A Dual-Modal Fusion Network Using Optical Coherence Tomography and Fundus Images in Detection of Glaucomatous Optic Neuropathy.

PURPOSE: We designed a dual-modal fusion network to detect glaucomatous optic neuropathy, which utilized both retinal nerve fiber layer thickness from optical coherence tomography reports and fundus images. METHODS: A total of 327 healthy subjects (410 eyes) and 87 glaucomatous optic neuropathy patients (113 eyes) were included. The retinal nerve fiber layer thickness from optical coherence tomography reports and fundus images were used as predictors in the dual-modal fusion network to diagnose glaucoma. The area under the receiver operation characteristic curve, accuracy, sensitivity, and specificity were measured to compare our method and other approaches. RESULTS: The accuracy of our dual-modal fusion network using both retinal nerve fiber layer thickness from optical coherence tomography reports and fundus images was 0.935 and we achieved a significant larger area under the receiver operation characteristic curve of our method with 0.968 (95% confidence interval, 0.937-0.999). For only using retinal nerve fiber layer thickness, we compared the area under the receiver operation characteristic curves between our network and other three approaches: 0.916 (95% confidence interval, 0.855, 0.977) with our optical coherence tomography Net; 0.841 (95% confidence interval, 0.749, 0.933) with Clock sectors division; 0.862 (95% confidence interval, 0.757, 0.968) with inferior, superior, nasal temporal sectors division and 0.886 (95% confidence interval, 0.815, 0.957) with optic disc sectors division. For only using fundus images, we compared the area under the receiver operation characteristic curves between our network and other two approaches: 0.867 (95% confidence interval: 0.781-0.952) with our Image Net; 0.774 (95% confidence interval: 0.670, 0.878) with ResNet50; 0.747 (95% confidence interval: 0.628, 0.866) with VGG16. CONCLUSION: Our dual-modal fusion network utilizing both retinal nerve fiber layer thickness from optical coherence tomography reports and fundus images can diagnose glaucoma with a much better performance than the current approaches based on optical coherence tomography only or fundus images only.

Improve the efficiency and accuracy of ophthalmologists' clinical decision-making based on AI technology.

BACKGROUND: As global aging intensifies, the prevalence of ocular fundus diseases continues to rise. In China, the tense doctor-patient ratio poses numerous challenges for the early diagnosis and treatment of ocular fundus diseases. To reduce the high risk of missed or misdiagnosed cases, avoid irreversible visual impairment for patients, and ensure good visual prognosis for patients with ocular fundus diseases, it is particularly important to enhance the growth and diagnostic capabilities of junior doctors. This study aims to leverage the value of electronic medical record data to developing a diagnostic intelligent decision support platform. This platform aims to assist junior doctors in diagnosing ocular fundus diseases quickly and accurately, expedite their professional growth, and prevent delays in patient treatment. An empirical evaluation will assess the platform's effectiveness in enhancing doctors' diagnostic efficiency and accuracy. METHODS: In this study, eight Chinese Named Entity Recognition (NER) models were compared, and the SoftLexicon-Glove-Word2vec model, achieving a high F1 score of 93.02%, was selected as the optimal recognition tool. This model was then used to extract key information from electronic medical records (EMRs) and generate feature variables based on diagnostic rule templates. Subsequently, an XGBoost algorithm was employed to construct an intelligent decision support platform for diagnosing ocular fundus diseases. The effectiveness of the platform in improving diagnostic efficiency and accuracy was evaluated through a controlled experiment comparing experienced and junior doctors. RESULTS: The use of the diagnostic intelligent decision support platform resulted in significant improvements in both diagnostic efficiency and accuracy for both experienced and junior doctors (P < 0.05). Notably, the gap in diagnostic speed and precision between junior doctors and experienced doctors narrowed considerably when the platform was used. Although the platform also provided some benefits to experienced doctors, the improvement was less pronounced compared to junior doctors. CONCLUSION: The diagnostic intelligent decision support platform established in this study, based on the XGBoost algorithm and NER, effectively enhances the diagnostic efficiency and accuracy of junior doctors in ocular fundus diseases. This has significant implications for optimizing clinical diagnosis and treatment.

