{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T22:34:35Z","timestamp":1774305275912,"version":"3.50.1"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,2,6]],"date-time":"2024-02-06T00:00:00Z","timestamp":1707177600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,2,6]],"date-time":"2024-02-06T00:00:00Z","timestamp":1707177600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Med Inform Decis Mak"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>The most common eye infection in people with diabetes is diabetic retinopathy (DR). It might cause blurred vision or even total blindness. Therefore, it is essential to promote early detection to prevent or alleviate the impact of DR. However, due to the possibility that symptoms may not be noticeable in the early stages of DR, it is difficult for doctors to identify them. Therefore, numerous predictive models based on machine learning (ML) and deep learning (DL) have been developed to determine all stages of DR. However, existing DR classification models cannot classify every DR stage or use a computationally heavy approach. Common metrics such as accuracy, F1 score, precision, recall, and AUC-ROC score are not reliable for assessing DR grading. This is because they do not account for two key factors: the severity of the discrepancy between the assigned and predicted grades and the ordered nature of the DR grading scale.\u00a0<\/jats:p>\n                  <jats:p>This research proposes computationally efficient ensemble methods for the classification of DR. These methods leverage pre-trained model weights, reducing training time and resource requirements. In addition, data augmentation techniques are used to address data limitations, improve features, and improve generalization. This combination offers a promising approach for accurate and robust DR grading. In particular, we take advantage of transfer learning using models trained on DR data and employ CLAHE for image enhancement and Gaussian blur for noise reduction. We propose a three-layer classifier that incorporates dropout and ReLU activation. This design aims to minimize overfitting while effectively extracting features and assigning DR grades. We prioritize the Quadratic Weighted Kappa (QWK) metric due to its sensitivity to label discrepancies, which is crucial for an accurate diagnosis of DR. This combined approach achieves state-of-the-art QWK scores (0.901, 0.967 and 0.944) in the Eyepacs, Aptos, and Messidor datasets.<\/jats:p>","DOI":"10.1186\/s12911-024-02446-x","type":"journal-article","created":{"date-parts":[[2024,2,6]],"date-time":"2024-02-06T03:02:37Z","timestamp":1707188557000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["A reliable diabetic retinopathy grading via transfer learning and ensemble learning with quadratic weighted kappa metric"],"prefix":"10.1186","volume":"24","author":[{"given":"Sai\u00a0Venkatesh","family":"Chilukoti","sequence":"first","affiliation":[]},{"given":"Liqun","family":"Shan","sequence":"additional","affiliation":[]},{"given":"Vijay\u00a0Srinivas","family":"Tida","sequence":"additional","affiliation":[]},{"given":"Anthony\u00a0S.","family":"Maida","sequence":"additional","affiliation":[]},{"given":"Xiali","family":"Hei","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,2,6]]},"reference":[{"key":"2446_CR1","unstructured":"Diabetic Retinopathy Data and Statistics.\u00a02022. https:\/\/www.nei.nih.gov\/learn-about-eye-health\/outreach-campaigns-and-resources\/eye-health-data-and-statistics\/diabetic-retinopathy-data-and-statistics. Accessed\u00a0Nov 2022."},{"issue":"3","key":"2446_CR2","doi-asserted-by":"publisher","first-page":"e022188","DOI":"10.1136\/bmjopen-2018-022188","volume":"9","author":"R Cheloni","year":"2019","unstructured":"Cheloni R, Gandolfi SA, Signorelli C, Odone A. Global prevalence of diabetic retinopathy: protocol for a systematic review and meta-analysis. BMJ Open. 2019;9(3):e022188.","journal-title":"BMJ Open."},{"key":"2446_CR3","unstructured":"Diabetic Retinopathy.\u00a02021. https:\/\/brailleinstitute.org\/diabetic-retinopathy?. Accessed Oct 2023."},{"key":"2446_CR4","unstructured":"Diabetes and your eyes.\u00a02021. https:\/\/www.noweyesee.com\/diabetes-and-your-eyes. Accessed Aug 2022."},{"key":"2446_CR5","doi-asserted-by":"publisher","unstructured":"T. E. D. P. R. Group*, The Prevalence of Diabetic Retinopathy Among Adults in the United States. Arch Ophthalmol. 