Computational aspects of deep learning models for detection of eye retina abnormalities

PurposeTo validate the performance of a commercially available, CE‐certified deep learning (DL) system, RetCAD v.1.3.0 (Thirona, Nijmegen, The Netherlands), for the joint automatic detection of diabetic retinopathy (DR) and age‐related macular degeneration (AMD) in colour fundus (CF) images on a dataset with mixed presence of eye diseases.MethodsEvaluation of joint detection of referable DR and AMD was performed on a DR‐AMD dataset with 600 images acquired during routine clinical practice, containing referable and non‐referable cases of both diseases. Each image was graded for DR and AMD by an experienced ophthalmologist to establish the reference standard (RS), and by four independent observers for comparison with human performance. Validation was furtherly assessed on Messidor (1200 images) for individual identification of referable DR, and the Age‐Related Eye Disease Study (AREDS) dataset (133 821 images) for referable AMD, against the corresponding RS.ResultsRegarding joint validation on the DR‐AMD dataset, the system achieved an area under the ROC curve (AUC) of 95.1% for detection of referable DR (SE = 90.1%, SP = 90.6%). For referable AMD, the AUC was 94.9% (SE = 91.8%, SP = 87.5%). Average human performance for DR was SE = 61.5% and SP = 97.8%; for AMD, SE = 76.5% and SP = 96.1%. Regarding detection of referable DR in Messidor, AUC was 97.5% (SE = 92.0%, SP = 92.1%); for referable AMD in AREDS, AUC was 92.7% (SE = 85.8%, SP = 86.0%).ConclusionThe validated system performs comparably to human experts at simultaneous detection of DR and AMD. This shows that DL systems can facilitate access to joint screening of eye diseases and become a quick and reliable support for ophthalmological experts.

Making computer detect desired object have always been an area of interest for humans. Object detection can be implemented using following stages: feature extraction, object localization followed by identifying object in input image. Most of the present-day object detection work is focused around x86 and ARM architectures. Researchers constantly strive to either identify better object detection architectures, updated models, improved model accuracies or reduce prediction time. In this paper, multiple pre-trained Deep Neural Network (DNN) models such as Region Based Convolutional Neural Network (RCNN), Fast RCNN, Faster RCNN. You Only Look Once (YOLO) V3 and Single Shot Multibox Detector (SSD) are used to identify fruits in given input image on RISC- V architecture. In order to bring uniformity across all DNN models, all these models are pre-trained on COCO datasets. Experimental results have shown that out of various DNN models tested for object recognition, YOLO and SSD-MobileNet gives optimum performance in terms of accuracy and inference time on RISC- V architecture.

Optical coherence tomography (OCT) imaging is a well-known technology for visualizing retinal layers and helps ophthalmologists to detect possible diseases. Accurate and early diagnosis of common retinal diseases can prevent the patients from suffering critical damages to their vision. Computer-aided diagnosis (CAD) systems can significantly assist ophthalmologists in improving their examinations. This paper presents a new enhanced deep ensemble convolutional neural network for detecting retinal diseases from OCT images. Our model generates rich and multi-resolution features by employing the learning architectures of two robust convolutional models. Spatial resolution is a critical factor in medical images, especially the OCT images that contain tiny essential points. To empower our model, we apply a new post-architecture model to our ensemble model for enhancing spatial resolution learning without increasing computational costs. The introduced post-architecture model can be deployed to any feature extraction model to improve the utilization of the feature map’s spatial values. We have collected two open-source datasets for our experiments to make our models capable of detecting six crucial retinal diseases: Age-related Macular Degeneration (AMD), Central Serous Retinopathy (CSR), Diabetic Retinopathy (DR), Choroidal Neovascularization (CNV), Diabetic Macular Edema (DME), and Drusen alongside the normal cases. Our experiments on two datasets and comparing our model with some other well-known deep convolutional neural networks have proven that our architecture can increase the classification accuracy up to 5%. We hope that our proposed methods create the next step of CAD systems development and help future researches.