Effect of propylene glycol mannate sulfate on non-proliferative diabetic retinopathy.

PURPOSE: To evaluate the effect of propylene glycol mannate sulfate (PGMS) on retinopathy in non-proliferative diabetic patients. METHODS: Eighty patients (111 eyes) with non-proliferative diabetic retinopathy were selected and retrospectively analyzed. Patients were divided into a control group (40 cases, 56 eyes) and an experimental group (40 cases, 55 eyes) using a random number table method. The control group continued had routine blood glucose management, while the experimental group received PGMS 100 mg additionally TID for 60 days. Changes in visual acuity, fundus conditions including hemorrhage points and exudation in each quadrant, and non-perfusion area were revealed through fundus angiography before and after the treatment period. RESULTS: After PGMS treatment, the experimental group demonstrated significant improvements compared to the control group in terms of eyesight improvement (P=0.002), the macular edema and macular retinal thickness (P=0.008). The total clinical efficacy rate of the experimental group was 67.86%, which was higher than 38.18% of the control group (P=0.032). Notably, there was a significant reduction in macular hemorrhage and hard extrusion. CONCLUSION: Oral administration of PGMS is an effective treatment for non-proliferative diabetic retinopathy.

Clinical Applications and Future Directions of Smartphone Fundus Imaging.

The advent of smartphone fundus imaging technology has marked a significant evolution in the field of ophthalmology, offering a novel approach to the diagnosis and management of retinopathy. This review provides an overview of smartphone fundus imaging, including clinical applications, advantages, limitations, clinical applications, and future directions. The traditional fundus imaging techniques are limited by their cost, portability, and accessibility, particularly in resource-limited settings. Smartphone fundus imaging emerges as a cost-effective, portable, and accessible alternative. This technology facilitates the early detection and monitoring of various retinal pathologies, including diabetic retinopathy, age-related macular degeneration, and retinal vascular disorders, thereby democratizing access to essential diagnostic services. Despite its advantages, smartphone fundus imaging faces challenges in image quality, standardization, regulatory considerations, and medicolegal issues. By addressing these limitations, this review highlights the areas for future research and development to fully harness the potential of smartphone fundus imaging in enhancing patient care and visual outcomes. The integration of this technology into telemedicine is also discussed, underscoring its role in facilitating remote patient care and collaborative care among physicians. Through this review, we aim to contribute to the understanding and advancement of smartphone fundus imaging as a valuable tool in ophthalmic practice, paving the way for its broader adoption and integration into medical diagnostics.

Enhancing stroke risk and prognostic timeframe assessment with deep learning and a broad range of retinal biomarkers.

Stroke stands as a major global health issue, causing high death and disability rates and significant social and economic burdens. The effectiveness of existing stroke risk assessment methods is questionable due to their use of inconsistent and varying biomarkers, which may lead to unpredictable risk evaluations. This study introduces an automatic deep learning-based system for predicting stroke risk (both ischemic and hemorrhagic) and estimating the time frame of its occurrence, utilizing a comprehensive set of known retinal biomarkers from fundus images. Our system, tested on the UK Biobank and DRSSW datasets, achieved AUROC scores of 0.83 (95% CI: 0.79-0.85) and 0.93 (95% CI: 0.9-0.95), respectively. These results not only highlight our system's advantage over established benchmarks but also underscore the predictive power of retinal biomarkers in assessing stroke risk and the unique effectiveness of each biomarker. Additionally, the correlation between retinal biomarkers and cardiovascular diseases broadens the potential application of our system, making it a versatile tool for predicting a wide range of cardiovascular conditions.

Association of retinal microvascular curve tortuosity and multiple sclerosis: A cross-section analysis from the UK Biobank.

