{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T01:15:24Z","timestamp":1789175724950,"version":"build-2803163510"},"reference-count":66,"publisher":"Public Library of Science (PLoS)","issue":"5","license":[{"start":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T00:00:00Z","timestamp":1778457600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Convolutional Neural Networks (CNNs) require a larger amount of input samples and computing resources to learn discriminative features for accurate identification of multiple retinal conditions, making the development and deployment of such models challenging on limited computing resources. This study presents a robust CNN (called LiteFeatNet) that requires fewer trainable parameters, computational resources, and processing time for accurate prediction. To enhance robustness and reduce computational time, a pre-trained NASNetMobile backbone is employed, and a method for time-efficient discriminative feature extraction from deep intermediate layers is proposed. The extracted features are refined using a spatially-aware feature map reduction module and classified using a custom classification module with fewer number of trainable parameters, reduced computational resource requirements, and computational time. Experiments are conducted using 1824 images from three distinct class labels in the Retinal Fundus Multi-Disease Image Dataset (RFMiD), with a 60:20:20 train-validation-test split. The LiteFeatNet architecture has a compact size (19.87 MB) and was trained using a standard pre-processing pipeline and training configurations. It outperformed twelve state-of-the-art models, achieving the highest testing accuracy of 90.33%, precision of 90.69%, recall of 90.33%, and F1-score of 90.27%, with a fast, impressive inference time of 4 milliseconds per image. Further, a generalizability study was also conducted using an external dataset, RFMiD 2.0, and the LiteFeatNet achieved competitive performance with quicker testing time compared to other architectures. To evaluate the scalability and adaptability of our proposed integrated framework for larger multi-class problems, we assessed the scalability by increasing class label complexity using two additional disease categories. Results validated the effectiveness and computational efficiency of this integrated framework compared with 9 baseline architectures. An ablation study was also conducted using the LiteFeatNet and two top-performing transfer learning architectures to validate that the synergistic combination of deep feature extraction and feature map refinement is the primary design decision behind the success of the LiteFeatNet architecture. The evaluation metrics, thus obtained, strongly suggest that the proposed LiteFeatNet is lightweight, fast, and robust, rendering it suitable for deployment in low-resource clinical settings.<\/jats:p>","DOI":"10.1371\/journal.pone.0347867","type":"journal-article","created":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T17:32:03Z","timestamp":1778520723000},"page":"e0347867","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":1,"title":["LiteFeatNet: A parameter-efficient and performance-centric deep learning model for multi-ocular disease identification using intermediate feature reduction from fundus images"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-4784-3011","authenticated-orcid":true,"given":"Usman","family":"Rafi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qamar","family":"Nawaz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad Ahsan","family":"Latif","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aisha","family":"Khatoon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,5,11]]},"reference":[{"key":"pone.0347867.ref001","article-title":"The Lancet Global Health Commission on Global Eye Health: vision beyond 2020","volume":"9","author":"MJ Burton","year":"2021","journal-title":"Lancet Glob Heal"},{"key":"pone.0347867.ref002","doi-asserted-by":"crossref","first-page":"2125","DOI":"10.1007\/s40123-024-00981-4","article-title":"Retina