An OCT retinal image classification model based on improved ResNet-34 network

Microaneurysms (MAs) are pathognomonic signs that help clinicians to detect diabetic retinopathy (DR) in the early stages. Automatic detection of MA in retinal images is an active area of research due to its application in screening processes for DR which is one of the main reasons of blindness amongst the working-age population. The focus of these works is on the automatic detection of MAs in en face retinal images like fundus color and Fluorescein Angiography (FA). On the other hand, detection of MAs from Optical Coherence Tomography (OCT) images has 2 main advantages: first, OCT is a non-invasive imaging technique that does not require injection, therefore is safer. Secondly, because of the proven application of OCT in detection of Age-Related Macular Degeneration, Diabetic Macular Edema, and normal cases, thanks to detecting MAs in OCT, extensive information is obtained by using this imaging technique. In this research, the concentration is on the diagnosis of MAs using deep learning in the OCT images which represent in-depth structure of retinal layers. To this end, OCT B-scans should be divided into strips and MA patterns should be searched in the resulted strips. Since we need a dataset comprising OCT image strips with suitable labels and such large labelled datasets are not yet available, we have created it. For this purpose, an exact registration method is utilized to align OCT images with FA photographs. Then, with the help of corresponding FA images, OCT image strips are created from OCT B-scans in four labels, namely MA, normal, abnormal, and vessel. Once the dataset of image strips is prepared, a stacked generalization (stacking) ensemble of four fine-tuned, pre-trained convolutional neural networks is trained to classify the strips of OCT images into the mentioned classes. FA images are used once to create OCT strips for training process and they are no longer needed for subsequent steps. Once the stacking ensemble model is obtained, it will be used to classify the OCT strips in the test process. The results demonstrate that the proposed framework classifies overall OCT image strips and OCT strips containing MAs with accuracy scores of 0.982 and 0.987, respectively.

The use of intravitreal corticosteroids in the management of macular oedema has recently gained widespread acceptance. New long-acting steroid preparations and methods of delivery have facilitated the use of these new modalities. This review describes the various types of macular oedema for which this therapeutic option is used and the results.

Convolutional neural networks (CNN) have been successfully used in the classification of medical images. However, CNNs extract the features of the image, neglecting the spatial information between the objects since they evaluate each object separately and this makes it difficult to analyse images reliably. CapsNets partially overcomes these limitations by encapsulating the objects in the image and their feature parameters without losing the spatial information between objects. However, this advantage of CapsNet can become a disadvantage due to the fact that CapsNet stores a lot of information, which can lead to an increase in the number of parameters and the complexity of the network. In this study, a new method is proposed in which residual block and CBAM (Convolutional Block Attention Module) modules are used hybridly with CapsNet in order to classify medical images with high accuracy and reliability and, at the same time, to overcome this disadvantage of CapsNet by reducing the number of parameters. In this study, more features of the image are extracted by using the residual block instead of the convolutional layer of CapsNet. The attention mechanism is used to increase the effectiveness of important features and reduce the effect of unnecessary features. In addition, the residual block and CBAM module reduced the number of parameters in CapsNet by approximately 2 million. Brain tumour images and OCT (Optical Coherence Tomography) images were classified with the proposed model. The results of the study show that the proposed model achieves significant results when compared to other CapsNet-based studies in the literature.

Classifying retinal diseases is a complex problem because the early problematic areas of retinal disorders are quite small and conservative. In recent years, Transformer architectures have been successfully applied to solve various retinal related health problems. Age-related macular degeneration (AMD) and diabetic macular edema (DME), two prevalent retinal diseases, can cause partial or total blindness. Diseases therefore require an early and accurate detection. In this study, we proposed Vision Transformer (ViT), Tokens-To-Token Vision Transformer (T2T-ViT) and Mobile Vision Transformer (Mobile-ViT) algorithms to detect choroidal neovascularization (CNV), drusen, and diabetic macular edema (DME), and normal using optical coherence tomography (OCT) images. The predictive accuracies of ViT, T2T-ViT and Mobile-ViT achieved on the dataset for the classification of OCT images are 95.14%, 96.07% and 99.17% respectively. Experimental results obtained from ViT approaches showed that Mobile-ViT have superior performance with regard to classification accuracy in comparison with the others. Overall, it has been observed that ViT architectures have the capacity to classify with high accuracy in the diagnosis of retinal diseases.