BACKGROUND: There is growing evidence supporting that vascular abnormalities contribute to multiple sclerosis (MS), and retinal microvasculature functions as a visible window to observe vessels. We hypothesized that retinal vascular curve tortuosity is associated with MS, which this study aims to address. METHODS: Participants from the UK Biobank with complete clinical records and gradable fundus photos were included in the study. Arteriolar and venular curve tortuosity and vessel area density are quantified automatically using a deep learning system. Individuals with MS were matched to healthy controls using propensity score matching (PSM). Conditional logistic regression was used to investigate the association between retinal vascular characteristics and MS. We also used a receiver operating characteristic (ROC) curve to assess the diagnostic performance of MS. RESULTS: Venular curve tortuosity (VCT) was found to be significantly associated with MS. And patients with multiple sclerosis were probable to have lower VCT than the non-MS group (OR = 0.22 [95 % CI, 0.05 to 0.92], P < 0.05). CONCLUSIONS: Our study reveals a significant association between vessel curve tortuosity and MS. The lower curve tortuosity of the retinal venular network may indicate a higher risk of incident multiple sclerosis.

Automated interpretation of retinal vein occlusion based on fundus fluorescein angiography images using deep learning: A retrospective, multi-center study.

Purpose: Fundus fluorescein angiography (FFA) is the gold standard for retinal vein occlusion (RVO) diagnosis. This study aims to develop a deep learning-based system to diagnose and classify RVO using FFA images, addressing the challenges of time-consuming and variable interpretations by ophthalmologists. Methods: 4028 FFA images of 467 eyes from 463 patients were collected and annotated. Three convolutional neural networks (CNN) models (ResNet50, VGG19, InceptionV3) were trained to generate the label of image quality, eye, location, phase, lesions, diagnosis, and macular involvement. The performance of the models was evaluated by accuracy, precision, recall, F-1 score, the area under the curve, confusion matrix, human-machine comparison, and Clinical validation on three external data sets. Results: The InceptionV3 model outperformed ResNet50 and VGG19 in labeling and interpreting FFA images for RVO diagnosis, achieving 77.63%-96.45% accuracy for basic information labels and 81.72%-96.45% for RVO-relevant labels. The comparison between the best CNN and ophthalmologists showed up to 19% accuracy improvement with the inceptionV3. Conclusion: This study developed a deep learning model capable of automatically multi-label and multi-classification of FFA images for RVO diagnosis. The proposed system is anticipated to serve as a new tool for diagnosing RVO in places short of medical resources.

Multi-degradation-adaptation network for fundus image enhancement with degradation representation learning.

Fundus image quality serves a crucial asset for medical diagnosis and applications. However, such images often suffer degradation during image acquisition where multiple types of degradation can occur in each image. Although recent deep learning based methods have shown promising results in image enhancement, they tend to focus on restoring one aspect of degradation and lack generalisability to multiple modes of degradation. We propose an adaptive image enhancement network that can simultaneously handle a mixture of different degradations. The main contribution of this work is to introduce our Multi-Degradation-Adaptive module which dynamically generates filters for different types of degradation. Moreover, we explore degradation representation learning and propose the degradation representation network and Multi-Degradation-Adaptive discriminator for our accompanying image enhancement network. Experimental results demonstrate that our method outperforms several existing state-of-the-art methods in fundus image enhancement. Code will be available at https://github.com/RuoyuGuo/MDA-Net.

Long COVID: cognitive, balance, and retina manifestations.