fundus photograph-based artificial intelligence algorithms in medicine: A systematic review","volume":"13","author":"A Grzybowski","year":"2024","journal-title":"Ophthalmol Ther"},{"key":"pone.0347867.ref003","doi-asserted-by":"crossref","DOI":"10.7717\/peerj-cs.1995","article-title":"DenseHillNet: a lightweight CNN for accurate classification of natural images","volume":"10","author":"SM Saqib","year":"2024","journal-title":"PeerJ Comput Sci"},{"key":"pone.0347867.ref004","doi-asserted-by":"crossref","first-page":"2190","DOI":"10.1016\/j.procs.2025.04.469","article-title":"Diabetic Retinopathy Detection Using Smartphone Fundoscopy: Advancing Healthcare Equity through Intelligent Edge Computing","volume":"258","author":"V L","year":"2025","journal-title":"Procedia Computer Science"},{"key":"pone.0347867.ref005","doi-asserted-by":"crossref","first-page":"109914","DOI":"10.1016\/j.knosys.2022.109914","article-title":"MobyDeep: A lightweight CNN architecture to configure models for text classification","volume":"257","author":"R Romero","year":"2022","journal-title":"Knowledge-Based Systems"},{"key":"pone.0347867.ref006","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1007\/s10791-026-10021-3","article-title":"A comprehensive review of lightweight deep learning models for edge computing with future directions","volume":"29","author":"N Lai","year":"2026","journal-title":"Discov Comput"},{"key":"pone.0347867.ref007","doi-asserted-by":"crossref","first-page":"97322","DOI":"10.1109\/ACCESS.2025.3572471","article-title":"A Low-Cost AI-Powered System for Early Detection of Diabetic Retinopathy and Ocular Diseases in Resource Limited Settings","volume":"13","author":"H Vohra","year":"2025","journal-title":"IEEE Access"},{"issue":"5","key":"pone.0347867.ref008","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0216492","article-title":"A comprehensive study capturing vision loss burden in Pakistan (1990-2025): Findings from the Global Burden of Disease (GBD) 2017 study","volume":"14","author":"B Hassan","year":"2019","journal-title":"PLoS One"},{"issue":"1","key":"pone.0347867.ref009","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1186\/s12910-023-00929-6","article-title":"Should Artificial Intelligence be used to support clinical ethical decision-making? A systematic review of reasons","volume":"24","author":"L Benzinger","year":"2023","journal-title":"BMC Med Ethics"},{"issue":"5","key":"pone.0347867.ref010","doi-asserted-by":"crossref","first-page":"535","DOI":"10.3390\/brainsci12050535","article-title":"Transfer Learning-Based Model for Diabetic Retinopathy Diagnosis Using Retinal Images","volume":"12","author":"MK Jabbar","year":"2022","journal-title":"Brain Sci"},{"key":"pone.0347867.ref011","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1007\/s44196-024-00520-w","article-title":"Deep transfer learning-based automated diabetic retinopathy detection using retinal fundus images in remote areas","volume":"17","author":"A Jabbar","year":"2024","journal-title":"Int J Comput Intell Syst"},{"issue":"1","key":"pone.0347867.ref012","doi-asserted-by":"crossref","first-page":"4633","DOI":"10.1038\/s41598-024-82241-w","article-title":"A comprehensive analysis of deep learning and transfer learning techniques for skin cancer classification","volume":"15","author":"M Shakya","year":"2025","journal-title":"Sci Rep"},{"issue":"12","key":"pone.0347867.ref013","article-title":"A lightweight CNN model for pepper leaf disease recognition in a human palm background","volume":"10","author":"Y Fu","year":"2024","journal-title":"Heliyon"},{"key":"pone.0347867.ref014","doi-asserted-by":"crossref","first-page":"1412988","DOI":"10.3389\/fpls.2024.1412988","article-title":"CSXAI: a lightweight 2D CNN-SVM model for detection and classification of various crop diseases with explainable AI visualization","volume":"15","author":"RH Prince","year":"2024","journal-title":"Front Plant Sci"},{"key":"pone.0347867.ref015","doi-asserted-by":"crossref","first-page":"100452","DOI":"10.1016\/j.array.2025.100452","article-title":"An improved deep learning approach for automated detection of multiclass eye diseases","volume":"27","author":"F Ghislain","year":"2025","journal-title":"Array"},{"key":"pone.0347867.ref016","unstructured":"Qasim DK, Jebur SA, Ali LR, Khalaf AJM, Hussain AJ. Lightweight Convolutional Neural Networks for Retinal Disease Classification. https:\/\/arxiv.org\/abs\/2506.03186. 