Method for predicting diabetic retinopathy based on choroid-retina feature ratio

Abstract

The application belongs to the field of intelligent medical treatment, and particularly relates to a prediction method for diabetic retinopathy based on choroid-retina feature ratio. The method comprises the following steps: obtaining an eye OCTA image of a diabetic patient; extracting choroid features and retina features based on the OCTA image, and calculating a choroid-retina feature ratio based on the ratio of the choroid features and the retina features; and inputting the choroid-retina feature ratio into a classifier to obtain the result of whether the diabetic patient has retinopathy. The application proposes and verifies the hypothesis that the retina may have a corresponding retina blood supply system reserve (RBSSR), and extracts the choroid-retina feature ratio which has important prediction performance for monitoring diabetic retinopathy based on the hypothesis, thereby achieving the effect of timely and accurate prediction of diabetic retinopathy.

Description

Technical Field

[0001] This invention relates to the field of intelligent healthcare, and more specifically, to a method, device, medium, and program product for predicting diabetic retinopathy based on choroid-retinal characteristic ratio. Background Technology

[0002] Diabetic retinopathy (DR) is one of the most common and serious microvascular complications of diabetes mellitus (DM), and has become a leading cause of blindness among the working-age population worldwide. However, the pathogenesis of DR remains unclear. Although the duration of diabetes and glycemic control are widely considered key risk factors for DR, clinical observations have revealed that some patients with good glycemic control and shorter duration of diabetes still develop DR, while others with poor glycemic control and longer duration of diabetes do not develop DR. This difference indicates that individual variations play an important role in the occurrence and development of DR.

[0003] The retina is one of the tissues in the human body with the highest oxygen consumption. In diabetic patients, impaired microcirculation leads to retinal ischemia and hypoxia, which can cause neurodegeneration, retinal dysfunction, and even vision loss. Cerebrovascular reserve refers to the ability of cerebrovascular neurovascular units to dynamically regulate blood pressure, intracranial pressure fluctuations, and increased metabolic demands. This adaptive capacity is often used as a key indicator for assessing the occurrence and progression of cerebrovascular diseases, including diabetes.

[0004] In existing technologies, the study "Assessment of choroidal structural changes in patients with pre- and early-stage clinical diabetic retinopathy using wide-field SS-OCTA" discloses the use of SS-OCTA to study microvascular changes in the choroidal structure of patients in the pre- and early stages of clinical diabetic retinopathy (DR). By recording and analyzing the choroidal vascular distribution index (CVI), choroidal thickness (ChT), and central macular thickness (CMT) across the entire region (12 mm in diameter), and concentric rings at different ranges (0-3, 3-6, 6-9, and 9-12 mm), it was found that the CVI and ChT values ​​in diabetic patients were significantly lower than those in healthy controls, especially in early-stage DR patients. Furthermore, peripheral choroidal capillaries were more susceptible to damage induced by early diabetic retinopathy than those in the central region. However, the existing technologies do not disclose the role of the retinal vascular supply system, composed of the retinal circulation (RC) and choroidal circulation (CC), in DR. Summary of the Invention

[0005] In view of the above problems, the present invention provides a method for predicting diabetic retinopathy based on the choroid-retinal characteristic ratio, which uses the relative changes in the volume of the choroid and retina to predict diabetic retinopathy.

[0006] This application (first aspect) discloses a method for predicting diabetic retinopathy based on choroid-retinal characteristic ratio, comprising:

[0007] Obtain OCTA images of the eyes of diabetic patients;

[0008] Based on the OCTA image, choroidal and retinal features are extracted, and the ratio of choroidal to retinal features is calculated based on the ratio of the choroidal and retinal features.

[0009] The choroidal and retinal feature ratio is input into the classifier to obtain the result of whether diabetic patients have developed retinopathy.

[0010] Furthermore, the choroid-to-retinal feature ratio includes any one or more of the following:

[0011] The ratio of total choroidal volume to total retinal volume, and the ratio of choroidal vessel volume to total retinal volume.

[0012] The ratio of the total volume of the choroid to the volume of the outer retina, and the ratio of the volume of the choroidal vessels to the volume of the outer retina.

[0013] Furthermore, based on the central region where the fovea of ​​the OCTA image is located, the choroidal and retinal features of the central region are extracted, and the ratio of choroidal to retinal features is calculated based on the ratio of the choroidal and retinal features of the central region.

[0014] Furthermore, the choroidal feature refers to the total volume of the choroid, the retinal feature refers to the total volume of the retina, and the ratio of the choroidal to retinal features is the ratio of the total volume of the choroid to the total volume of the retina;

[0015] Furthermore, the ratio of the total volume of the choroid to the total volume of the retina is the ratio of the total volume of the choroid to the total volume of the retina in the central region;

[0016] Furthermore, the choroidal feature refers to the total volume of the choroid, the retinal feature refers to the total volume of the retina, and the ratio of the choroidal to retinal features is the ratio of the total volume of the choroid to the total volume of the retina;

[0017] Furthermore, the ratio of the total volume of the choroid to the total volume of the retina is the ratio of the total volume of the choroid to the total volume of the retina in the central region;

[0018] The ratio of the total choroidal volume to the total retinal volume in the central region is input into the classifier to obtain the result of whether diabetic patients have developed retinopathy.

[0019] Furthermore, the choroidal feature is the choroidal thickness, the retinal feature is the retinal layer thickness, and the ratio of the choroidal to the retinal feature is the ratio of the choroidal thickness to the retinal layer thickness.