Background: The neurological symptoms of Long COVID (LC) and the impact of neuropsychological manifestations on people's daily lives have been extensively described. Although a large body of literature describes symptoms, validating this with objective measures is important. This study aims to identify and describe the effects of Long COVID on cognition, balance, and the retinal fundus, and determine whether the duration of symptoms influences cognitive impairment. Methods: This cross-sectional study involved LC volunteers with cognitive complaint from public health centers in northern Barcelona who participated between January 2022 and March 2023. This study collected sociodemographic characteristics, information on substance use, comorbidities, and clinical data related to COVID-19. We measured five cognitive domains using a battery of neuropsychological tests. Balance was assessed through posturography and retinal vascular involvement by retinography. Results: A total of 166 people with LC and cognitive complaints participated, 80.72% were women and mean age was 49.28 ± 8.39 years. The most common self-reported symptoms were concentration and memory deficit (98.80%), brain fog (82.53%) and insomnia (71.17%). The 68.67% presented cognitive deficit in at least one domain, with executive functions being the most frequent (43.98%). The 51.52% of the participants exhibited a dysfunctional pattern in balance, and 9.2% showed some alteration in the retina. There were no statistically significant differences between cognitive impairment and symptom duration. Conclusion: Our findings contribute to a more comprehensive understanding of the pathology associated with Long COVID. They highlight the diversity of self-reported symptoms, the presence of abnormal balance patterns, and some cognitive impairment. These findings underscore the necessity of addressing the clinical management of this condition in primary care through follow-up and the pursuit of multidisciplinary and comprehensive treatment.

Eyesi direct ophthalmoscope simulator: an effective training tool for medical undergraduates.

INTRODUCTION: Non-ophthalmologists often lack sufficient operational training to use a direct ophthalmoscope proficiently, resulting in a global deficit of basic ophthalmological skills among general practitioners. This deficiency hampers the timely diagnosis, referral, and intervention of patients. Consequently, the optimization of teaching tools and methods to enhance teaching efficiency is imperative. This study explores the effectiveness of the Eyesi Direct Ophthalmoscope Simulator (Eyesi) as an innovative tool for fundus examination training. METHODS: Medical undergraduates were randomly assigned to Group A or B (n = 168). All participants completed a pre-training questionnaire. Group A received Eyesi training, while Group B underwent traditional direct ophthalmoscope (TDO) training. Subsequently, participants answered questionnaires relevant to their respective training methods. Both groups exchanged training tools and completed a summary questionnaire. RESULTS: After training, 54.17% of participants believed that images presented by the Eyesi were consistent with the real fundus. Group A scored significantly higher than Group B in fundus structure recognition and self-confidence in examination. The degree of mastery over fundus theory score increased from 6.10 ± 0.13 to 7.74 ± 0.16 (P < 0.001) in Group A, but Group B did not demonstrate a significant difference. We also compared undergraduates' tendencies for different learning purposes, 75.59% of participants preferred the Eyesi to TDO as a training tool, and 88.41% of participants were receptive to introducing the Eyesi in training. CONCLUSION: According to subjective participant feedback, Eyesi outperformed TDO in fundus observation, operational practice, and theoretical learning. It effectively equips undergraduates with fundus examination skills, potentially promoting the use of direct ophthalmoscopes in primary medical institutions.

Choroidal vascularity features of fundus tessellation in adults with high myopia.

BACKGROUND: To investigate alterations in choroidal vascularity index among highly myopic adults with fundus tessellation, utilizing optical coherence tomography. METHODS: Total of 143 highly myopic adults (234 eyes) with fundus tessellation were collected in this cross-sectional study, which was stratified into different lesion groups based on the novel tessellated fundus classification. Subfoveal choroidal thickness (SFCT), choroidal luminal area (LA), stromal area (SA), total choroidal area (TCA), and choroidal vascularity index (CVI) were analyzed utilizing optical coherence tomography (OCT) with enhanced depth imaging (EDI) mode, enabling precise quantification of these parameters. RESULTS: Comparison analysis demonstrated notable distinctions in spherical equivalent (SE), axial length (AL), and SFCT across the four tessellation grades (p < 0.001). Analysis of the choroidal vascularity parameters, including LA, TCA, and CVI, demonstrated notable disparities across the four groups (p < 0.001), while no significant variations were observed in SA when comparing Grade 1 versus Grade 2, as well as Grade 2 versus Grade 3 (p > 0.05). Logistic regression analyses illustrated that the higher grade of tessellated exhibited a positive association with AL (OR = 1.701, p = 0.027), while negatively associated with SFCT (OR = 0.416, p = 0.007), LA (OR = 0.438, p = 0.010) and CVI (OR = 0.529, p = 0.004). Multiple regression analyses demonstrated a significant negative association between CVI and both SE and AL after adjusting for age, while positively associated with SFCT (p < 0.05). CONCLUSION: Subtle choroidal vascularity changes may have a meaningful contribution to the development and progression of fundus tessellation. CVI and LA dramatically decreased during the early stages of tessellation development and maintained a relatively stable status when in the severe tessellated grades.