2025."},{"issue":"7","key":"pone.0347867.ref017","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0307317","article-title":"A deep learning framework for the early detection of multi-retinal diseases","volume":"19","author":"S Ejaz","year":"2024","journal-title":"PLoS One"},{"key":"pone.0347867.ref018","doi-asserted-by":"crossref","first-page":"20552076251328120","DOI":"10.1177\/20552076251328120","article-title":"Fundus image classification using feature concatenation for early diagnosis of retinal disease","volume":"11","author":"S Ejaz","year":"2025","journal-title":"Digit Health"},{"key":"pone.0347867.ref019","doi-asserted-by":"crossref","first-page":"56170","DOI":"10.1109\/ACCESS.2023.3281859","article-title":"Multi-Class Retinal Diseases Detection Using Deep CNN With Minimal Memory Consumption","volume":"11","author":"A Nawaz","year":"2023","journal-title":"IEEE Access"},{"key":"pone.0347867.ref020","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1186\/s44147-023-00335-0","article-title":"Automatic multi-disease classification on retinal images using multilevel glowworm swarm convolutional neural network","volume":"71","author":"R Chavan","year":"2024","journal-title":"J Eng Appl Sci"},{"key":"pone.0347867.ref021","doi-asserted-by":"crossref","first-page":"2607","DOI":"10.32604\/iasc.2023.034041","article-title":"Convolutional neural network-based classification of multiple retinal diseases using fundus images","volume":"36","author":"A Aslam","year":"2023","journal-title":"Intell Autom & Soft Comput"},{"key":"pone.0347867.ref022","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s41666-024-00182-5","article-title":"A low complexity efficient deep learning model for automated retinal disease diagnosis","volume":"9","author":"SS Chowa","year":"2025","journal-title":"J Healthc Informatics Res"},{"key":"pone.0347867.ref023","doi-asserted-by":"crossref","DOI":"10.3389\/fcomp.2023.1252295","article-title":"Deep learning-based classification of eye diseases using convolutional neural network for OCT images","volume":"5","author":"M Elkholy","year":"2024","journal-title":"Front Comput Sci"},{"key":"pone.0347867.ref024","doi-asserted-by":"crossref","first-page":"101632","DOI":"10.1016\/j.imu.2025.101632","article-title":"DeB5-XNet: An explainable ensemble model for ocular disease classification using feature extraction and Grad-CAM","volume":"54","author":"G Kher","year":"2025","journal-title":"Informatics in Medicine Unlocked"},{"key":"pone.0347867.ref025","doi-asserted-by":"crossref","first-page":"13","DOI":"10.4186\/ej.2024.28.7.13","article-title":"Diabetic retinopathy classification: performance evaluation of pre-trained lightweight CNN using imbalance dataset","volume":"28","author":"PK Das","year":"2024","journal-title":"Eng J"},{"issue":"6","key":"pone.0347867.ref026","doi-asserted-by":"crossref","first-page":"45","DOI":"10.5755\/j02.eie.38674","article-title":"A Mobile Deep Learning Classification Model for Diabetic Retinopathy","volume":"30","author":"D Rimaru","year":"2024","journal-title":"ELEKTRON ELEKTROTECH"},{"issue":"2","key":"pone.0347867.ref027","doi-asserted-by":"crossref","DOI":"10.3390\/healthcare11020212","article-title":"A deep learning-based framework for retinal disease classification","volume":"11","author":"A Choudhary","year":"2023","journal-title":"Healthcare"},{"key":"pone.0347867.ref028","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1007\/s42452-025-06565-6","article-title":"Detection of retinal diseases from OCT images using a VGG16 and transfer learning","volume":"7","author":"WJ Jaimes","year":"2025","journal-title":"Discov Appl