[0020] Furthermore, the choroid-to-retinal feature ratio is the ratio of the choroidal thickness to the retinal layer thickness in the central region;

[0021] The ratio of choroidal thickness to retinal thickness in the central region is input into the classifier to obtain the result of whether diabetic patients have developed retinopathy.

[0022] Furthermore, the choroidal feature is the choroidal thickness, the retinal feature is the outer retinal layer thickness, and the ratio of the choroidal to the retinal feature is the ratio of the choroidal thickness to the outer retinal layer thickness.

[0023] Furthermore, the ratio of the total volume of the choroid to the total volume of the retina is the ratio of the thickness of the choroid in the central region to the thickness of the outer layer of the retina;

[0024] The ratio of the choroidal thickness in the central region to the outer retinal layer thickness is input into the classifier to obtain the result of whether diabetic patients have developed retinopathy.

[0025] Furthermore, the choroidal feature refers to the total volume of the choroid, the retinal feature refers to the volume of the outer retinal layer, and the ratio of the choroidal feature to the retinal feature is the ratio of the total volume of the choroid to the volume of the outer retinal layer.

[0026] Furthermore, the ratio of the total volume of the choroid to the volume of the outer retina is the ratio of the total volume of the choroid to the volume of the outer retina in the central region;

[0027] The ratio of the total choroidal volume in the central region to the outer retinal volume is input into the classifier to obtain the result of whether diabetic patients have developed retinopathy.

[0028] Furthermore, the choroidal feature is the choroidal vessel volume, the retinal feature is the total retinal volume, and the ratio of choroidal to retinal features is the ratio of choroidal vessel volume to total retinal volume;

[0029] Furthermore, the ratio of the choroidal vessel volume to the total retinal volume is the ratio of the total choroidal volume to the total retinal volume in the central region;

[0030] The ratio of choroidal vessel volume in the central region to the total retinal volume is input into the classifier to obtain the result of whether diabetic patients have developed retinopathy.

[0031] Furthermore, the choroidal feature is the volume of choroidal vessels, the retinal feature is the volume of the outer retinal layer, and the ratio of choroidal to retinal features is the ratio of the volume of choroidal vessels to the volume of the outer retinal layer.

[0032] Furthermore, the ratio of the total volume of the choroid to the total volume of the retina is the ratio of the total volume of the choroid to the total volume of the retina in the central region; the ratio of the choroidal vessel volume in the central region to the outer layer volume of the retina is input into the classifier to obtain the result of whether the diabetic patient has developed retinopathy.

[0033] Furthermore, the total volume of the choroid is the volume between the central region RPE / BM and the choroid-scleral interface.

[0034] The choroidal vessel volume refers to the volume of the large and medium-sized vessels within the central region of the choroid.

[0035] The total retinal volume is the volume between the central region's inner limiting membrane and the RPE / BM.

[0036] The volume of the outer retinal layer is the volume between the outer plexiform layer in the central region and the RPE / BM.

[0037] Furthermore, the OCTA image is divided into a central region containing the fovea and a peripheral region outside the fovea. Choroidal and retinal features are extracted from the central region and the peripheral region, respectively. The ratio of choroidal to retinal features is calculated based on the ratio of choroidal to retinal features in the central region, and the ratio of choroidal to retinal features in the peripheral region is calculated based on the ratio of choroidal to retinal features in the peripheral region.

[0038] Furthermore, the choroid-to-retinal feature ratio also includes any one or more of the following:

[0039] The ratio of the total volume of the choroid to the total volume of the retina in the peripheral region, and the ratio of the volume of the choroidal vessels to the total volume of the retina in the peripheral region.

[0040] The ratio of the total volume of the choroid in the peripheral region to the volume of the outer retina, and the ratio of the volume of the choroidal vessels in the peripheral region to the volume of the outer retina.

[0041] Furthermore, the eye OCTA image is obtained by performing OCTA imaging using a scanning mode centered on the fovea. The image is divided into a 3 × 3 grid, with the central grid designated as the central region and the surrounding grids considered as the peripheral region.

[0042] Furthermore, concentric circles with different radii are set around the center of the central concave area of ​​the image, with the area within a radius of 6mm as the central region and the area from 6mm to 12mm as the outer perimeter region.

[0043] Furthermore, the method for constructing the classifier is as follows:

[0044] Obtain OCTA images of the eyes of diabetic patients in the training set and their corresponding labels, the labels including no retinopathy and retinopathy;

[0045] Based on the OCTA images of the eye in the training set, choroidal and retinal features were extracted, and the ratio of choroidal to retinal features was calculated.

[0046] The classifier is obtained by iteratively training a machine learning model by inputting the choroid-retinal feature ratio and labels.

[0047] The second aspect of this application discloses a prediction system for diabetic retinopathy based on choroid-retinal characteristic ratios, comprising:

[0048] Acquisition module 201: Used to acquire OCTA images of the eyes of diabetic patients;

[0049] Feature extraction module 202: used to extract choroidal features and retinal features based on the image, and calculate the ratio of choroidal features to retinal features based on the ratio of the choroidal features to retinal features;

[0050] Prediction module 203: used to input the choroidal-retinal feature ratio into the classifier to obtain the result of whether diabetic patients have developed retinopathy.

[0051] A third aspect of this application discloses a computer device, the device comprising: a memory and a processor; the memory being used to store program instructions; the processor being used to invoke the program instructions, which, when executed, are used to perform the steps of the method described above.