Deep learning for predicting circular retinal nerve fiber layer thickness from fundus photographs and diagnosing glaucoma.

Purpose: This study aimed to propose a new deep learning (DL) approach to automatically predict the retinal nerve fiber layer thickness (RNFLT) around optic disc regions in fundus photography trained by optical coherence tomography (OCT) and diagnose glaucoma based on the predicted comprehensive information about RNFLT. Methods: A total of 1403 pairs of fundus photographs and OCT RNFLT scans from 1403 eyes of 1196 participants were included. A residual deep neural network was trained to predict the RNFLT for each local image in a fundus photograph, and then a RNFLT report was generated based on the local images. Two indicators were designed based on the generated report. The support vector machines (SVM) algorithm was used to diagnose glaucoma based on the two indicators. Results: A strong correlation was found between the predicted and actual RNFLT values on local images. On three testing datasets, we found the Pearson r to be 0.893, 0.850, and 0.831, respectively, and the mean absolute error of the prediction to be 14.345, 17.780, and 19.250 µm, respectively. The area under the receiver operating characteristic curves for discriminating glaucomatous from healthy eyes was 0.860 (95 % confidence interval, 0.799-0.921). Conclusions: We established a novel local image-based DL approach to provide comprehensive quantitative information on RNFLT in fundus photographs, which was used to diagnose glaucoma. In addition, training a deep neural network based on local images to predict objective detail information in fundus photographs provided a new paradigm for the diagnosis of ophthalmic diseases.

Unpaired fundus image enhancement based on constrained generative adversarial networks.

Fundus photography (FP) is a crucial technique for diagnosing the progression of ocular and systemic diseases in clinical studies, with wide applications in early clinical screening and diagnosis. However, due to the nonuniform illumination and imbalanced intensity caused by various reasons, the quality of fundus images is often severely weakened, brings challenges for automated screening, analysis, and diagnosis of diseases. To resolve this problem, we developed strongly constrained generative adversarial networks (SCGAN). The results demonstrate that the quality of various datasets were more significantly enhanced based on SCGAN, simultaneously more effectively retaining tissue and vascular information under various experimental conditions. Furthermore, the clinical effectiveness and robustness of this model were validated by showing its improved ability in vascular segmentation as well as disease diagnosis. Our study provides a new comprehensive approach for FP and also possesses the potential capacity to advance artificial intelligence-assisted ophthalmic examination.

Segmentation of retinal microaneurysms in fluorescein fundus angiography images by a novel three-step model.

Introduction: Microaneurysms serve as early signs of diabetic retinopathy, and their accurate detection is critical for effective treatment. Due to their low contrast and similarity to retinal vessels, distinguishing microaneurysms from background noise and retinal vessels in fluorescein fundus angiography (FFA) images poses a significant challenge. Methods: We present a model for automatic detection of microaneurysms. FFA images were pre-processed using Top-hat transformation, Gray-stretching, and Gaussian filter techniques to eliminate noise. The candidate microaneurysms were coarsely segmented using an improved matched filter algorithm. Real microaneurysms were segmented by a morphological strategy. To evaluate the segmentation performance, our proposed model was compared against other models, including Otsu's method, Region Growing, Global Threshold, Matched Filter, Fuzzy c-means, and K-means, using both self-constructed and publicly available datasets. Performance metrics such as accuracy, sensitivity, specificity, positive predictive value, and intersection-over-union were calculated. Results: The proposed model outperforms other models in terms of accuracy, sensitivity, specificity, positive predictive value, and intersection-over-union. The segmentation results obtained with our model closely align with benchmark standard. Our model demonstrates significant advantages for microaneurysm segmentation in FFA images and holds promise for clinical application in the diagnosis of diabetic retinopathy. Conclusion: The proposed model offers a robust and accurate approach to microaneurysm detection, outperforming existing methods and demonstrating potential for clinical application in the effective treatment of diabetic retinopathy.