Sci"},{"key":"pone.0347867.ref029","doi-asserted-by":"crossref","first-page":"106907","DOI":"10.1016\/j.bspc.2024.106907","article-title":"DIA-VXNET: A framework for automated diabetic eye disease detection using transfer learning with feature fusion network","volume":"100","author":"MN Hasan","year":"2025","journal-title":"Biomedical Signal Processing and Control"},{"issue":"7","key":"pone.0347867.ref030","doi-asserted-by":"crossref","DOI":"10.3390\/info16070593","article-title":"Hybrid deep learning model for improved glaucoma diagnostic accuracy","volume":"16","author":"N Flores","year":"2025","journal-title":"Information"},{"issue":"1","key":"pone.0347867.ref031","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1186\/s12938-019-0649-y","article-title":"CNNs for automatic glaucoma assessment using fundus images: an extensive validation","volume":"18","author":"A Diaz-Pinto","year":"2019","journal-title":"Biomed Eng Online"},{"issue":"1","key":"pone.0347867.ref032","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1167\/iovs.17-22617","article-title":"A Deep Learning Approach to Digitally Stain Optical Coherence Tomography Images of the Optic Nerve Head","volume":"59","author":"SK Devalla","year":"2018","journal-title":"Invest Ophthalmol Vis Sci"},{"key":"pone.0347867.ref033","doi-asserted-by":"crossref","first-page":"1551315","DOI":"10.3389\/fmed.2025.1551315","article-title":"A lightweight multi-deep learning framework for accurate diabetic retinopathy detection and multi-level severity identification","volume":"12","author":"A Zafar","year":"2025","journal-title":"Front Med (Lausanne)"},{"key":"pone.0347867.ref034","doi-asserted-by":"crossref","first-page":"79793","DOI":"10.1109\/ACCESS.2025.3566073","article-title":"EffNet-SVM: A Hybrid Model for Diabetic Retinopathy Classification Using Retinal Fundus Images","volume":"13","author":"KV Naveen","year":"2025","journal-title":"IEEE Access"},{"issue":"1","key":"pone.0347867.ref035","doi-asserted-by":"crossref","first-page":"15166","DOI":"10.1038\/s41598-025-99309-w","article-title":"A hybrid deep learning framework for early detection of diabetic retinopathy using retinal fundus images","volume":"15","author":"M Sushith","year":"2025","journal-title":"Sci Rep"},{"issue":"8","key":"pone.0347867.ref036","doi-asserted-by":"crossref","first-page":"275","DOI":"10.3390\/jimaging11080275","article-title":"A Lightweight CNN for Multiclass Retinal Disease Screening with Explainable AI","volume":"11","author":"AKB Arnob","year":"2025","journal-title":"J Imaging"},{"key":"pone.0347867.ref037","doi-asserted-by":"crossref","unstructured":"Mowla N, Mowla MdN, Rabie K, Alsinglawi B. A Lightweight Deep Learning Model for Retinopathy of Prematurity Classification in eHealth Applications. In: 2025 International Wireless Communications and Mobile Computing (IWCMC). 2025;227\u201332. https:\/\/doi.org\/10.1109\/iwcmc65282.2025.11059591","DOI":"10.1109\/IWCMC65282.2025.11059591"},{"key":"pone.0347867.ref038","doi-asserted-by":"crossref","unstructured":"Pachade S, Porwal P, Thulkar D, Kokare M, Deshmukh G, Sahasrabuddhe V. Retinal fundus multi-disease image dataset (RFMiD): A dataset for multi-disease detection research. 2021. https:\/\/www.mdpi.com\/2306-5729\/6\/2\/14","DOI":"10.3390\/data6020014"},{"key":"pone.0347867.ref039","doi-asserted-by":"crossref","unstructured":"Pachade S, Porwal P, Thulkar D, Kokare M, Deshmukh G, Sahasrabuddhe V. Retinal Disease Classification. Retin. Fundus Multi-Disease Image Dataset A Dataset Multi-Disease Detect. https:\/\/www.kaggle.com\/datasets\/andrewmvd\/retinal-disease-classification. 