Split computing: DNN inference partition with load balancing in IoT-edge platform for beyond 5G

The paper "Detection of Retinal Disease Using Convolutional Neural Networks" focuses on leveraging deep learning techniques for the early detection of retinal degeneration. Retinal diseases such as age-related macular degeneration (AMD), retinal detachment, diabetic retinopathy (DR), retinitis pigmentosa, and retinoblastoma can result in severe vision loss. Automated recognition of these pathologies is of outmost importance for early diagnosis and cure. There are various methods developed in history for automatic segmentation and detection of retinal landmarks and diseases. But, modern deep learning technology and advanced imaging tools in the field of ophthalmology have given new areas for investigation. This inquiry introduces two deep neural networks (DNN) as the primary research- the Multilayer Convolutional Neural Network (CNN) and AlexNet for the detection of retinal degeneration. The scientists play with the sensitivity of the neural networks by applying the three different optimizers—ADAM, RMSProp, and SGDM—to the fundus images and the results are analyzed at three different training rates for these neural networks. The write-up aims at insignificantly different things from CNNs which are image-based pattern recognition, and their layered structure which consists of an input layer, an output, and a hidden layer. Each layer accomplishes the operations of linear and non-linear, getting the details correct from the images. On the contrary, the combination of fully connected layers with convolutional layers was used in AlexNet, a very comprehensive approach. The research makes it absolutely clear that optimization procedures play a key role in this kind of network because the use of RMSProp usually provides the best performance. Key Words: Retinal diseases, Convolutional Neural Networks (CNN), Retina images, Disease detection, Medical image analysis.

The detection of diabetic retinopathy (DR) is challenging, as the current diagnostic methods rely heavily on the expertise of specialists and require the mass screening of diabetic patients. The prevalence of avoidable vision impairment due to DR necessitates the exploration of alternative diagnostic techniques. Specifically, it is necessary to develop reliable automatic methods to enable the early diagnosis and detection of DR from optical images. To address the lack of such methods, this research focused on employing various pre-trained deep neural networks (DNNs) and statistical metrics to provide an automatic framework for detecting DR in optical images. The receiver operating characteristic (ROC) was employed to examine the performance of each network. Ethically obtained real datasets were utilized to validate and enhance the robustness of the proposed detection framework. The experimental results showed that, in terms of the overall performance in DR detection, ResNet-50 was the best, followed by GoogleNet, with 99.44% sensitivity, while they were similar in terms of accuracy (93.56%). ResNet-50 outperformed GoogleNet in terms of the specificity (89.74%) and precision (90.07%) of DR detection. The ROC curves of both ResNet-50 and GoogleNet yielded optimal results, followed by SqueezeNet. MobileNet-v2 showed the weakest performance in terms of the ROC, while all networks showed negligible errors in diagnosis and detection. These results show that the automatic detection and diagnosis framework for DR is a promising tool enabling doctors to diagnose DR early and save time. As future directions, it is necessary to develop a grading algorithm and to explore other strategies to further improve the automatic detection and diagnosis of DR and integrate it into digital slit lamp machines.

A comparative evaluation of deep convolutional neural network and deep neural network-based land use/land cover classifications of mining regions using fused multi-sensor satellite data

Advancing diabetic retinopathy diagnosis with fundus imaging: A comprehensive survey of computer-aided detection, grading and classification methods

