Optic Cup Segmentation using U-Net Architecture on Retinal Fundus Image

Diabetic retinopathy (DR) is a complication of retinal related common micro vascular disease occurred in diabetic patients. It is the one of the major causes of adult blindness in the worldwide. DR is indicated by the presence of hard exudates, soft exudates, haemorrhages, the growth of new blood vessels and foveal avascular zone (FAZ) enlargement. The objective of this work is to detect FAZ area in the colour retinal fundus images. In retinal fundus images, FAZ is located in the centre of macula, which is usually capillary-free. The detection of FAZ is an important step in the assessment of retinal images for visual related pathology detection. Retinal images are taken from Messidor database consisting of 59 retinal images. The proposed method has four main steps, i.e. pre-processing, blood vessels extraction, FAZ detection, and validation test. In the pre-processing step, morphological operation followed by contrast stretching is used to enhance and improve image quality. In other hand, matched filter and local entropy thresholding are applied to extract retinal blood vessels. FAZ area is detected by connecting retinal vessel endpoints. Finally, validation test is conducted by calculating the correlation between polygon area as detected FAZ by proposed method and circular area as labelled FAZ by ophthalmologists. The result achieves the correlation coefficient of 0.912 indicating that the proposed method has significant correlation with the method of the ophthalmologists.

Optic disc detection and segmentation using saliency mask in retinal fundus images

Glaucoma detection from retinal fundus images using graph convolution based multi-task model

Glaucoma, the leading cause of irreversible blindness, must be diagnosed early and thus treated in time. However, it has no noticeable symptoms in its early stages and may not be detected easily. This paper aims to compare two well-known convolutional neural network (CNN) structures, namely Fully Convolutional Networks (FCNs) and U-Net for the segmentation of the optic disc (OD) and optic cup (OC) from retinal fundus images which play an important role in glaucoma diagnosis. The performance of both models is assessed using qualitative parameters such as the Dice coefficient, Jaccard index, and cup-to-disc ratio (CDR) error. In our experiment, the U-Net model yields more accurate segmentation results with 0.9601 average pixel accuracy and 0.9255 dice score for OD segmentation, outperforming the FCNs model with 0.9560 average pixel accuracy and 0.9132 dice score for OD segmentation. However, FCNs have a shorter inference time of 0. 0043 seconds against U-net’s 0. 0062 seconds making FCNs more suitable for real-time applications. The restrictions related to this study include biases from using only one dataset acquired from particular imaging devices, dependency on mask-based cropping techniques, and comparison being restricted to two fundamental architectures. This work presents the contribution of the deep learning models in improving glaucoma screening and therefore helping in avoiding blindness.

The aim of this survey is to list the various disease predictions from retinal fundus images and various methods used to detect the disease. This paper gives a detailed description about the various diseases predicted in retina by comparing retinal fundus image structure. Till now, the prediction of various diseases such as diabetic retinopathy, cardiovascular disease and other eye problems had been predicted by using retinal fundus images. Next, a comparitive study of the various methods followed using image processing to find out the diseases from retinal fundus images, is provided. The basic matrices observed to predict the diseases are optic disc,nerve cup and rim. To find the differences in the basic matrices, image processing techniques such as mask generation, colour normalization, edge detection, contrast enhancement are used. The datasets that are used for retinal image inputs are STARE, DRIVE, ONHSD, ARIA, IMAGERET. The survey at the end, discusses the future work for the possibilities of predicting gastreointestinal problems via retinal fundus images.

Retinal fundus image is a crucial tool for ophthalmologists to diagnose eye-related diseases. These images provide visual information of the interior layer of the retina structures such as optic disc, optic cup, blood vessels and macula that can assist ophthalmologist in determining the health of an eye. Segmentation of blood vessels in fundus images is one of the most fundamental phase in detecting diseases such as diabetic retinopathy. However, the ambiguity of the retina structures in the retinal fundus images presents a challenge for researcher to segment the blood vessels. Extensive pre-processing and training of the images is necessary for precise segmentation, which is very intricate and laborious. This paper proposes the implementation of object-oriented-based metadata (OOM) structures of each pixel in the retinal fundus images. These structures comprise of additional metadata towards the conventional red, green, and blue data for each pixel within the images. The segmentation of the blood vessels in the retinal fundus images are performed by considering these additional metadata that enunciates the location, color spaces, and neighboring pixels of each individual pixel. From the results, it is shown that accurate segmentation of retinal fundus blood vessels can be achieved by purely employing straightforward thresholding method via the OOM structures without extensive pre-processing image processing technique or data training.

The structure of the optic disc is impacted by the devastating eye disease glaucoma. Most doctors rely on viewing and screening the retinal fundus images to detect it. Identifying the optic disc is a crucial stage for automated diagnosis of glaucoma. This study presents a transfer learning-based approach to locate the optic disc in the retinal fundus image. The fundus images are categorized into four distinct classes according to the positions of optic disc to learn the in-depth specific features.Based on the YOLOv3 model, the optic disc detection method is then fine-tuned using the specialised image dataset. The model involved is trained and evaluated on 2178 retinal fundus images obtained from database at a nearby hospital and publically accessible datasets. In 2103 of the retinal fundus images, the suggested approach successfully detected the optical disc, yielding an average accuracy of 96.56%.

