Mayfly optimization with deep learning enabled retinal fundus image classification model

Automated screening and diagnostic process in the healthcare sector improves services, reduces cost and labour. With the developments of machine learning (ML) and deep learning (DL) models, intelligent disease diagnosis models can be designed. Retinal fundus image classification using DL models becomes essential for the identification and classification of distinct retinal diseases. This article develops a salp swarm optimisation with deep transfer learning enabled retinal fundus image classification (SSODTL-RFIC) model. The proposed SSODTL-RFIC model examines the retinal fundus image for the existence of diseases. In addition, a median filtering (MF) approach is employed for the noise removal process and graph cut (GC) segmentation is applied. Besides, MobileNetv1 feature extractor is involved to produce feature vectors. Finally, SSO with cascade forward neural network (CFNN) model is applied for recognition and classification process. A widespread experimentation process is performed on benchmark datasets to examine the enhanced performance of the SSODTL-RFIC model, an extensive comparative examination pointed out the supremacy of the SSODTL-RFIC model over the recent approaches with maximum accuracy of 98.71% and 99.12% on the test ARIA and STARE datasets respectively.

BackgroundEarly diagnosis and treatment of diabetic eye disease (DED) improve prognosis and lessen the possibility of permanent vision loss. Screening of retinal fundus images is a significant process widely employed for diagnosing patients with DED or other eye problems. However, considerable time and effort are required to detect these images manually.MethodsDeep learning approaches in machine learning have attained superior performance for the binary classification of healthy and pathological retinal fundus images. In contrast, multi-class retinal eye disease classification is still a difficult task. Therefore, a two-phase transfer learning approach is developed in this research for automated classification and segmentation of multi-class DED pathologies.ResultsIn the first step, a Modified ResNet-50 model pre-trained on the ImageNet dataset was transferred and learned to classify normal diabetic macular edema (DME), diabetic retinopathy, glaucoma, and cataracts. In the second step, the defective region of multiple eye diseases is segmented using the transfer learning-based DenseUNet model. From the publicly accessible dataset, the suggested model is assessed using several retinal fundus images. Our proposed model for multi-class classification achieves a maximum specificity of 99.73%, a sensitivity of 99.54%, and an accuracy of 99.67%.

Diabetic retinopathy (DR) and age related macular degeneration (AMD) becomes widespread microvascular illness among diabetic patients. Traditional retinal fundus image classification requires visual inspection by the professionals, which is time consuming and requires expert's knowledge. Earlier identification of retinal diseases is essential to delay or avoid vision deterioration and vision loss. The recently developed artificial intelligence (AI) and deep learning (DL) models can be employed for accurate retinal image classification. With this motivation, this study designs a new artificial intelligence with optimal deep convolutional neural network (AI‐ODCNN) technique for retinal fundus image classification. Primarily, the proposed model uses the Gaussian Blur based noise removal and contrast enhancement technique (CLAHE) based contrast enhancement technique to pre‐process the retinal fundus image. In addition, morphology and contour based image segmentation is performed. Moreover, the deep CNN with RMSProp Optimizer is employed for retinal fundus image classification. A wide range of simulations was performed on the automated retinal image analysis and structured analysis of the retina and the outcomes are examined with respect to various measures. The simulation outcomes ensured the better performance of the proposed approach related to other recent algorithms with maximum accuracy of 96.47%.

Several types of eye diseases can lead to blindness, including glaucoma. For better diagnosis, retinal images should be assessed using advanced artificial intelligence techniques, which are used to identify a wide range of eye diseases. In this paper, support vector machine (SVM), random forest (RF), decision tree (DT), and convolutional neural network (CNN) methods are used to classify fundus retinal images of healthy and glaucomatous patients. This study tests various models on a small dataset of 30 high-resolution fundus retinal images. To classify these retinal images, the proposed CNN-based classifier achieved a classification accuracy of 80%. Furthermore, according to the confusion matrix, the proposed CNN model was 80% accurate for the healthy and glaucoma classes. In the glaucoma case, the CNN-based classifier proved superior to other classifiers based on the comparative analysis.

Several Deep Learning (DL) and medical image Machine Learning (ML) methods have been investigated for efficient data representations of medical images, such as image classification, Content-Based Image Retrieval (CBIR), and image segmentation. CBIR helps medical professionals make decisions by retrieving similar cases and images from electronic medical image databases. CBIR needs expressive data representations for similar image identification and knowledge discovery in massive medical image databases explored by distinct algorithmic methods. In this study, an Improved Whale Optimization Algorithm with Deep Learning-Driven Retinal Fundus Image Grading and Retrieval (IWOADL-RFIGR) approach was developed. The presented IWOADL-RFIGR method mainly focused on retrieving and classifying retinal fundus images. The proposed IWOADL-RFIGR method used the Bilateral Filtering (BF) method to preprocess the retinal images, a lightweight Convolutional Neural Network (CNN) based on scratch learning with Euclidean distance-based similarity measurement for image retrieval, and the Least Square Support Vector Machine (LS-SVM) model for image classification. Finally, the IWOA was used as a hyperparameter optimization technique to improve overall performance. The experimental validation of the IWOADL-RFIGR model on a benchmark dataset exhibited better performance than other models.