The recruitment of mechanosensitive enteric neurons in the guinea pig gastric fundus is dependent on ganglionic stretch level.

BACKGROUND: Serving as a reservoir, the gastric fundus can expand significantly, with an initial receptive and a following adaptive relaxation, controlled by extrinsic and intrinsic reflex circuits, respectively. We hypothesize that mechanosensitive enteric neurons (MEN) are involved in the adaptive relaxation, which is initiated when a particular gastric volume and a certain stretch of the stomach wall is reached. To investigate whether the responsiveness of MEN in the gastric fundus is dependent on tissue stretch, we performed mechanical stimulations in stretched versus ganglia "at rest". METHODS: Responses of myenteric neurons in the guinea pig gastric fundus were recorded with membrane potential imaging using Di-8-ANEPPS. MEN were identified by small-volume intraganglionic injection in ganglia stretched to different degrees using a self-constructed stretching tool. Immunohistochemical staining identified the neurochemical phenotype of MEN. Hexamethonium and capsaicin were added to test their effect on recruited MEN. KEY RESULTS: In stretched compared to "at rest" ganglia, significantly more MEN were activated. The change in the ganglionic area correlated significantly with the number of additional recruited MEN. The additional recruitment of MEN was independent from nicotinic transmission and the ratio of active MEN in stretched ganglia shifted towards a nitrergic phenotype. CONCLUSION AND INFERENCES: The higher number of active MEN with increasing stretch of the ganglia and their greater share of nitrergic phenotype might indicate their contribution to the adaptive relaxation. Further experiments are necessary to address the receptors involved in mechanotransduction.

FQ-UWF: Unpaired Generative Image Enhancement for Fundus Quality Ultra-Widefield Retinal Images.

Ultra-widefield (UWF) retinal imaging stands as a pivotal modality for detecting major eye diseases such as diabetic retinopathy and retinal detachment. However, UWF exhibits a well-documented limitation in terms of low resolution and artifacts in the macular area, thereby constraining its clinical diagnostic accuracy, particularly for macular diseases like age-related macular degeneration. Conventional supervised super-resolution techniques aim to address this limitation by enhancing the resolution of the macular region through the utilization of meticulously paired and aligned fundus image ground truths. However, obtaining such refined paired ground truths is a formidable challenge. To tackle this issue, we propose an unpaired, degradation-aware, super-resolution technique for enhancing UWF retinal images. Our approach leverages recent advancements in deep learning: specifically, by employing generative adversarial networks and attention mechanisms. Notably, our method excels at enhancing and super-resolving UWF images without relying on paired, clean ground truths. Through extensive experimentation and evaluation, we demonstrate that our approach not only produces visually pleasing results but also establishes state-of-the-art performance in enhancing and super-resolving UWF retinal images. We anticipate that our method will contribute to improving the accuracy of clinical assessments and treatments, ultimately leading to better patient outcomes.

The Outcome of Snare-Assisted Traction Endoscopic Full-Thickness Resection for the Gastric Fundus Submucosal Tumors Originating from the Muscularis Propria.