[0052] The fourth aspect of this application discloses a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described above.

[0053] The fifth aspect of this application discloses a computer program product, including a computer program that, when executed by a processor, implements the steps of the above-described method.

[0054] This application has the following beneficial effects:

[0055] (1) This application proposes and verifies the hypothesis that the retina may have a corresponding retinal blood supply system reserve (RBSSR), and extracts the choroid-retinal feature ratio, which has important predictive performance for the detection of diabetic retinopathy, based on the hypothesis, thus achieving the predictive effect of diabetic retinopathy.

[0056] (2) The clinical index of choroid-to-retinal volume ratio proposed in this application has high predictive sensitivity for diabetic retinopathy and can detect the risk of retinopathy in diabetic patients in a timely manner. Attached Figure Description

[0057] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0058] Figure 1 This is a schematic diagram of the method flow provided in the first aspect of the present invention;

[0059] Figure 2 This is a schematic diagram of a program product provided in the second aspect of the present invention;

[0060] Figure 3 This is a schematic diagram of a computer device provided in an embodiment of the present invention;

[0061] Figure 4 This is a schematic diagram of the architecture of an exemplary computing device provided in an embodiment of the present invention;

[0062] Figure 5 This is a schematic diagram of the storage medium provided in an embodiment of the present invention;

[0063] Figure 6 This is a schematic diagram of OCTA image acquisition and analysis provided in an embodiment of the present invention, wherein a 12 × 12mm image is used. 2 The scanning mode captures OCTA fundus images centered on the macula, using built-in software for automatic layering and analysis: the retinal layer refers to the area from the internal limiting membrane (ILM) to the retinal pigment epithelium / Bruch membrane (RPE / BM); the outer retinal layer refers to the area from the outer plexus layer (OPL) to the RPE / BM; and the choroidal layer refers to the area from the RPE / BM to the choroid-scleral interface (CSI). (AB) The OCTA scan results for each retinal and choroidal layer are divided into 3 × 3 4 × 4 mm segments using the built-in software. 2A grid was constructed (the central 4×4mm grid was defined as the central region, and the remaining grids were defined as the peripheral region), and then the relevant retinal and choroidal volumes were measured. (CD) Schematic diagram of the B-scan pattern for the choroidal to retinal volume ratio: TCV / ORV, defined as the ratio of total choroidal volume to outer retinal volume; TCV / TRV, defined as the ratio of total choroidal volume to total retinal volume; LCV / ORV, defined as the ratio of choroidal vessel volume (LCV, yellow area) to outer retinal volume; LCV / TRV, defined as the ratio of LCV to total retinal volume.

[0064] Figure 7 This is a schematic diagram of atropine increasing the choroid-to-retina volume ratio in mice, provided by an embodiment of the present invention; (A) Figure shows a comparison of OCTA images before / after drug administration and after drug administration, and compares the ratio of choroid thickness between the control group and the experimental group; (B) Figure is a comparison of retinal volume, choroid volume, and choroid-to-retina volume ratio between the control group and the atropine experimental group.

[0065] Figure 8 This is a schematic diagram illustrating the correlation between a low choroid-to-retina volume ratio and diabetic retinopathy (DR) in diabetic mice, provided by an embodiment of the present invention. (A) is a schematic diagram of the animal modeling experimental procedure; (B) shows wide-angle color fundus images (CF), fundus autofluorescence images (AF), and OCTA 6 x 6 mm² scan images of diabetic mice, with the yellow arrow pointing towards the temporal side (n=7); (C) a representative image of HE staining of retinal tissue from diabetic mice (n=6); and (D) TUNEL staining of retinal tissue from diabetic mice to detect apoptosis (n=6). Data analysis was performed using paired t-tests, and results are expressed as mean ± SD. * p < 0.05, ** p < 0.01, *** p < 0.001. Detailed Implementation

[0066] To enable those skilled in the art to better understand the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings.

[0067] In some of the processes described in the specification, claims, and accompanying drawings of this invention, multiple operations appearing in a specific order are included. However, it should be clearly understood that these operations may not be executed in the order they appear herein, or may be executed in parallel. The operation numbers, such as S101, S102, etc., are merely used to distinguish different operations and do not represent any execution order. Furthermore, these processes may include more or fewer operations, and these operations may be executed sequentially or in parallel. It should be noted that the descriptions such as "first," "second," etc., in this document are used to distinguish different messages, devices, modules, etc., and do not represent a sequential order, nor do they limit "first" and "second" to different types.

[0068] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0069] Figure 1 This is a schematic flowchart of a method for predicting diabetic retinopathy based on the choroid-retinal characteristic ratio provided by an embodiment of the present invention. Specifically, the method includes the following steps:

[0070] S101: Acquire OCTA images of the eyes of diabetic patients;

[0071] S102: Extract choroidal and retinal features based on the OCTA image, and calculate the choroidal to retinal feature ratio based on the ratio of the choroidal and retinal features;

[0072] S103: The choroidal and retinal feature ratio is input into the classifier to obtain the result of whether the diabetic patient has developed retinopathy.

[0073] Given that the retina is part of the central nervous system, we have reason to hypothesize that the retina may also possess a corresponding retinal blood supply reserve (RBSSR), i.e., the ability of the retinal vascular supply system to meet increased metabolic demands. This reserve capacity may play a crucial role in the pathogenesis of diabetic retinopathy (DR).