Retinal image analysis for disease screening through local tetra patterns

The most common retinal diseases that are to be diagnosed are Diabetic Retinopathy (DR), Age-related Macular Degeneration (AMD) and Choroidal Neovascularization (CNV). For the people above 60 years of age, detection of these retinal diseases is an important task for treatment that reduces the risk of vision loss. Retinal fundus images play a significant role in the detection of DR, AMD and CNV disease diagnosis and treatment. The existing techniques for the detection of DR, AMD and CNV have not fulfilled with the classification accuracy of the retinal diseases effectively. This research work proposes an efficient classification framework for retinal fundus image recognition to overcome these drawbacks. Initially, the input image from the publicly available STARE database is preprocessed with the following three steps (a) Specular reflection removal and smoothing, (b) contrast enhancement and (c) retinal region expansion. With the preprocessed image, the features are extracted using Multi-Scale Discriminative Robust Local Binary Pattern (MS-DRLBP), based on RGB component selection, Gradient operation, and LBP descriptor. Finally, classification was done using hybrid Convolution Neural Network (CNN) and Radial Basis Function (RBF) model (CNN-RBF) which classifies the retinal fundus images into four classes such as DR, AMD, CNV and Normal (NR). Experimental results of the proposed method gives an accuracy of 97.22% compared with the existing other methodologies.

Deep neural networks (DNNs) are utilized in numerous image processing, object detection, and video analysis tasks and need to be implemented using hardware accelerators to achieve practical speed. Logic locking is one of the most popular methods for preventing chip counterfeiting. Nevertheless, existing logic-locking schemes need to sacrifice the number of input patterns leading to wrong output under incorrect keys to resist the powerful satisfiability (SAT)-attack. Furthermore, DNN model inference is fault-tolerant. Hence, using a wrong key for those SAT-resistant logic-locking schemes may not affect the accuracy of DNNs. This makes the previous SAT-resistant logic-locking scheme ineffective on protecting DNN accelerators. Besides, to prevent DNN models from being illegally used, the models need to be obfuscated by the designers before they are provided to end-users. Previous obfuscation methods either require long time to retrain the model or leak information about the model. This paper proposes a joint protection scheme for DNN hardware accelerators and models. The DNN accelerator is modified using a hardware key (Hkey) and a model key (Mkey). Different from previous logic locking, the Hkey, which is used to protect the accelerator, does not affect the output when it is wrong. As a result, the SAT attack can be effectively resisted. On the other hand, a wrong Hkey leads to substantial increase in memory accesses, inference time, and energy consumption and makes the accelerator unusable. A correct Mkey can recover the DNN model that is obfuscated by the proposed method. Compared to previous model obfuscation schemes, our proposed method avoids model retraining and does not leak model information.

- Diabetic Retinopathy (DR) is a severe complication of diabetes that affects the retina and can lead to vision loss if not detected early. Automated DR classification using artificial intelligence has gained significant attention due to the limitations of manual diagnosis. Traditional machine learning approaches, such as the K-Nearest Neighbour (KNN) algorithm, have been widely used for DR classification, leveraging distance-based similarity measures for image classification. However, KNN struggles with high-dimensional medical image data, leading to suboptimal accuracy, longer computational time, and sensitivity to noise. To overcome these limitations, this study proposes a Deep Neural Network (DNN)-based framework for the automated detection and classification of Diabetic Retinopathy using retinal images. The model integrates Convolutional Neural Networks (CNNs) for feature extraction and a fully connected DNN for classification, ensuring efficient learning of spatial features and robust decision making. The proposed method is evaluated on publicly available DR datasets, achieving higher accuracy, sensitivity, and specificity compared to traditional KNN-based approaches. Results demonstrate that DNN outperforms KNN in handling complex retinal features, reducing false positive rates, and enhancing early-stage DR detection. This study highlights the potential of deep learning in enhancing clinical decision support systems, providing an accurate and scalable solution for automated DR screening. Future work may involve hybrid models combining deep learning with explainable AI techniques to improve interpretability and clinical adoption. Key Words: Diabetic Retinopathy, Deep Neural Networks (DNN), Convolutional Neural Networks (CNN), K-Nearest Neighbour (KNN), Performance metrics.