Glaucoma is caused by damaged optic nerves, and can lead to permanent vision loss. The cup-to-disk ratio (CDR) is a key criterion for glaucoma diagnosis, therefore an accurate automatic segmentation of the optic disc (OD) and optic cup (OC) in retinal fundus images has become a major research topic. However, with deeper deep learning models being used to complete a fundus segmentation, the segmentation results remain acceptable only on certain datasets. In this research, a lightweight deep-learning encoder–decoder architecture, which adopts polar coordinate transformation and histogram equalization to simplify the learning complexity, is proposed for the simultaneous segmentation of OD and OC. The proposed model employs an encoder–decoder architecture consisting of a feature extraction module and a multi-output module to both simplify the model and to adjust the result through different outputs and multilabel loss functions. Experiment results demonstrate that the proposed approach outperforms other deep network models on OD and OC segmentation over the datasets REFUGE, MESSIDOR, and RIM-ONE, which contain images captured from cameras with various specifications. In addition, better results on glaucoma screening through CDR calculation were obtained on the REFUGE dataset with the proposed method.

Image quality can either boost or reduce segmentation sensitivity and predictive accuracy of micro vessels from retinal fundus images. The main cause of difficulty in segmentation task particularly in medical imaging such as retinal fundus images, can be majorly attributed to image degradation as a result of noise, low contrast, uneven illumination, obscurity and so on. Image quality degradation leads to loss of information and can affect both the classification and segmentation accuracy of Convolutional Neural Networks (CNNs) as well as diagnosis and analysis. Regardless of how good a CNNs model is, blur and noise can reduce the pixels classification accuracy by exhibiting partial biasness. To this end, this paper aims at reviewing the existing CNNs based method for the segmentation of blood vessels from the retinal fundus image. The review focuses majorly on the image enhancement technique(s) used to address the image quality degradation at pre-processing, processing and postprocessing stages and examines the effects on the CNNs based method performance. The review will aid a critical analysis of the effects of these enhancement techniques, particularly on sensitivity and Area under the ROC curve (AUC) metrics. The percentage of these two metrics are good and dependable yardstick to a successful model in terms of the blood vessels segmentation performance evaluation.

Glaucoma is a one of the serious diseases that occurs in retina. Early detection of glaucoma can prevent patients from blindness. One of the techniques to support the diagnosis of glaucoma is developed through the detection and segmentation of optic disc area. Optic disc area is also useful in assisting automated detection of abnormalities in the case of diabetic retinopathy. In this work, extracted red channel of colour retinal fundus images is used. Median filter is used to reduce noises in the red channel image. Segmentation of optic disc is conducted based on morphological operation. DRISHTI-GS dataset is used in this research works. Results indicate that the proposed method can achieve an accuracy of 94.546% in segmenting the optic disc.

Computerized framework based-automated analysis of medical images is an emerging area of research for identifying diseases in the medical field using imaging technology. The process of segmenting the blood vessels in the retinal fundus image plays a vital role in finding many eye diseases, in which glaucoma is a currently leading disease that affected the Optic Nerve on the retina due to high pressure generated on the eyes because of excessive usage of electronic screen devices. It is essential to early detection and analysis of the glaucoma in the retinal fundus image for preventing from the vision loss, the time of its detection could be very essential while it cannot be cured. In recent days, many segmentation and classification techniques to detect the glaucoma based on an optic cup and optic disc parameters in retina are proposed, but there is an improvement needed in existing techniques in order to enhance the precision of diagnosis. The aim of this review paper is to assist readers to study about current methods and barriers to enhance the accuracy in the output of the retinal fundus image..

PurposeTo assess the performance of deep learning algorithms for different tasks in retinal fundus images: (1) detection of retinal fundus images versus optical coherence tomography (OCT) or other images, (2) evaluation of good quality retinal fundus images, (3) distinction between right eye (OD) and left eye (OS) retinal fundus images,(4) detection of age-related macular degeneration (AMD) and (5) detection of referable glaucomatous optic neuropathy (GON).Patients and MethodsFive algorithms were designed. Retrospective study from a database of 306,302 images, Optretina’s tagged dataset. Three different ophthalmologists, all retinal specialists, classified all images. The dataset was split per patient in a training (80%) and testing (20%) splits. Three different CNN architectures were employed, two of which were custom designed to minimize the number of parameters with minimal impact on its accuracy. Main outcome measure was area under the curve (AUC) with accuracy, sensitivity and specificity.ResultsDetermination of retinal fundus image had AUC of 0.979 with an accuracy of 96% (sensitivity 97.7%, specificity 92.4%). Determination of good quality retinal fundus image had AUC of 0.947, accuracy 91.8% (sensitivity 96.9%, specificity 81.8%). Algorithm for OD/OS had AUC 0.989, accuracy 97.4%. AMD had AUC of 0.936, accuracy 86.3% (sensitivity 90.2% specificity 82.5%), GON had AUC of 0.863, accuracy 80.2% (sensitivity 76.8%, specificity 83.8%).ConclusionDeep learning algorithms can differentiate a retinal fundus image from other images. Algorithms can evaluate the quality of an image, discriminate between right or left eye and detect the presence of AMD and GON with a high level of accuracy, sensitivity and specificity.