[0074] In the human body, the retinal vascular supply system consists of the retinal circulation (RC) and the choroidal circulation (CC). The RC accounts for only a small portion of the retinal blood supply, while the CC accounts for approximately 85%, primarily supplying the outer five layers of the retina and the macula. Furthermore, the RC is characterized by low blood flow and a high oxygen uptake rate, resulting in a large arteriovenous oxygen saturation difference and an extremely sensitive response to hypoxia. In contrast, the CC has a large blood flow but a very low oxygen uptake rate, resulting in a small arteriovenous difference and a high oxygen transport reserve, indicating a strong tolerance to hypoxia. Given these characteristics, the CC is likely the main contributor to the RBSSR (Retinal Blood Supply System Routine).

[0075] Since the choroid is mainly composed of vascular tissue, its volume is theoretically positively correlated with the oxygen-carrying capacity of the choroid. As the tissue that consumes the most oxygen in the human body, the size of the retina directly affects its oxygen demand.

[0076] Based on the above theoretical analysis, the choroid-to-retinal volume ratio can theoretically serve as a relative indicator of RBSSR. Detailed examination of this ratio may help assess RBSSR and deepen our understanding of the underlying pathogenesis of DR. Combining the above theoretical insights and clinical observations, we hypothesize that individuals with relatively low RBSSR may be more prone to DR. Specifically, this hypothesis suggests that DR patients typically exhibit a low choroid-to-retinal volume ratio. To verify this hypothesis, we used ultra-wide field-of-view optical coherence tomography (OCTA) to analyze retinal and choroidal vascular images of DM patients and found that a low choroid-to-retinal volume ratio is a risk factor for DR.

[0077] Previous reports indicated that atropine could induce choroidal thickening in myopic patients or animals. Therefore, we established an animal model using atropine and further demonstrated that atropine treatment effectively reduced early-stage diabetic retinopathy, an effect associated with an increased choroid-to-retinal volume ratio.

[0078] The specific experimental research is described below.

[0079] I. Materials and Methods:

[0080] 1.1 Research Subjects

[0081] This was a cross-sectional study that included patients with type 2 diabetes mellitus (T2DM) recruited at the Department of Ophthalmology, The Third Affiliated Hospital of Southern Medical University, Guangzhou, China, between June 1, 2022, and June 1, 2024. Participants were divided into two groups according to the International Clinical Diabetic Retinopathy Severity Scale. The control group consisted of T2DM patients without significant retinopathy (disease duration ≥ 5 years) (NDR group, 79 patients / 134 eyes), and the DR group consisted of T2DM patients with non-proliferative DR (disease duration not limited) (89 patients / 125 eyes).

[0082] All participants underwent ophthalmological examinations, including best-corrected visual acuity (BCVA), intraocular pressure (IOP), slit-lamp fundus examination, fundus photography, axial length (AL), spherical equivalence (SE), OCT, and OCTA. Demographic data for all participants were collected, including age, sex, body mass index (BMI), fasting blood glucose (FBG) level, duration of diabetes, history of hypertension, and chronic kidney disease status.

[0083] The inclusion criteria for subjects are as follows: (1) age ≥ 18 years; (2) diagnosis of T2DM; (3) T2DM duration ≥ 5 years in the NDR group. Exclusion criteria include: (1) intraocular pressure below 21 mmHg; (2) blood pressure ≥ 160 / 100 mmHg; (3) accompanied by diabetic macular edema, epiretinal membrane or pathological myopia; (iv) history of other intraocular surgeries besides cataracts, including retinal photocoagulation; (5) poor OCTA image quality due to opacity of refractive media, with a signal score below 7 points (out of 10); (vi) other ocular diseases that may affect ocular circulation, such as glaucoma, age-related macular degeneration, retinal vascular diseases, etc.

[0084] 1.2 Laboratory Animals

[0085] Three-week-old male C57BL / 6J mice were purchased from Guangzhou Ruige Biotechnology Co., Ltd. Atropine eye drops at a concentration of 2% were administered to one eye twice daily, while the contralateral eye received saline eye drops as a control. Diabetes was induced for 5 consecutive days by intraperitoneal injection of streptozotocin (STZ) 55 mg / kg dissolved in sodium citrate buffer (pH 4.5). One week after induction, blood glucose levels were measured; a blood glucose level ≥16.7 mmol / L confirmed diabetes.

[0086] 1.3 OCTA Image Acquisition and Analysis

[0087] All OCTA images were taken using a BM-400K (BMizar, TowardPi Medical Technology Co., Ltd., Beijing, China) during the same time period (8:00 - 17:00) on the same day. For human subjects, a 12×12 mm foveal-centered MRI scanner was used. 2 OCTA imaging in scanning mode ( Figure 6 A). The resulting image was divided into 4 × 4 mm sections. 2 A 3 × 3 grid.

[0088] The central grid is designated as the central region, while the surrounding grid is considered the outer region. Figure 6 B).

[0089] 1.3.1 Volume Measurement

[0090] The volume of the retina and choroid is measured after automatic stratification using built-in software:

[0091] like Figure 6 As shown in D, the retinal layer refers to the layer from the internal limiting membrane (ILM, marked by the red line) to the retinal pigment epithelium / Bruch's membrane (RPE / BM); the total retinal volume (TRV) corresponds to... Figure 6 D represents the volume of the portion marked by the blue line segment; the total retinal volume includes the total volume of the inner layer (ILM to INL) and the outer layer (ONL to RPE / BM), i.e., the total volume from ILM to RPE / BM. The outer retina (or outer layer) refers to the area from the outer retinal layer (OPL) to RPE / BM; the outer retinal volume (ORV) corresponds to the volume of the portion marked by the red line segment in Figure 6D.