Early diagnosis of eye diseases plays a critical role in treatment success and public health. With the widespread use of modern medical imaging methods, the development of automated diagnostic systems from retinal fundus images has become an important research area. In this study, the effects of integrating the Convolutional Block Attention Module (CBAM) into EfficientNetB0 and DenseNet121 architectures were investigated for the classification of cataract, diabetic retinopathy, glaucoma, and healthy subjects. Experimental results demonstrated that the CBAM attention mechanism enhances accuracy and generalization performance, particularly in distinguishing complex retinal findings. For DenseNet121, accuracy, precision, recall, and F1-score were obtained as 88.37%, 89.66%, 88.37%, and 88.52%, respectively. EfficientNetB0 achieved 96.32% accuracy, 96.34% precision, 96.32% recall, and 96.33% F1-score. After CBAM integration, the accuracy of DenseNet121 increased to 90.39% and its F1-score to 90.54%, while EfficientNetB0 improved to 96.56% accuracy and 96.57% F1-score. These results reveal that the incorporation of CBAM enhances the performance of deep learning models and significantly contributes to the development of reliable and clinically applicable systems for the automated detection of eye diseases

Retinal diseases are among the leading causes of blindness worldwide, requiring early detection for effective treatment. Manual interpretation of ophthalmic imaging, such as optical coherence tomography (OCT), is traditionally time-consuming, prone to inconsistencies, and requires specialized expertise in ophthalmology. This study introduces OculusNet, an efficient and explainable deep learning (DL) approach for detecting retinal diseases using OCT images. The proposed method is specifically tailored for complex medical image patterns in OCTs to identify retinal disorders, such as choroidal neovascularization (CNV), diabetic macular edema (DME), and age-related macular degeneration characterized by drusen. The model benefits from Saliency Map visualization, an Explainable AI (XAI) technique, to interpret and explain how it reaches conclusions when identifying retinal disorders. Furthermore, the proposed model is deployed on a web page, allowing users to upload retinal OCT images and receive instant detection results. This deployment demonstrates significant potential for integration into ophthalmic departments, enhancing diagnostic accuracy and efficiency. In addition, to ensure an equitable comparison, a transfer learning approach has been applied to four pre-trained models: VGG19, MobileNetV2, VGG16, and DenseNet-121. Extensive evaluation reveals that the proposed OculusNet model achieves a test accuracy of 95.48% and a validation accuracy of 98.59%, outperforming all other models in comparison. Moreover, to assess the proposed model's reliability and generalizability, the Matthews Correlation Coefficient and Cohen's Kappa Coefficient have been computed, validating that the model can be applied in practical clinical settings to unseen data.

Background: To design a novel anomaly detection and localization approach using artificial intelligence methods using optical coherence tomography (OCT) scans for retinal diseases. Methods: High-resolution OCT scans from the publicly available Kaggle dataset and a local dataset were used by four state-of-the-art self-supervised frameworks. The backbone model of all the frameworks was a pre-trained convolutional neural network (CNN), which enabled the extraction of meaningful features from OCT images. Anomalous images included choroidal neovascularization (CNV), diabetic macular edema (DME), and the presence of drusen. Anomaly detectors were evaluated by commonly accepted performance metrics, including area under the receiver operating characteristic curve, F1 score, and accuracy. Results: A total of 25,315 high-resolution retinal OCT slabs were used for training. Test and validation sets consisted of 968 and 4000 slabs, respectively. The best performing across all anomaly detectors had an area under the receiver operating characteristic of 0.99. All frameworks were shown to achieve high performance and generalize well for the different retinal diseases. Heat maps were generated to visualize the quality of the frameworks' ability to localize anomalous areas of the image. Conclusions: This study shows that with the use of pre-trained feature extractors, the frameworks tested can generalize to the domain of retinal OCT scans and achieve high image-level ROC-AUC scores. The localization results of these frameworks are promising and successfully capture areas that indicate the presence of retinal pathology. Moreover, such frameworks have the potential to uncover new biomarkers that are difficult for the human eye to detect. Frameworks for anomaly detection and localization can potentially be integrated into clinical decision support and automatic screening systems that will aid ophthalmologists in patient diagnosis, follow-up, and treatment design. This work establishes a solid basis for further development of automated anomaly detection frameworks for clinical use.