Corona viruses are a type of virus with a large family which can cause several terrible and devastating infectious diseases like middle east respiratory syndrome and severe acute respiratory syndrome. The first task of the authority is to screen as many people as possible to detect COVID-19 patients which arises the challenge of rapid screening. Although polymerase chain reaction(PCR) tests are primarily used for the COVID-19 test but because of it's high false negative results and need of experts leading to an alternative diagnostic system based on radiological images like chest X-ray. Moreover, computer aided diagnosis systems from radiography images has significantly been advanced during the last decade with promising efficiency which can overcome the need of both time and experts. In this case, machine learning(ML) and deep learning(DL) based screening techniques can provide automated, fast and reliable results. Therefore, many researchers have proposed several deep neural network(DNN) models for rapid screening of COVID-19 using chest X-ray images. Nevertheless, the vulnerability issue DNN models are overlooked or poorly evaluated in the COVID-19 screening. DNN models are remarkably vulnerable to perturbation which is addressed universal adversarial perturbation (UAP). UAP can falsely influence a DNN model and can eventually lead to going wrong in most of the classification problems. Here, we experimented and evaluated the performance of several DNN based automated COVID-19 diagnostic models, and investigated the robustness of these models against two types of adversarial attack:non targeted and targeted. We showed that DNN based COVID-19 detection models are highly vulnerable to adversarial attack and it is substantially important to be aware of the risk factors of DNN models before deploying for real life applications.

Diabetic retinopathy (DR) is an age-related macular degeneration eye disease problem that causes pathological changes in the retinal neural and vascular system. Recently, fundus imaging is a popular technology and widely used for clinical diagnosis, diabetic retinopathy, etc. It is evident from the literature that image quality changes due to uneven illumination, pigmentation level effect, and camera sensitivity affect clinical performance, particularly in automated image analysis systems. In addition, low-quality retinal images make the subsequent precise segmentation a challenging task for the computer diagnosis of retinal images. Thus, in order to solve this issue, herein, we proposed an adaptive enhancement-based Deep Convolutional Neural Network (DCNN) model for diabetic retinopathy (DR). In our proposed model, we used an adaptive gamma enhancement matrix to optimize the color channels and contrast standardization used in images. The proposed model integrates quantile-based histogram equalization to expand the perceptibility of the fundus image. Our proposed model provides a remarkable improvement in fundus color images and can be used particularly for low-contrast quality images. We performed several experiments, and the efficiency is evaluated using a large public dataset named Messidor’s. Our proposed model efficiently classifies a distinct group of retinal images. The average assessment score for the original and enhanced images is 0.1942 (standard deviation: 0.0799), Peak Signal-to-Noise Ratio (PSNR) 28.79, and Structural Similarity Index (SSIM) 0.71. The best classification accuracy is , indicating that Convolutional Neural Networks (CNNs) and transfer learning are superior to traditional methods. The results show that the proposed model increases the contrast of a particular color image without altering its structural information.

The high-pace rise in advanced computing and imaging systems has given rise to a new research dimension called computer-aided diagnosis (CAD) system for various biomedical purposes. CAD-based diabetic retinopathy (DR) can be of paramount significance to enable early disease detection and diagnosis decision. Considering the robustness of deep neural networks (DNNs) to solve highly intricate classification problems, in this paper, AlexNet DNN, which functions on the basis of convolutional neural network (CNN), has been applied to enable an optimal DR CAD solution. The DR model applies a multilevel optimization measure that incorporates pre-processing, adaptive-learning-based Gaussian mixture model (GMM)-based concept region segmentation, connected component-analysis-based region of interest (ROI) localization, AlexNet DNN-based highly dimensional feature extraction, principle component analysis (PCA)- and linear discriminant analysis (LDA)-based feature selection, and support-vector-machine-based classification to ensure optimal five-class DR classification. The simulation results with standard KAGGLE fundus datasets reveal that the proposed AlexNet DNN-based DR exhibits a better performance with LDA feature selection, where it exhibits a DR classification accuracy of 97.93% with FC7 features, whereas with PCA, it shows 95.26% accuracy. Comparative analysis with spatial invariant feature transform (SIFT) technique (accuracy-94.40%) based DR feature extraction also confirms that AlexNet DNN-based DR outperforms SIFT-based DR.