Convolutional Neural Networks (CNNs) have been established as a powerful class of models for image classification and related tasks. However, the fully-connected layers in CNN are not robust enough to serve as a classifier to discriminate deep convolutional features, due to the local minima problem of back-propagation. Kernel Extreme Learning Machines (KELMs), known as an outstanding classifier, can not only converge extremely fast but also ensure an outstanding generalization performance. In this paper, we propose a novel image classification framework, in which CNN and KELM are well integrated. In our work, Densely connected network (DenseNet) is employed as the feature extractor, while a radial basis function kernel ELM instead of linear fully connected layer is adopted as a classifier to discriminate categories of extracted features to promote the image classification performance. Experiments conducted on four publicly available datasets demonstrate the promising performance of the proposed framework against the state-of-the-art methods.

Automated crowd classification in aerial images finds it helpful to avoid crowd disaster in complicated situations of mass events. Earlier works have focused on crowd count and crowd density computation using regression models. But these models operate only if the proper manual count has existed for reference purposes. So, it is needed to determine the high density crowd in aerial images by the use of classification models. In this aspect, this study presents a new VGG16 with kernel extreme learning machine (KELM) model for high density crowd detection and classification. The proposed VGG16-KELM model primarily undergoes pre-processing step to boost the quality of the input images. Besides, VGG16 method was employed as a feature extractor which derives a useful group of feature vectors. In addition, KELM technique is applied as a classifier which determines the density of the crowd, shows the novelty of the work. For demonstrating the enhanced performance of the VGG16-KELM approach, a wide range of simulations were carried out and the results are assessed under several aspects. The experimental outcomes reported the enhanced performance of the VGG16-KELM technique on the other compared methods.

A deep neural network and machine learning approach for retinal fundus image classification

In the development of social economy and scientific and technological innovation, the image processing mode and classification model chosen by network technology platform is becoming more and more changeable, but in essence, it is necessary to obtain characteristic information in effective image recognition and choose high-quality network algorithm and processing technology to complete image processing and image classification. Therefore, on the basis of understanding the current research trend of computer image processing and image classification model methods, this paper conducts in-depth discussion on the image processing methods and image classification model training design with artificial intelligence as the core and takes the image classification model of transfer learning as an example for practical exploration. The final results show that the image processing method and image classification model based on artificial intelligence have strong performance advantages in practical application.KeywordsArtificial intelligenceImage processingImage classificationThe migration study

We introduce the Plant Disease Detection Platform (PDDP) that allows users to send photos of sick plant leaves or textual descriptions of their appearance to obtain information about an infection that hit the vegetation and treatment tips. The backend of the platform in terms of deep learning includes image classification and text similarity models. The image classification model has two parts: feature extractor and classifier. The feature extractor was trained using the triplet loss function along with transfer learning when the weights of the network are initialized from the MobileNetV2 pretrained on the ImageNet dataset. The classifier is a simple multilayer perceptron. The test on 100 random plant images from the Internet shows 98% of the classification accuracy. We did the post-training static quantization in order to reduce the overall model size and increase the inference performance. The final model has a size of 7 Mb and works 5 times faster than the initial model without significant loss of accuracy. The text similarity model is a BERT-based transformer for obtaining vector representation of input texts for further similarity calculation between user requests and disease descriptions on the PDDP.

Recently, number of medical X-ray images being generated is increasing rapidly due to the advancements in radiological equipment in medical centres. Medical X-ray image classification techniques are needed for effective decision making in the healthcare sector. Since the traditional image classification models are ineffective to accomplish maximum X-ray image classification performance, deep learning (DL) models have emerged. In this study, an Arithmetic Optimization Algorithm with Deep Learning-Based Medical X-Ray Image Classification (AOADL-MXIC) model has been developed. The proposed AOADL-MXIC model investigates the available X-ray images for the identification of diseases. Initially, the AOADL-MXIC model executes the pre-processing step using the Gabor filtering (GF) technique to eliminate the presence of noise. In the next level, the Capsule Network (CapsNet) model is utilized to derive feature vectors from the input X-ray images. Furthermore, for optimizing the hyperparameters related to the CapsNet approach, the AOA is exploited. Finally, the bidirectional gated recurrent unit (BiGRU) model is employed for the classification of medical X-ray images. The experimental result analysis of the AOADL-MXIC technique on a set of medical images stated the promising performance over the other models.KeywordsX-ray imagesArithmetic optimization algorithmDeep learningFeature extractionHyperparameter tuning