Retinal diseases become more complex for people at any age. In the early stages, many people suffering from retinal diseases have very mild symptoms. It is observed that retinal diseases mainly damage the blood vessels that cause the leakage of fluid. The accretion of fluid can impact the retina and cause vision changes. Retinal diseases such as diabetic retinopathy (DR), age-related macular degeneration (AMD), diabetic macular edema (DME), drusen, and choroidal neovascularization (CNV) are complex diseases that show a huge impact on human retinal health. If the patients are not detected with retinal diseases in the early stages, this may lead to permanent vision loss. These diseases have a lot of other side effects, such as brain disorders. Prevention of these diseases may stop permanent vision loss in patients. Machine learning (ML) algorithms are most widely used to detect retinal diseases in their early stages. The main disadvantage of ML is that these algorithms will take more time to process the data and select complex methods. In this paper, deep learning (DL) algorithms are discussed, and various optical coherence tomography (OCT) datasets are used for experiments. Experimental results show the performance of various ML and DL approaches applied to OCT and retinal image datasets. The performance and comparison of various algorithms is also discussed in this paper.

Optical coherence tomography (OCT) enables instant and direct imaging of morphological retinal tissue and has become an essential imaging modality for ophthalmology diagnosis. As one of the important morphological retinal characteristics, the structural information of retinal layers provides meaningful diagnostic information and is closely related to several retinal diseases. In this letter, we propose a novel layer guided convolutional neural network (LGCNN) to identify normal retina and three common types of macular pathologies, namely, diabetic macular edema, drusen, and choroidal neovascularization. Specifically, an efficient segmentation network is first employed to generate the retinal layer segmentation maps, which can delineate two lesion-related retinal layers associated with the meaningful retinal lesions. Then, two well-designed subnetworks in LGCNN are utilized to integrate the information of two lesion-related layers. Consequently, LGCNN can efficiently focus on the meaningful lesion-related layer regions to improve OCT classification. The experimental results conducted on two clinically acquired datasets demonstrate the effectiveness of the proposed method.

With the continuous development of deep learning technologies, fault prediction techniques based on various neural networks have been evolving. The deep learning modules based on U-Net residual networks have shown significant advantages in both learning efficiency and effectiveness. In this paper, we propose a deep learning model that integrates a 3D U-Net residual architecture, Convolutional Block Attention Module (CBAM), and Multi-scale Enhanced Global Attention (MEGA) module for automatic seismic fault detection and segmentation. This model can effectively handle complex 3D seismic data, fully exploiting both spatial and channel information, significantly improving the prediction accuracy for small faults, while only slightly increasing the computational cost.Firstly, the model uses the 3D U-Net as the backbone framework, where the residual blocks (BasicRes) extract features through multiple convolution layers. The CBAM module is incorporated to apply attention weighting, enhancing the model's ability to focus on critical information. The CBAM module combines channel attention and spatial attention, effectively adjusting the importance of feature maps from different dimensions, enabling the model to identify potential fault features in complex seismic data.Secondly, the MEGA module is introduced into the model, which further improves the model's feature representation ability by fusing multi-scale features and applying a global attention mechanism. By weighting global information, the MEGA module helps the model better capture key seismic fault features during feature fusion. This design allows the model to focus not only on local details but also to fully utilize the global contextual information in 3D data, thereby enhancing the accuracy of fault detection.After validation, the model achieved promising results in seismic fault detection tasks, automatically identifying and segmenting fault structures in seismic data. The accuracy was improved from 80% with the original 3D U-Net residual network to 85%-87%. This provides strong support for applications such as seismic exploration and subsurface imaging.Keywords: Seismic Fault Detection, 3D U-Net, Convolutional Block Attention Module (CBAM), Multi-scale Enhanced Global Attention (MEGA), Deep Learning

Diabetic retinopathy (DR), one of the most prevalent microvascular complications of diabetes, stands as a leading cause of vision loss globally. Due to its asymptomatic nature in early stages, delayed diagnosis and staging may result in irreversible visual impairment. Therefore, accurate and simultaneous lesion segmentation and stage classification of DR are of critical clinical importance. In this study, a two‐stage, end‐to‐end, holistic framework is proposed for automated DR diagnosis. In the first stage, an Improved U‐Net architecture enhanced with residual blocks and additional convolutional layers is employed to segment small and low‐contrast lesions such as microaneurysms, hemorrhages, and hard/soft exudates with high precision. Model hyperparameters are optimized using the harmony search algorithm to enhance training efficiency. In the second stage, lesion‐based weight maps obtained from the segmentation step are applied to fundus images from the APTOS dataset, generating enriched inputs for classification. A vision transformer (ViT)‐based model, augmented with a Convolutional Block Attention Module (CBAM), is utilized to improve feature extraction. In addition, features derived from ViT are further refined using a graph convolutional network (GCN) and traditional machine‐learning classifiers. The proposed approach achieves high performance in multi‐class DR stage classification. Compared to existing studies, the framework demonstrates notable improvements in both segmentation and classification accuracy, offering a robust and generalizable solution for DR diagnosis.