Aim: To explore the feasibility and effectiveness of snare-assisted traction endoscopic full thickness resection (EFTR) on gastric fundus submucosal tumors (SMTs). Methods: The clinical and pathological data of patients with gastric SMTs who underwent EFTR treatment at the Endoscopy Center of Kaifeng Central Hospital from January 2018 to June 2023 were collected. Among them, 36 patients underwent snare-assisted traction EFTR (SAT-EFTR) and 46 patients underwent standard EFTR (S-EFTR). The clinical baseline data, operative data, adverse events, and follow-up results of the two groups were collected and compared. Results: All patients successfully completed EFTR technique. There were 34 male and 48 female patients, with an average age of (56.62 ± 11.31) years. The average operation time was shorter in the snare-assisted EFTR group than the S-EFTR group (73.39 ± 31.33 minutes versus 92.89 ± 37.57 minutes, P = .014). In addition, the resection speed of the snare-assisted EFTR group was also significantly faster than that of the S-EFTR group (4.04 ± 2.23 versus 2.48 ± 0.93 mm2/min, P < .001). There was no statistically significant difference in the age, gender, lesion size, postoperative fasting duration, and postoperative hospitalization stay between the two groups (P > .05). One patient in the SAT-EFTR group developed delayed postoperative perforation which was close with purse­string suture technique. All patients were discharged successfully, and there was no recurrence or metastasis during the follow-up period. Conclusion: Snare-assisted traction of EFTR could shorten the operation time, reduce the difficulty of the operation, and improve the efficiency of the operation. At the same time, this method is simple and easy to learn, more suitable for beginners, and worthy of clinical promotion and application.

Research on segmentation model of optic disc and optic cup in fundus.

BACKGROUND: Glaucoma is a worldwide eye disease that can cause irreversible vision loss. Early detection of glaucoma is important to reduce vision loss, and retinal fundus image examination is one of the most commonly used solutions for glaucoma diagnosis due to its low cost. Clinically, the cup-disc ratio of fundus images is an important indicator for glaucoma diagnosis. In recent years, there have been an increasing number of algorithms for segmentation and recognition of the optic disc (OD) and optic cup (OC), but these algorithms generally have poor universality, segmentation performance, and segmentation accuracy. METHODS: By improving the YOLOv8 algorithm for segmentation of OD and OC. Firstly, a set of algorithms was designed to adapt the REFUGE dataset's result images to the input format of the YOLOv8 algorithm. Secondly, in order to improve segmentation performance, the network structure of YOLOv8 was improved, including adding a ROI (Region of Interest) module, modifying the bounding box regression loss function from CIOU to Focal-EIoU. Finally, by training and testing the REFUGE dataset, the improved YOLOv8 algorithm was evaluated. RESULTS: The experimental results show that the improved YOLOv8 algorithm achieves good segmentation performance on the REFUGE dataset. In the OD and OC segmentation tests, the F1 score is 0.999. CONCLUSIONS: We improved the YOLOv8 algorithm and applied the improved model to the segmentation task of OD and OC in fundus images. The results show that our improved model is far superior to the mainstream U-Net model in terms of training speed, segmentation performance, and segmentation accuracy.

Multi-label classification of retinal diseases based on fundus images using Resnet and Transformer.

Retinal disorders are a major cause of irreversible vision loss, which can be mitigated through accurate and early diagnosis. Conventionally, fundus images are used as the gold diagnosis standard in detecting retinal diseases. In recent years, more and more researchers have employed deep learning methods for diagnosing ophthalmic diseases using fundus photography datasets. Among the studies, most of them focus on diagnosing a single disease in fundus images, making it still challenging for the diagnosis of multiple diseases. In this paper, we propose a framework that combines ResNet and Transformer for multi-label classification of retinal disease. This model employs ResNet to extract image features, utilizes Transformer to capture global information, and enhances the relationships between categories through learnable label embedding. On the publicly available Ocular Disease Intelligent Recognition (ODIR-5 k) dataset, the proposed method achieves a mean average precision of 92.86%, an area under the curve (AUC) of 97.27%, and a recall of 90.62%, which outperforms other state-of-the-art approaches for the multi-label classification. The proposed method represents a significant advancement in the field of retinal disease diagnosis, offering a more accurate, efficient, and comprehensive model for the detection of multiple retinal conditions.