2021. Accessed 2025 July 2.","DOI":"10.3390\/data6020014"},{"key":"pone.0347867.ref040","author":"S Pachade","year":"2020"},{"key":"pone.0347867.ref041","doi-asserted-by":"crossref","first-page":"103365","DOI":"10.1016\/j.media.2024.103365","article-title":"RFMiD: Retinal Image Analysis for multi-Disease Detection challenge","volume":"99","author":"S Pachade","year":"2025","journal-title":"Med Image Anal"},{"issue":"2","key":"pone.0347867.ref042","doi-asserted-by":"crossref","first-page":"1548","DOI":"10.1007\/s10489-022-03490-8","article-title":"An empirical study of preprocessing techniques with convolutional neural networks for accurate detection of chronic ocular diseases using fundus images","volume":"53","author":"V Mayya","year":"2023","journal-title":"Appl Intell (Dordr)"},{"key":"pone.0347867.ref043","first-page":"4983174","article-title":"Transfer learning with feature extraction modules for improved classifier performance on medical image data","volume":"2022","author":"R Jha","year":"2022","journal-title":"Sci Program"},{"issue":"3","key":"pone.0347867.ref044","doi-asserted-by":"crossref","first-page":"2663","DOI":"10.1007\/s40747-021-00637-x","article-title":"Feature dimensionality reduction: a review","volume":"8","author":"W Jia","year":"2022","journal-title":"Complex Intell Syst"},{"key":"pone.0347867.ref045","doi-asserted-by":"crossref","DOI":"10.3390\/diagnostics15121507","article-title":"ViSwNeXtNet Deep Patch-Wise Ensemble of Vision Transformers and ConvNeXt for Robust Binary Histopathology Classification","volume":"15","author":"\u00d6A Solmaz","year":"2025","journal-title":"Diagnostics"},{"key":"pone.0347867.ref046","doi-asserted-by":"crossref","first-page":"110071","DOI":"10.1016\/j.compbiomed.2025.110071","article-title":"Integrating lightweight convolutional neural network with entropy-informed channel attention and adaptive spatial attention for OCT-based retinal disease classification","volume":"190","author":"MR Ahmed","year":"2025","journal-title":"Comput Biol Med"},{"key":"pone.0347867.ref047","doi-asserted-by":"crossref","DOI":"10.3390\/s25144337","article-title":"Novel deep learning model for glaucoma detection using fusion of fundus and optical coherence tomography images","volume":"25","author":"S Islam","year":"2025","journal-title":"Sensors"},{"issue":"14","key":"pone.0347867.ref048","doi-asserted-by":"crossref","first-page":"4929","DOI":"10.3390\/jcm14144929","article-title":"KidneyNeXt: A Lightweight Convolutional Neural Network for Multi-Class Renal Tumor Classification in Computed Tomography Imaging","volume":"14","author":"G Ma\u00e7in","year":"2025","journal-title":"J Clin Med"},{"issue":"23","key":"pone.0347867.ref049","doi-asserted-by":"crossref","first-page":"17095","DOI":"10.1007\/s00521-023-08568-z","article-title":"A modified Adam algorithm for deep neural network optimization","volume":"35","author":"M Reyad","year":"2023","journal-title":"Neural Comput & Applic"},{"key":"pone.0347867.ref050","doi-asserted-by":"crossref","first-page":"110571","DOI":"10.1016\/j.engappai.2025.110571","article-title":"Evaluating pre-trained convolutional neural networks and foundation models as feature extractors for content-based medical image retrieval","volume":"150","author":"A Mahbod","year":"2025","journal-title":"Eng Appl Artif Intell"},{"issue":"10","key":"pone.0347867.ref051","doi-asserted-by":"crossref","first-page":"12049","DOI":"10.1007\/s10489-021-03041-7","article-title":"General Performance Score for classification problems","volume":"52","author":"IM De Diego","year":"2022","journal-title":"Appl Intell"},{"key":"pone.0347867.ref052","doi-asserted-by":"crossref","first-page":"89428","DOI":"10.1109\/ACCESS.2025.3571696","article-title":"UltraLightSqueezeNet: A Deep Learning Architecture for Malaria Classification With Up to 54\u00d7 Fewer Trainable Parameters for Resource Constrained Devices","volume":"13","author":"SB Nettur","year":"2025","journal-title":"IEEE Access"},{"key":"pone.0347867.ref053","doi-asserted-by":"crossref","unstructured":"G P, Walikar A, Ahammed SR, Suresh Y, Parihar H, Manoj V. Deep learning applications in embedded systems and IoT devices. In: 13th int conf Smart Grid. 2025;518\u201326.","DOI":"10.1109\/icSmartGrid66138.2025.11071811"},{"key":"pone.0347867.ref054","doi-asserted-by":"crossref","unstructured":"Baller SP, Jindal A, Chadha M, Gerndt M. DeepEdgeBench: Benchmarking Deep Neural Networks on Edge Devices. In: 2021 IEEE Int Conf Cloud Eng. 