Autism spectrum disorder (ASD) is a complicated neurodevelopmental disorder. There is no definitive or easily interpretable medical test that aids in the early diagnosis of ASD, which leads to delays in its detection. In this study, we compared deep learning and traditional feature extraction methods used to detect ASD using retinal fundus images. The authors implemented convolutional neural networks (CNNs) such as ResNet50, EfficientNet, and vision transformers (ViTs), apart from the hybrid CNN + ViT model, for automated feature extraction. In addition, classic methods such as the gray level co-occurrence matrix for texture analysis, Frangi filters for measuring vessel density, and cup-to-disc ratio estimation were used to extract clinically relevant retinal features. To evaluate the discriminative power of the features obtained by each technique, classification models such as support vector machines, random forest, and XGBoost were implemented. Among the models used, hybrid CNN + ViT obtained the highest accuracy, which suggests that combining spatial and contextual retinal information enhances the detection of ASD. This study examined various feature extraction approaches in detail and elucidated the advantages of deep-learning-based approaches to enhance ASD diagnosis using retinal images. The results contribute to ongoing research on AI-supported ASD detection and provide crucial insights into the selection of optimal feature representation methods for future clinical applications. Received: 29 April 2025 | Revised: 14 July 2025 | Accepted: 18 July 2025 Conflicts of Interest The authors declare that they have no conflicts of interest to this work. Data Availability Statement Data are available on request from the corresponding author upon reasonable request. Author Contribution Statement Ayain John: Conceptualization, Methodology, Software, Formal analysis, Investigation, Resources, Data curation, Writing – original draft, Writing – review & editing, Visualization, Project administration. Santhanalakshmi S.: Validation, Formal analysis, Resources, Writing – review & editing, Supervision, Project administration.

Diabetic eye disease is a collection of ocular problems that affect patients with diabetes. Thus, timely screening enhances the chances of timely treatment and prevents permanent vision impairment. Retinal fundus images are a useful resource to diagnose retinal complications for ophthalmologists. However, manual detection can be laborious and time-consuming. Therefore, developing an automated diagnose system reduces the time and workload for ophthalmologists. Recently, the image classification using Deep Learning (DL) in between healthy or diseased retinal fundus image classification already achieved a state of the art performance. While the classification of mild and multi-class diseases remains an open challenge, therefore, this research aimed to build an automated classification system considering two scenarios: (i) mild multi-class diabetic eye disease (DED), and (ii) multi-class DED. Our model tested on various datasets, annotated by an opthalmologist. The experiment conducted employing the top two pretrained convolutional neural network (CNN) models on ImageNet. Furthermore, various performance improvement techniques were employed, i.e., fine-tune, optimization, and contrast enhancement. Maximum accuracy of 88.3% obtained on the VGG16 model for multi-class classification and 85.95% for mild multi-class classification.

Abstract. This paper reviews the application and improvement of convolutional neural networks (CNNs) in image classification. Firstly, a shallow CNN for interstitial lung disease image classification is presented. This model suppresses overfitting through a unique network architecture and optimisation algorithm. Next, the improved VGG16 architecture and MIDNet18 model are discussed and their superior performance in brain tumour image classification is demonstrated. Subsequently, a CNN-CapsNet model for cervical cancer image classification and its improvement are presented and the customised model is compared with the conventional VGG-16 CNN architecture in the paper. Next, the application of sparse convolutional kernels and hybrid sparse convolutional kernels (HDCs) in solving the problem of computational resource consumption is presented. Subsequently, methods for solving the problem of limited training data through transfer learning and network data augmentation techniques are discussed, as well as GAN-generated datasets for solving the overfitting problem. Finally, the effect of degraded images on the classification effectiveness of CNNs is explored. The results show that the improved CNN architecture and algorithms have significant effects in solving the problems of overfitting and computational resource consumption, and can significantly improve the accuracy and efficiency of image classification. And degraded images do adversely affect the accuracy of CNN for image classification.

The paper constructed a depression classification model based on emotionally related eye-movement data and kernel extreme learn machine (ELM). In order to improve the classification ability of the model, we use particle swarm optimization (PSO) to optimize the model parameters (regularization coefficient C and the parameter σ in the kernel function). At the same time, in order to avoid to be caught in the local optimum and improve PSO's searching ability, we use improved chaotic PSO optimization algorithm and Gauss mutation strategy to increase PSO's particle diversity. The classification results show that the accuracy, sensitivity and specificity of classification models without parameter optimization and Gauss mutation strategy are 80.23%, 80.31% and 79.43%, respectively, while those results of classification model using improved chaotic projection model and Gauss mutation strategy are improved to 88.55%, 87.71% and 89.42%, respectively. Compared with other classification methods of depression, the proposed classification method has better performance on depression recognition.