[0092] The outer retina (or outer layers) refers to the layer from the outer plexus (OPL) to the RPE / BM; the outer retinal volume (ORV) corresponds to... Figure 6 The volume of the portion marked by the red line segment in D;

[0093] The choroidal layer refers to the layer extending from the RPE / BM to the choroid-scleral interface (CSI). The total choroidal volume (TCV) corresponds to... Figure 6 The total volume of the area marked by the white line segment in D;

[0094] The choroid is a crucial component of the membranous structure of the eyeball wall, located between the outer retina and the sclera. It is primarily composed of a vascular layer, connective tissue, and melanocytes. The choroidal vascular system is the core anatomical structure of this layer, supplied by short posterior ciliary arteries, forming a unique layered distribution including: Haller's layer (large vessels), Sattler's layer (medium vessels), and the choroidal capillary layer. In this study, the volume of the large and medium choroidal vessels was measured as the choroidal vascular volume (LCV). Figure 6 The yellow area in D indicates the large and medium vessel layers of the choroid.

[0095] 1.3.2 Volume Calculation

[0096] Based on the above volume measurements, the following ratios are calculated:

[0097] TCV / ORV is defined as the ratio of total choroidal volume to outer retinal volume.

[0098] TCV / TRV is defined as the ratio of the total choroidal volume to the total retina volume.

[0099] LCV / ORV is defined as the ratio of choroidal vessel volume (LCV) to the outer retinal volume.

[0100] LCV / TRV is defined as the ratio of LCV to the total volume of the retina;

[0101] Treatment of laboratory mice: in OCTA 6x6 mm 2 In this mode, a mouse fundus image centered on the ONH (Optimal Ocular Hemorrhage) is displayed. The volumes of the retina and choroid are then automatically measured by built-in software. Mouse OCTA 6x6 mm. 2 Scan the image. Select a slice that passes horizontally through the center of the ONH to measure the choroid thickness. Figure 7 A).

[0102] 1.4 Statistical Analysis

[0103] Statistical analysis was performed using GraphPad Prism version 9.0.0. The Shapiro-Wilk test was used to assess the normality of the data distribution. Data were expressed as mean ± standard deviation (SD) or median (interquartile range, IQR), depending on the distribution. Categorical data were expressed as percentages. BCVA values ​​were converted to the logarithm of the minimum resolution angle (logMAR) for analysis. For comparisons of continuous data, independent samples t-tests, Welch's test, or Mann-Whitney U tests were used as appropriate. Chi-square tests or Fisher's exact tests were used for comparisons of categorical data. Univariate logistic regression analysis was used to assess correlation. Specifically, paired t-tests were used to analyze animal experimental data. All p-values ​​were two-tailed, and p < 0.05 was considered statistically significant.

[0104] 1.5 Fundus photography and autofluorescence images

[0105] After mouse anesthesia, wide-angle color fundus imaging and autofluorescence images centered on the ONH were obtained using Optos 200 Tx (Optos PLC, Dunfermline, United Kingdom).

[0106] 1.6 H&E staining and TUNEL test

[0107] Mice were euthanized, and their eyeballs were removed and fixed with FAS eye fixative (Servicebio) for 24 hours. 4 μm tissue sections were prepared. Subsequently, hematoxylin and eosin (H&E) staining was performed using an HE staining kit (Solarbio) according to the manufacturer's instructions.

[0108] 2. Experimental Results

[0109] 2.1 Demographic and clinical characteristics

[0110] This study included 134 eyes from 79 NDR patients and 125 eyes from 89 DR patients. There were no statistically significant differences between the two groups in terms of age, sex, duration of diabetes, fasting blood glucose (FBG), hypertension, BMI, BCVA, IOP, AL, and SE (P < 0.05). The NDR group had a lower incidence of chronic kidney disease compared to the DR group (P = 0.037). Table 1 provides a summary of baseline characteristics for each group (Table 1).

[0111] Table 1. Demographic and clinical characteristics of the subjects

[0112]

[0113] Notes: * indicates P<0.05; BMI = Body Mass Index; HTN = Hypertension; CKD = Chronic Kidney Disease; FBG = Fasting Blood Glucose; BCVA = Best Corrected Visual Acuity; IOP = Intraocular Pressure; SE = Spherical Equivalent; AL = Axial Length; logMAR = Logarithmic Visual Acuity of Minimum Resolution; SD = Standard Deviation; IQR = Interquartile Range.

[0114] 2.2 Choroid-retina volume ratio analysis

[0115] Compared with the NDR group, the DR group showed a significant reduction in retinal volume in both the central and peripheral regions (P < 0.001). The central LCV (1.601 ± 0.618 vs. 1.154 ± 0.674, P < 0.001) and peripheral LCV (9.600 ± 3.266 vs. 7.136 ± 3.203, P < 0.001) were significantly lower in the DR group than in the NDR group. There were no statistically significant differences in retinal outer layer volume or total retinal volume between the two groups in any region (P < 0.05). (Table 2)

[0116] Analysis of the TCV / ORV, TCV / TRV, LCV / ORV, and LCV / TRV ratios showed that these ratios were significantly lower in DR patients compared to the NDR group. This difference was consistent in both the central and peripheral regions, and all comparisons were statistically significant (P < 0.001, Table 2).