2004;122(4):552\u2013563. https:\/\/doi.org\/10.1001\/archopht.122.4.552.","DOI":"10.1001\/archopht.122.4.552"},{"key":"2446_CR6","unstructured":"Saving Vision for Patients Living with Diabetes Starts with You.\u00a02021. https:\/\/www.hillrom.com\/en\/solutions\/enable-earlier-diagnosis-and-treatment\/. Accessed Aug 2022."},{"key":"2446_CR7","unstructured":"Diabetic retinopathy.\u00a02004. https:\/\/www.mayoclinic.org\/diseases-conditions\/diabetic-retinopathy\/symptoms-causes\/syc-20371611. Accessed Aug 2022."},{"key":"2446_CR8","unstructured":"WHO reports.\u00a02021. https:\/\/apps.who.int\/iris\/bitstream\/handle\/10665\/336660\/9789289055321-eng.pdf. Accessed\u00a0Nov 2022."},{"key":"2446_CR9","unstructured":"Nonproliferative Diabetic Retinopathy (NPDR) and Macular Edema.\u00a02020. https:\/\/louisvillediabeticeyedoctor.com\/truck-drivers\/nonproliferative-diabetic-retinopathy-npdr-and-macular-edema\/. Accessed Dec 2022."},{"key":"2446_CR10","unstructured":"Diabetic retinopathy.\u00a02021. https:\/\/www.aoa.org\/healthy-eyes\/eye-and-vision-conditions\/diabetic-retinopathy?sso=y. Accessed Nov 2022."},{"key":"2446_CR11","unstructured":"Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556. 2014."},{"key":"2446_CR12","doi-asserted-by":"publisher","unstructured":"He K, Zhang X, Ren S, et al. Deep residual learning for image recognition. In: Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., vol. 2016-December. 2016. pp. 770\u20138. https:\/\/doi.org\/10.1109\/CVPR.2016.90.","DOI":"10.1109\/CVPR.2016.90"},{"key":"2446_CR13","doi-asserted-by":"crossref","unstructured":"Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z. Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2016. pp. 2818\u20132826.","DOI":"10.1109\/CVPR.2016.308"},{"key":"2446_CR14","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G. Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2018. pp. 7132\u20137141.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"2446_CR15","unstructured":"Krizhevsky A, Sutskever I, Hinton GE. ImageNet Classification with Deep Convolutional Neural Networks (AlexNet) ImageNet Classification with Deep Convolutional Neural Networks (AlexNet) ImageNet Classification with Deep Convolutional Neural Networks."},{"key":"2446_CR16","doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, Van Der Maaten L, Weinberger KQ. Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2017. pp. 4700\u20134708).","DOI":"10.1109\/CVPR.2017.243"},{"key":"2446_CR17","unstructured":"Quadratic weighted kappa.\u00a02018. https:\/\/www.Eyepacs.com\/aroraaman\/quadratic-kappa-metric-explained-in-5-simple-steps. Accessed\u00a0July 2022."},{"key":"2446_CR18","doi-asserted-by":"crossref","unstructured":"Al-Smadi M, Hammad M, Baker QB, Sa\u2019ad A. A transfer learning with deep neural network approach for diabetic retinopathy classification. Int J Electr Comput Eng.\u00a02021;11(4):3492.","DOI":"10.11591\/ijece.v11i4.pp3492-3501"},{"key":"2446_CR19","unstructured":"Karthik, Maggie, Sohier Dane. APTOS 2019 Blindness Detection. Kaggle. 2019. https:\/\/kaggle.com\/competitions\/aptos2019-blindness-detection. nnMobileNet: RETHINKING CNN FOR RETINOPATHY RESEARCH."},{"key":"2446_CR20","doi-asserted-by":"crossref","unstructured":"Zhu\u00a0W, Qiu\u00a0P, Li X, Lepore\u00a0N, Dumitrascu\u00a0OM, Wang Y.\u00a0nnMobileNe: Rethinking CNN for Retinopathy Research.\u00a02023.\u00a0arXiv preprint arXiv:2306.01289.","DOI":"10.1109\/CVPRW63382.2024.00234"},{"key":"2446_CR21","doi-asserted-by":"publisher","first-page":"48784","DOI":"10.1109\/ACCESS.2020.2980055","volume":"8","author":"M Mateen","year":"2020","unstructured":"Mateen M, Wen J, Hassan M, Nasrullah N, Sun S, Hayat S. Automatic detection of diabetic retinopathy: a review on datasets, methods and evaluation metrics. IEEE Access. 2020;8:48784\u2013811.","journal-title":"IEEE Access."},{"key":"2446_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2020\/5801870","volume":"2020","author":"M Mateen","year":"2020","unstructured":"Mateen M, Wen J, Nasrullah N, Sun S, Hayat S. Exudate detection for diabetic retinopathy using pretrained convolutional neural networks. Complexity. 2020;2020:1\u201311.","journal-title":"Complexity."