BackgroundBrain volume measurement serves as a critical approach for assessing brain health status. Considering the close biological connection between the eyes and brain, this study aims to investigate the feasibility of estimating brain volume through retinal fundus imaging integrated with clinical metadata, and to offer a cost-effective approach for assessing brain health.MethodsBased on clinical information, retinal fundus images, and neuroimaging data derived from a multicenter, population-based cohort study, the KaiLuan Study, we proposed a cross-modal correlation representation (CMCR) network to elucidate the intricate co-degenerative relationships between the eyes and brain for 755 subjects. Specifically, individual clinical information, which has been followed up for as long as 12 years, was encoded as a prompt to enhance the accuracy of brain volume estimation. Independent internal validation and external validation were performed to assess the robustness of the proposed model. Root mean square error (RMSE), peak signal-to-noise ratio (PSNR), and structural similarity index measure (SSIM) metrics were employed to quantitatively evaluate the quality of synthetic brain images derived from retinal imaging data.ResultsThe proposed framework yielded average RMSE, PSNR, and SSIM values of 98.23, 35.78 dB, and 0.64, respectively, which significantly outperformed 5 other methods: multi-channel Variational Autoencoder (mcVAE), Pixel-to-Pixel (Pixel2pixel), transformer-based U-Net (TransUNet), multi-scale transformer network (MT-Net), and residual vision transformer (ResViT). The two- (2D) and three-dimensional (3D) visualization results showed that the shape and texture of the synthetic brain images generated by the proposed method most closely resembled those of actual brain images. Thus, the CMCR framework accurately captured the latent structural correlations between the fundus and the brain. The average difference between predicted and actual brain volumes was 61.36 cm3, with a relative error of 4.54%. When all of the clinical information (including age and sex, daily habits, cardiovascular factors, metabolic factors, and inflammatory factors) was encoded, the difference was decreased to 53.89 cm3, with a relative error of 3.98%. Based on the synthesized brain MR images from retinal fundus images, the volumes of brain tissues could be estimated with high accuracy.ConclusionsThis study provides an innovative, accurate, and cost-effective approach to characterize brain health status through readily accessible retinal fundus images.Trial registration No. NCT05453877 (https://clinicaltrials.gov/).Supplementary InformationThe online version contains supplementary material available at 10.1186/s40779-025-00630-2.

Accurate retinal vessel segmentation plays a vital role in the early detection and diagnosis of ophthalmologic dis- eases such as diabetic retinopathy, glaucoma, and hypertension. Traditional image processing and machine learning techniques often struggle to capture the fine vessel structures and complex variations present in retinal fundus images. To overcome these limitations, this study proposes a hybrid deep learning framework that combines Convolutional Neural Networks (CNNs) and Gen- erative Adversarial Networks (GANs) for precise retinal vessel segmentation. In the proposed method, the CNN component serves as the feature extractor, learning multi-scale spatial and contextual features from retinal images, while the GAN framework enhances segmentation accuracy by employing a discriminator network that distinguishes between real and generated vessel maps. This adversarial learning setup encourages the generator to produce vessel segmentations that closely resemble ground truth images. Additionally, preprocessing techniques such as contrast enhancement and noise reduction are applied to improve the visibility of retinal structures, and post-processing steps refine the vessel boundaries for higher accuracy. Experimental results on publicly available retinal image datasets, such as DRIVE and STARE, demonstrate that the pro- posed GAN-CNN model outperforms conventional CNN-based segmentation methods in terms of accuracy, sensitivity, specificity, and Dice coefficient. The system achieves robust performance even under varying illumination and noise conditions. These findings indicate that integrating adversarial learning with convolutional feature extraction can significantly enhance retinal vessel segmentation, paving the way for more efficient and automated retinal disease screening systems

In this research, retinal blood vessel fundus images will be segmented. Moreover, bifurcation point of the segmented blood vessel images will be determined. The data used for this research was obtained from fundus image database of DRIVE (Digital Retinal Images for Vessel Extraction) dataset. The preprocessing phases contain of several steps such as green channel extraction, histogram equalization and optic disc elimination. Meanwhile, the segmentation phase was performed by combining two filtering methods. These methods are median and derivative of Gaussian filter. Median filter was used to reduce the noise on retinal fundus image such as hard and soft exudates as well as dot and blot hemorrhages. Combination of these two filtering methods were also employed to determine the bifurcation point of segmented blood vessel image. The bifurcation points and the result from blood vessel segmentation were among two of the unique parameters of retinal fundus image. These parameters will be used eventually as unique features of the advanced research which is a biometric system to identify an individual based on his/her unique retinal pattern.