[0117] Table 2. Retinal and choroidal volumes and choroidal-to-retinal volume ratio

[0118]

[0119]

[0120] Notes: * indicates P < 0.05; Abbreviations and acronyms: LMCV (large and medium choroidal vessels): large and medium choroidal vessels; LCV (choroidal vascularity volume of LCMV): choroidal vascular volume of large and medium choroidal vessels; TCV / ORV = ratio of total choroidal volume to external retinal volume; TCV / TRV = ratio of total choroidal volume to total retinal volume; LCV / ORV = ratio of large and medium choroidal vascular volume to external retinal volume; LCV / TRV = ratio of large and medium choroidal vascular volume to total retinal volume; SD = standard deviation.

[0121] 2.3 Logistic Regression Analysis

[0122] Univariate logistic regression analysis showed that low choroid / retinal volume ratios, including TCV / ORV, TCV / TRV, LCV / ORV, and LCV / TRV, were significantly associated with DR. Notably, the LCV / TRV ratios in the central region (OR 0.0019, 95% CI 0.0001 ~ 0.0181, P < 0.001) and the LCV / TRV ratios in the peripheral region (OR 1.254×10⁻⁴, 95% CI 4.969×10⁻⁶ ~ 2.469×10⁻³, P < 0.001) were both strongly negatively correlated with DR (Table 3).

[0123] Table 3. Univariate Logistic Regression Analysis of the Correlation Between Choroid-Retina Volume Ratio and Diabetic Respiratory Disorder (DR)

[0124]

[0125] Note: * P<0.05; Abbreviations and acronyms: TCV / ORV = ratio of total choroidal volume to outer retinal volume; TCV / TRV = ratio of total choroidal volume to total retina volume; LCV / ORV = ratio of LCV to outer retina volume; LCV / TRV = ratio of LCV to total retina volume.

[0126] In some embodiments, the occurrence of DR is predicted based on the LCV / TRV ratio (OR 0.0019, 95% CI 0.0001 ~ 0.0181, P < 0.001). If the LCV / TRV ratio is higher than a threshold, DR is predicted to occur; otherwise, DR is predicted not to occur. The threshold is determined based on the above statistical analysis of the training set data.

[0127] In some embodiments, the occurrence of DR is predicted based on the LCV / TRV ratio of the surrounding area (OR 1.254×10-4, 95% CI 4.969×10-6 ~ 2.469×10-3, P < 0.001). If the LCV / TRV ratio is higher than a threshold, DR is predicted to occur; otherwise, DR is predicted not to occur. The threshold is determined based on the above statistical analysis of the training set data.

[0128] Based on the results of univariate logistic regression analysis, we established a predictive model for DR using the characteristics of significant differences between groups that we found:

[0129] Feature values ​​and corresponding labels (NDR label is 0, DR label is 1) were extracted from the NDR and DR groups in the study. A dataset was constructed, and the model was trained by randomly splitting the data into 70% as the training set and 30% as the test set. The performance of the model is shown in Table 4.

[0130] Table 4. Receiver Operating Characteristic (ROC) curve analysis of choroid-to-retinal volume ratio for differentiating between non-diabetic retinopathy (NDR) and diabetic retinopathy (DR).

[0131]

[0132] Note: * indicates P<0.05; Abbreviations and abbreviations: TCV / ORV = ratio of total choroidal volume to outer retinal volume; TCV / TRV = ratio of total choroidal volume to total retinal volume; LCV / ORV = ratio of LCV (local choroidal volume) to outer retinal volume; LCV / TRV = ratio of LCV to total retinal volume; AUC = area under the ROC curve.

[0133] 2.4 Atropine increases the choroid-to-retina volume ratio in mice.

[0134] To further validate the significance of the choroid-to-retina volume ratio in diabetic retinopathy (DR), we conducted animal experiments. Initially, we explored the feasibility of using atropine to increase the choroid-to-retina volume ratio in mice. OCT results showed that the choroid (temporal and nasal sides) of eyes treated with atropine was significantly thicker than that of control eyes. Figure 7 A). Meanwhile, OCTA results showed that we successfully established a mouse model with a significant difference in the choroid-to-retina volume ratio between the two eyes (A). Figure 7 B).

[0135] Three-week-old mice were given 2% atropine in one eye and saline in the other eye twice daily for 6 weeks (n = 11). (A) Mouse OCTA 6X6 mm 2 Scanning images. Data were collected before and after the instillation, and the changes in choroidal thickness at 2000 μm near the ONH were assessed using built-in software. The yellow arrows indicate the temporal side. (B) OCTA analysis of retinal and choroidal volume changes, and the choroidal-to-retinal volume ratio. Paired t-tests were used for data analysis, and results are expressed as mean ± SD. * p < 0.05, ** p < 0.01.

[0136] 2.5. Low choroid-to-retinal volume ratio is associated with diabetic retinopathy (DR) in diabetic mice.

[0137] We induced diabetes by intraperitoneal injection of STZ while maintaining atropine or saline eye drops. Color fundus photography showed no significant difference between the two eyes. However, fundus autofluorescence imaging showed fewer punctate hyperfluorescence lesions in the experimental eyes compared to the control group, suggesting that atropine reduced the number of abnormal RPE cells in DM mice. Furthermore, OCTA showed that the choroid in the atropine-treated eyes was thicker than in the control group. Figure 8 B). HE staining showed that the outer nuclear layer (ONL) of DM mice was loosely and disordered, and this condition was alleviated after atropine treatment. Figure 8 C).