Retinal disease classification is a significant problem in computer-aided diagnosis (CAD) for medical applications. This paper is focused on a 4-class classification problem to automatically detect choroidal neovascularization (CNV), diabetic macular edema (DME), DRUSEN, and NORMAL in optical coherence tomography (OCT) images. The proposed classification algorithm adopted an ensemble of four classification model instances to identify retinal OCT images, each of which was based on an improved residual neural network (ResNet50). The experiment followed a patient-level 10-fold cross-validation process, on development retinal OCT image dataset. The proposed approach achieved 0.973 (95% confidence interval [CI], 0.971-0.975) classification accuracy, 0.963 (95% CI, 0.960-0.966) sensitivity, and 0.985 (95% CI, 0.983-0.987) specificity at the B-scan level, achieving a matching or exceeding performance to that of ophthalmologists with significant clinical experience. Other performance measures used in the study were the area under receiver operating characteristic curve (AUC) and kappa value. The observations of the study implied that multi-ResNet50 ensembling was a useful technique when the availability of medical images was limited. In addition, we performed qualitative evaluation of model predictions, and occlusion testing to understand the decision-making process of our model. The paper provided an analytical discussion on misclassification and pathology regions identified by the occlusion testing also. Finally, we explored the effect of the integration of retinal OCT images and medical history data from patients on model performance.

To evaluate the optical coherence tomographic (OCT) features of the retina of rats, we compared the OCT images with the histological appearance of normal retinas and retinas with laser-induced choroidal neovascularization. Twelve eyes of 12 adult pigmented rats (Brown-Norway) were used. Color fundus photography, fluorescein angiography (FAG), and OCT images of normal retinas and retinas with laser photocoagulation-induced choroidal neovascularization were studied. OCT showed a double-layered structure in the normal sensory retina with a highly reflective layer located in the inner retina and a low reflective layer located in the outer retina. The retinal pigment epithelium (RPE) and choriocapillaris were imaged as a layer with the highest reflection. On the first day after photocoagulation, OCT showed a disruption of the highly reflective layer corresponding to the RPE, and an enhanced reflectivity in the choroid under the lesion. Choroidal neovascularizations (CNVs) which appeared 2 weeks after photocoagulation was seen as a multi-layered, highly reflective area protruding from the RPE into the subretinal space A CNV beneath a subretinal hematoma was difficult to detect because of the low transmission of the scanning light through the hematoma. The histopathological appearance was well correlated with the OCT images. The two reflective bands in the OCT images were identified as coming from the inner layers of the retina and from the photoreceptors. The highest reflective band arose from the RPE and choriocapillaris. In the future, OCT combined with FAG or indocyanine-green angiography will be a useful tool for the evaluation of animal studies of choroidal neovascularization and other retinal diseases.

To investigate morphological variations in the macular area with optical coherence tomography (OCT) after vitrectomy for diabetic fibrovascular proliferation. We reviewed 108 cases using OCT 7-15 months after vitrectomy. Of these, 32 received OCT within 3 months postoperatively. Morphological variations were categorized and correlated with visual outcome. Only 24 cases (21.4%) had no obvious abnormalities. The most frequent findings were epiretinal membrane (52.8%), macular thickening (37.0%) and macular cysts (28.7%). Multivariate regression showed that diffuse macular thickening, loss of foveal depression and diffuse retinal thinning were significantly associated with poor visual acuity. Sequential OCT (< 3 and >or= 7 months) revealed that epiretinal membrane and oedema outside of fovea changed significantly between two examinations. OCT may identify diverse morphological changes in the macular area after diabetic vitrectomy for fibrovascular proliferation. Macular appearance may change over time, and certain types of morphological changes may be associated with poor visual function.

RETRACTED: Deep learning network (DL-Net) based classification and segmentation of multi-class retinal diseases using OCT scans