2021;20\u201330.","DOI":"10.1109\/IC2E52221.2021.00016"},{"issue":"1","key":"pone.0347867.ref055","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1007\/s11554-021-01164-1","article-title":"Smartphone-based real-time object recognition architecture for portable and constrained systems","volume":"19","author":"I Martinez-Alpiste","year":"2021","journal-title":"J Real-Time Image Proc"},{"issue":"6","key":"pone.0347867.ref056","doi-asserted-by":"crossref","DOI":"10.3390\/app15063077","article-title":"Performance evaluation of convolutional neural network (CNN) for skin cancer detection on edge computing devices","volume":"15","author":"DG Vincent","year":"2025","journal-title":"Applied Sciences"},{"key":"pone.0347867.ref057","doi-asserted-by":"crossref","first-page":"100035","DOI":"10.1016\/j.csbr.2025.100035","article-title":"Real-time deep learning for multi-label retinal disease diagnosis with embedded system","volume":"2","author":"F Ghislain","year":"2025","journal-title":"Computational and Structural Biotechnology Reports"},{"issue":"1","key":"pone.0347867.ref058","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/116.00000015","article-title":"Convolutional Neural Networks Inference Memory Optimization with Receptive Field-Based Input Tiling","volume":"12","author":"W Zhuang","year":"2023","journal-title":"APSIPA Transactions on Signal and Information Processing"},{"key":"pone.0347867.ref059","article-title":"Overview of memory-efficient architectures for deep learning in real-time systems","volume":"104","author":"B Demir","year":"2025","journal-title":"Eng Proc"},{"key":"pone.0347867.ref060","doi-asserted-by":"crossref","first-page":"242","DOI":"10.1007\/s10462-024-10877-1","article-title":"A comprehensive survey of deep learning-based lightweight object detection models for edge devices","volume":"57","author":"P Mittal","year":"2024","journal-title":"Artif Intell Rev"},{"issue":"2","key":"pone.0347867.ref061","doi-asserted-by":"crossref","first-page":"29","DOI":"10.3390\/data8020029","article-title":"Retinal Fundus Multi-Disease Image Dataset (RFMiD) 2.0: A Dataset of Frequently and Rarely Identified Diseases","volume":"8","author":"S Panchal","year":"2023","journal-title":"Data"},{"key":"pone.0347867.ref062","unstructured":"Panchal S, Naik A, Kokare M, Pachade S, Phadnis P, Bhange A. Retinal Fundus Multi-Disease Image Dataset (RFMiD) 2.0. https:\/\/zenodo.org\/records\/7505822. 2023. Accessed 2025 July 2."},{"key":"pone.0347867.ref063","doi-asserted-by":"crossref","first-page":"110979","DOI":"10.1016\/j.dib.2024.110979","article-title":"A dataset of color fundus images for the detection and classification of eye diseases","volume":"57","author":"S Sharmin","year":"2024","journal-title":"Data Brief"},{"key":"pone.0347867.ref064","unstructured":"Rashid MR, Sharmin S, Khatun T, Hasan MZ, Uddin MS. Eye Disease Image Dataset. A Dataset Color Fundus Images Detect. Classif. Eye Dis. 2024. https:\/\/data.mendeley.com\/datasets\/s9bfhswzjb\/1"},{"key":"pone.0347867.ref065","unstructured":"Rashid MR, Sharmin S, Khatun T, Hasan MZ, Uddin MS. Eye Disease Image Dataset - Mendeley. A dataset. 2024. https:\/\/www.kaggle.com\/datasets\/linabennaa\/eye-disease-image-dataset-mendeley"},{"issue":"1","key":"pone.0347867.ref066","doi-asserted-by":"crossref","first-page":"5037","DOI":"10.1038\/s41598-026-35428-2","article-title":"Automatic diagnosis of age-related macular degeneration using machine learning and image processing techniques","volume":"16","author":"D Agarwal","year":"2026","journal-title":"Sci Rep"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0347867","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T17:32:16Z","timestamp":1778520736000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0347867"}},"subtitle":[],"editor":[{"given":"Taikyeong Ted","family":"Jeong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,5,11]]},"references-count":66,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5,11]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0347867","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,11]]}}}