding to the main venous arch and the included angle corresponding to the aortic arch are determined respectively. Based on the included angle of the aortic arch and the included angle of the main venous arch, the included angle corresponding to the main blood vessel arch is determined.

6. The image processing method of claim 1, wherein, The fundus vascular intersections include the intersections of the main vascular arch and the bifurcation vessels of the main vascular arch. Determining the vascular angle corresponding to the fundus vascular intersection based on the fundus vascular intersections and the corresponding fundus vessels includes: Based on the intersection of the main vascular arches and the corresponding fundus vessels, a fitting line for the fundus vessels corresponding to the intersection of the main vascular arches is determined; based on the fitting line for the fundus vessels corresponding to the intersection of the main vascular arches, the vessel angle corresponding to the intersection of the main vascular arches is determined; based on the vessel angles corresponding to the fundus vessel intersections included in the target fundus image, the vessel angle of the target fundus image is determined, including: determining the vessel angle of the target fundus image based on the vessel angle corresponding to the intersection of the main vascular arches.

7. An image processing apparatus characterized by comprising: include: The first determining module is used to determine each retinal blood vessel contained in the target retinal image based on the target retinal image; The second determining module is used to determine the pre-crossing points of each of the fundus vessels; The removal module is used to remove the two-dimensional intersections of arteries and veins in the pre-intersection points to obtain the fundus vascular intersections; The third determining module is used to determine the angle of the retinal blood vessel intersection corresponding to each retinal blood vessel intersection based on the retinal blood vessel intersection and the retinal blood vessel corresponding to the retinal blood vessel intersection. The fourth determining module is used to determine the vascular angle of the target fundus image based on the vascular angle corresponding to each intersection of the fundus vessels contained in the target fundus image; After determining the retinal vessels contained in the target retinal image based on the target retinal image, the method further includes: Based on the diameter of the retinal vessels contained in the target retinal image, the main retinal vessels contained in the target retinal image are determined; A first arc is generated with the center point of the viewing disk as the center and based on a first preset radius; Determine the intersection point of the first arc line and the main blood vessel in the fundus; Based on the center point of the optic disc, the intersection of the first arc and the main retinal blood vessel, a curve fitting operation is performed on the main retinal blood vessel to obtain the main vascular arch corresponding to the main retinal blood vessel, and the included angle corresponding to the main vascular arch is determined based on the main vascular arch corresponding to the main retinal blood vessel. Determining the vascular angles of the target fundus image based on the vascular angles corresponding to the intersections of the fundus vessels contained in the target fundus image includes: determining the vascular angles of the target fundus image based on the angles corresponding to the main vascular arch.

8. A computer-readable storage medium, characterized in that, The storage medium stores a computer program for executing the image processing method according to any one of claims 1 to 6.

9. An electronic device, characterized in that, The electronic device includes: processor; Memory used to store the processor's executable instructions; The processor is configured to execute the image processing method according to any one of claims 1 to 6.

Images