},{"issue":"1","key":"2446_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/sym11010001","volume":"11","author":"M Mateen","year":"2018","unstructured":"Mateen M, Wen J, Song S, Huang Z. Fundus image classification using vgg-19 architecture with pca and svd. Symmetry. 2018;11(1):1.","journal-title":"Symmetry."},{"key":"2446_CR24","doi-asserted-by":"crossref","unstructured":"Mohan NJ, Murugan R, Goel T, Mirjalili S, Singh YK, Deb D, Roy P. Optimal hybrid feature selection technique for diabetic retinopathy grading using fundus images. S\u0101dhan\u0101. 2023;48(3):102.","DOI":"10.1007\/s12046-023-02175-3"},{"key":"2446_CR25","doi-asserted-by":"crossref","unstructured":"Mohan NJ, Murugan R, Goel T, Roy P. DRFL: Federated Learning in Diabetic Retinopathy Grading Using Fundus Images. IEEE Trans Parallel Distrib Syst. 2023.","DOI":"10.1007\/s12046-023-02175-3"},{"key":"2446_CR26","unstructured":"ImageNet.\u00a02009. https:\/\/www.image-net.org\/. Accessed June 2022."},{"key":"2446_CR27","unstructured":"Tan M, Le Q. Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning 2019 May 24 (pp. 6105-6114). PMLR."},{"key":"2446_CR28","doi-asserted-by":"crossref","unstructured":"Sandler\u00a0M, Howard\u00a0A, Zhu\u00a0M, Zhmoginov\u00a0A, Chen L-C.\u00a0MobileNetV2: Inverted Residuals and Linear Bottlenecks.\u00a02019.\u00a0arXiv preprint arXiv:1801.04381.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"2446_CR29","unstructured":"Pytorch.\u00a02017. https:\/\/pytorch.org\/. Accessed\u00a0Feb 2022."},{"key":"2446_CR30","unstructured":"Dataset.\u00a02018. https:\/\/www.Eyepacs.com\/tanlikesmath\/diabetic-retinopathy-resized. Accessed\u00a0May 2022."},{"key":"2446_CR31","unstructured":"Huang Y, Lyu J, Cheng P, Tam R, Tang X. Ssit: Saliency-guided self-supervised image transformer for diabetic retinopathy grading. 2022.\u00a0arXiv\u00a0preprint\u00a0arXiv:2210.10969."},{"key":"2446_CR32","doi-asserted-by":"crossref","unstructured":"Chollet F. Xception: Deep learning with depthwise separable convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2017. pp. 1251\u20131258.","DOI":"10.1109\/CVPR.2017.195"},{"key":"2446_CR33","unstructured":"Dai Z, Liu H, Le QV, Tan M. Coatnet: Marrying convolution and attention for all data sizes.\u00a0Adv Neural Inf Process Syst. 2021;34:3965\u201377."},{"key":"2446_CR34","unstructured":"Islam SMS, Hasan\u00a0MM, Abdullah S. Deep learning based early detection and grading of diabetic retinopathy using retinal fundus images. 2018. arXiv preprint arXiv:1812.10595."},{"key":"2446_CR35","unstructured":"Yang\u00a0T, Andrew\u00a0G, Eichner\u00a0H, Sun\u00a0H, Li\u00a0W, Kong N, Ramage D, Beaufays F. Applied federated learning: Improving google keyboard query suggestions.\u00a02018. arXiv\u00a0preprint\u00a0arXiv:1812.02903."},{"key":"2446_CR36","doi-asserted-by":"publisher","unstructured":"Krause J, et al. Grader variability and the importance of reference standards for evaluating machine learning models for diabetic retinopathy. Ophthalmology. 2018. https:\/\/doi.org\/10.1016\/j.ophtha.2018.01.034.","DOI":"10.1016\/j.ophtha.2018.01.034"},{"key":"2446_CR37","unstructured":"Karthik, Maggie, Dane S. APTOS 2019 Blindness Detection. Kaggle. 2019. https:\/\/kaggle.com\/competitions\/aptos2019-blindness-detection. Accessed Dec 2023."}],"container-title":["BMC Medical Informatics and Decision Making"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-024-02446-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12911-024-02446-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-024-02446-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,10]],"date-time":"2024-11-10T09:28:21Z","timestamp":1731230901000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcmedinformdecismak.biomedcentral.com\/articles\/10.1186\/s12911-024-02446-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,6]]},"references-count":37,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["2446"],"URL":"https:\/\/doi.org\/10.1186\/s12911-024-02446-x","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-2383368\/v1","asserted-by":"object"}]},"ISSN":["1472-6947"],"issn-type":[{"value":"1472-6947","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,6]]},"assertion":[{"value":"15 December 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 January 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 February 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"37"}}