[0138] Increased retinal cell apoptosis is a key characteristic of early diabetic retinopathy (DR). Here, we demonstrate that atropine can reduce apoptosis in the outer retinal lamina (ONL) and retinas (RPE) of DM mice. Figure 8 D). In summary, these data indicate that atropine can inhibit the progression of DR in DM mice, which is associated with an increased choroid-to-retinal volume ratio. Therefore, this further confirms that the choroid-to-retinal volume ratio is a key clinical feature of diabetic retinopathy.

[0139] Figure 3 This is a schematic diagram of a computer device provided in an embodiment of the present invention, such as... Figure 3 As shown, the device 2000 may include: one or more processors 2010 and one or more memories 2020; wherein the memories store computer-readable code that, when run by the one or more processors, can perform the methods described above.

[0140] The processor in this embodiment can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, operations, and logic block diagrams disclosed in this embodiment. The general-purpose processor can be a microprocessor or any conventional processor, and can be based on an x86 or ARM architecture.

[0141] In general, the various exemplary embodiments of this disclosure can be implemented in hardware or dedicated circuitry, software, firmware, logic, or any combination thereof. Some aspects can be implemented in hardware, while others can be implemented in firmware or software that can be executed by a controller, microprocessor, or other computing device. When aspects of embodiments of this disclosure are illustrated or described as block diagrams, flowcharts, or using some other graphical representation, it will be understood that the blocks, apparatuses, systems, techniques, or methods described herein can be implemented as non-limiting examples in hardware, software, firmware, dedicated circuitry or logic, general-purpose hardware or controllers or other computing devices, or some combination thereof.

[0142] For example, the method or apparatus according to embodiments of this disclosure can also be used by means of Figure 4 The architecture of the computing device 3000 shown is used for implementation. For example... Figure 4As shown, the computing device 3000 may include a bus 3010, one or more CPUs 3020, a read-only memory (ROM) 3030, a random access memory (RAM) 3040, a communication port 3050 connected to a network, an input / output component 3060, a hard disk 3070, etc. The storage devices in the computing device 3000, such as the ROM 3030 or the hard disk 3070, may store various data or files used for processing and / or communication of the methods provided in this disclosure, as well as program instructions executed by the CPU. The computing device 3000 may also include a user interface 3080. Of course, Figure 4 The architecture shown is merely exemplary and can be omitted as needed when implementing different devices. Figure 4 One or more components in the computing device shown.

[0143] This invention also includes a computer-readable storage medium, such as... Figure 5 The diagram illustrates a storage medium 4000 provided in an embodiment of the present invention. The computer storage medium 4020 stores computer-readable instructions 4010. When the computer-readable instructions 4010 are executed by a processor, the method described above according to embodiments of the present disclosure can be performed. The computer-readable storage medium in the embodiments of the present disclosure may be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. Non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory may be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic Random Access Memory (SDRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM), Enhanced Synchronous Dynamic Random Access Memory (ESDRAM), Synchronous Link Dynamic Random Access Memory (SLDRAM), and Direct Memory Bus Random Access Memory (DR RAM). It should be noted that the memory used in the methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0144] This disclosure also provides a computer program product or computer program that, when executed by a processor, implements the steps of the above-described method, such as... Figure 2 As shown, the computer program product or computer program includes:

[0145] Acquisition module 201: Used to acquire OCTA images of the eyes of diabetic patients;

[0146] Feature extraction module 202: used to extract choroidal features and retinal features based on the OCTA image, and calculate the ratio of choroidal features to retinal features based on the ratio of the choroidal features to retinal features;

[0147] Prediction module 203: used to input the choroidal-retinal feature ratio into the classifier to obtain the result of whether diabetic patients have developed retinopathy.

[0148] It should be noted that the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0149] In general, the various exemplary embodiments of this disclosure can be implemented in hardware or dedicated circuitry, software, firmware, logic, or any combination thereof. Some aspects can be implemented in hardware, while others can be implemented in firmware or software that can be executed by a controller, microprocessor, or other computing device. When aspects of embodiments of this disclosure are illustrated or described as block diagrams, flowcharts, or using some other graphical representation, it will be understood that the blocks, apparatuses, systems, techniques, or methods described herein can be implemented as non-limiting examples in hardware, software, firmware, dedicated circuitry or logic, general-purpose hardware or controllers or other computing devices, or some combination thereof.

[0150] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0151] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between apparatuses or units through some interfaces, and may be electrical, mechanical, or other forms.

[0152] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0153] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0154] The exemplary embodiments of this disclosure described in detail above are merely illustrative and not restrictive. Those skilled in the art will understand that various modifications and combinations can be made to these embodiments or their features without departing from the principles and spirit of this disclosure, and such modifications should fall within the scope of this disclosure.

Claims

1. A method for predicting diabetic retinopathy based on choroid-retinal characteristic ratio, characterized in that, The method includes: Obtain OCTA images of the eyes of diabetic patients; The ocular OCTA image is divided into a central region containing the fovea and a peripheral region outside the fovea. Choroidal and retinal features are extracted from the central region and the peripheral region, respectively. The ratio of choroidal to retinal features in the central region is calculated based on the ratio of choroidal to retinal features in the central region, and the ratio of choroidal to retinal features in the peripheral region is calculated based on the ratio of choroidal to retinal features in the peripheral region. The choroid-to-retinal feature ratio of the central region and the choroid-to-retinal feature ratio of the peripheral region are input into the classifier to obtain the result of whether diabetic patients have developed retinopathy. The method for constructing the classifier is as follows: acquiring OCTA images of the eyes of diabetic patients in the training set and corresponding labels, the labels including no retinopathy and retinopathy; extracting choroidal features and retinal features based on the OCTA images of the eyes in the training set, and calculating the ratio of choroidal to retinal features; inputting the ratio of choroidal to retinal features and labels into a machine learning model for iterative training to obtain the classifier; the ratio of choroidal to retinal features includes any one or more of the following: the ratio of total choroidal volume to total retinal volume, the ratio of choroidal vessel volume to total retinal volume, the ratio of total choroidal volume to outer retinal volume, and the ratio of choroidal vessel volume to outer retinal volume.

2. The method for predicting diabetic retinopathy based on choroid-retinal characteristic ratio according to claim 1, characterized in that, The ratio of choroidal to retinal features in the central region includes any one or more of the following: the ratio of the total volume of the choroid in the central region to the total volume of the retina, the ratio of the volume of the choroidal vessels in the central region to the total volume of the retina, the ratio of the total volume of the choroid in the central region to the volume of the outer retina, and the ratio of the volume of the choroidal vessels in the central region to the volume of the outer retina.

3. The method for predicting diabetic retinopathy based on choroid-retinal characteristic ratio according to claim 2, characterized in that, The total volume of the choroid in the central region is the volume between the RPE / BM in the central region and the choroid-scleral interface; the total volume of the retina in the central region is the volume between the inner limiting membrane and the RPE / BM in the central region. The choroidal vessel volume in the central region is the volume of the large and medium vessels within the choroid in the central region, and the total retinal volume in the central region is the volume between the inner boundary membrane and the RPE / BM in the central region. The volume of the outer retinal layer in the central region is the volume between the outer plexiform layer and the RPE / BM in the central region.

4. The method for predicting diabetic retinopathy based on choroid-retinal characteristic ratio according to claim 2, characterized in that, The ratio of choroidal to retinal features in the central region also includes the ratio of choroidal thickness to retinal thickness in the central region, wherein the choroidal thickness in the central region is the average thickness between the central region RPE / BM and the choroid-scleral interface, and the retinal thickness in the central region is the average thickness between the central region's inner boundary membrane and the RPE / BM. Alternatively, the ratio of choroidal to retinal features in the central region may further include the ratio of the choroidal thickness in the central region to the outer retinal layer thickness, wherein the choroidal thickness in the central region is the average thickness between the RPE / BM in the central region and the choroid-scleral interface, and the outer retinal layer volume in the central region is the average thickness between the outer plexiform layer in the central region and the RPE / BM.

5. The method for predicting diabetic retinopathy based on choroid-retinal characteristic ratio according to claim 1, characterized in that, The ratio of choroidal to retinal characteristics in the peripheral region includes any one or more of the following: the ratio of the total volume of the choroid in the peripheral region to the total volume of the retina, the ratio of the volume of the choroidal vessels in the peripheral region to the total volume of the retina, the ratio of the total volume of the choroid in the peripheral region to the volume of the outer retina, and the ratio of the volume of the choroidal vessels in the peripheral region to the volume of the outer retina.

6. The method for predicting diabetic retinopathy based on choroid-retinal characteristic ratio according to claim 5, characterized in that, The total volume of the choroid in the peripheral region is the volume between the RPE / BM in the peripheral region and the choroid-scleral interface; the total volume of the retina in the peripheral region is the volume between the inner limiting membrane and the RPE / BM in the peripheral region. The volume of the choroidal vessels in the peripheral region is the volume of the large and medium vessels within the choroid in the peripheral region, and the total volume of the retina in the peripheral region is the volume between the inner limiting membrane and the RPE / BM in the peripheral region. The volume of the outer retinal layer in the peripheral region is the volume between the outer plexiform layer and the RPE / BM in the peripheral region.

7. The method for predicting diabetic retinopathy based on choroid-retinal characteristic ratio according to claim 5, characterized in that, The ratio of choroidal to retinal features in the peripheral region further includes the ratio of choroidal thickness to retinal thickness in the peripheral region, wherein the choroidal thickness in the peripheral region is the average thickness between the peripheral region RPE / BM and the choroid-scleral interface, and the retinal thickness in the peripheral region is the average thickness between the peripheral region inner boundary membrane and the RPE / BM. Alternatively, the ratio of choroidal to retinal features in the peripheral region may further include the ratio of choroidal thickness to outer retinal thickness in the peripheral region, wherein the choroidal thickness in the peripheral region is the average thickness between the RPE / BM and the choroid-scleral interface in the peripheral region, and the outer retinal volume in the peripheral region is the average thickness between the outer plexus layer and the RPE / BM in the peripheral region.

8. The method for predicting diabetic retinopathy based on choroid-retinal characteristic ratio according to claim 1, characterized in that, The eye OCTA image is obtained by performing OCTA imaging using a fovea-centered scanning mode. The image is divided into a 3×3 grid, with the central grid designated as the central region and the surrounding grids considered as the peripheral region.

9. A computer device, characterized in that, The device includes: a memory and a processor; the memory is used to store a computer program; the processor executes the computer program to implement the steps of the method according to any one of claims 1-8.

10. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by a processor, implements the steps of the method as described in any one of claims 1-8.

11. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the steps of the method described in any one of claims 1-8.

Images