Abstract
Aims
This study aims to develop an advanced model for the classification of Diabetic Macular Edema (DME) using deep learning techniques. Specifically, the objective is to introduce a novel architecture, SSCSAC-Net, that leverages self-supervised learning and category-selective attention mechanisms to improve the precision of DME classification.
Methods
The proposed SSCSAC-Net integrates self-supervised learning to effectively utilize unlabeled data for learning robust features related to DME. Additionally, it incorporates a category-specific attention mechanism and a domain-specific layer into the ResNet-152 base architecture. The model is trained using an ensemble of unsupervised and supervised learning techniques. Benchmark datasets are utilized for testing the model's performance, ensuring its robustness and generalizability across different data distributions.
Results
Evaluation of the SSCSAC-Net on multiple datasets demonstrates its superior performance compared to existing techniques. The model achieves high accuracy, precision, and recall rates, with an accuracy of 98.7%, precision of 98.6%, and recall of 98.8%. Furthermore, the incorporation of self-supervised learning reduces the dependency on extensive labeled data, making the solution more scalable and cost-effective.
Conclusions
The proposed SSCSAC-Net represents a significant advancement in automated DME classification. By effectively using self-supervised learning and attention mechanisms, the model offers improved accuracy in identifying DME-related features within retinal images. Its robustness and generalizability across different datasets highlight its potential for clinical applications, providing a valuable tool for clinicians in diagnosing DME effectively.
Similar content being viewed by others
Data availability
All authors contributed to the study conception and design. Material preparation, data collection and analysis were performed by Sachin Chavan, Nitin Choubey. The first draft of the manuscript was written by Sachin Chavan and all authors commented on previous versions of the manuscript. All authors read and approved the final manuscript.
References
Iyer SS, Radhakrishnan NS, Roohipourmoallai R, Guerin CM, Maylath JS, Garson N (2023) Chronic ocular small vessel disease: An overview of diabetic retinopathy and its relationship with cardiovascular health. American Heart Journal Plus: Cardiology Research and Practice. 100270.
Semeraro F, Morescalchi F, Cancarini A, Russo A, Rezzola S, Costagliola C (2019) Diabetic retinopathy, a vascular and inflammatory disease: therapeutic implications. Diabetes Metab 45(6):517–527
Lanzetta P, Sarao V, Scanlon PH, Barratt J, Porta M, Bandello F, Loewenstein A (2020) Fundamental principles of an effective diabetic retinopathy screening program. Acta Diabetol 57:785–798
Liu X, Ali TK, Singh P, Shah A, McKinney SM, Ruamviboonsuk P, Turner AW, Keane PA, Chotcomwongse P, Nganthavee V, Chia M (2022) Deep learning to detect OCT-derived diabetic macular edema from color retinal photographs: a multicenter validation study. Ophthalmol Retina 6(5):398–410
Li X, Hu X, Yu L, Zhu L, Fu CW, Heng PA (2019) CANet: cross-disease attention network for joint diabetic retinopathy and diabetic macular edema grading. IEEE Trans Med Imaging 39(5):1483–1493
Chalakkal R, Hafiz F, Abdulla W, Swain A (2021) An efficient framework for automated screening of Clinically Significant Macular Edema. Comput Biol Med 130:104128
Chalakkal RJ, Abdulla WH, Hong SC (2020) Fundus retinal image analyses for screening and diagnosing diabetic retinopathy, macular edema, and glaucoma disorders. InDiabetes and Fundus OCT (pp 59–111). Elsevier
Lalithadevi B, Krishnaveni S (2022) Detection of diabetic retinopathy and related retinal disorders using fundus images based on deep learning and image processing techniques: a comprehensive review. Concurr Comput Pract Exp 34(19):e7032
Mathews MR, Anzar SM (2021) A comprehensive review on automated systems for severity grading of diabetic retinopathy and macular edema. Int J Imaging Syst Technol 31(4):2093–2122
Sundaram S, Selvamani M, Raju SK, Ramaswamy S, Islam S, Cha JH, Almujally NA, Elaraby A (2023) Diabetic retinopathy and diabetic macular edema detection using ensemble based convolutional neural networks. Diagnostics 13(5):1001
Senthamizh Selvi R, Bragadesh Bharatwaj S, Ajith Kumar B, Bharath Raj VR, Sudha S (2021) Convolutional neural network-based detection and classification of cardiovascular disease and diabetic macular edema. InMicro-Electronics and telecommunication engineering: proceedings of 4th ICMETE 2020 (pp. 407–422). Springer Singapore
Everett LA, Paulus YM (2021) Laser therapy in the treatment of diabetic retinopathy and diabetic macular edema. Curr DiabRep 21:1–2
Brito P, Costa J, Gomes N, Costa S, Correia-Pinto J, Silva R (2018) Serological inflammatory factors as biomarkers for anatomic response in diabetic macular edema treated with anti-VEGF. J Diabetes Complicat 32(7):643–649
Cacciamani A, Esposito G, Scarinci F, Parravano M, Dinice L, Di Nicola M, Micera A (2019) Inflammatory mediators in the vitreal reflux of patients with diabetic macular edema. Graefes Arch Clin Exp Ophthalmol 257:187–197
Islam MR, Abdulrazak LF, Nahiduzzaman M, Goni MO, Anower MS, Ahsan M, Haider J, Kowalski M (2022) Applying supervised contrastive learning for the detection of diabetic retinopathy and its severity levels from fundus images. Comput Biol Med 146:105602
Bhardwaj C, Jain S, Sood M (2021) Deep learning–based diabetic retinopathy severity grading system employing quadrant ensemble model. J Digit Imaging 34:440–457
Yang Y, Shang F, Wu B, Yang D, Wang L, Xu Y, Zhang W, Zhang T (2021) Robust collaborative learning of patch-level and image-level annotations for diabetic retinopathy grading from fundus image. IEEE Trans Cybern 52(11):11407–11417
Chavan S, Choubey N (2023) An automated diabetic retinopathy of severity grade classification using transfer learning and fine-tuning for fundus images. Multimed Tools Appl 82(24):36859–36884
Alahmadi MD (2022) Texture attention network for diabetic retinopathy classification. IEEE Access 10:55522–55532
Farag MM, Fouad M, Abdel-Hamid AT (2022) Automatic severity classification of diabetic retinopathy based on denseNet and convolutional block attention module. IEEE Access 10:38299–38308
Bilal A, Sun G, Li Y, Mazhar S, Khan AQ (2021) Diabetic retinopathy detection and classification using mixed models for a disease grading database. IEEE Access 9:23544–23553
Al-Antary MT, Arafa Y (2021) Multi-scale attention network for diabetic retinopathy classification. IEEE Access 9:54190–54200
Wu T, Liu L, Zhang T, Wu X (2022) Deep learning-based risk classification and auxiliary diagnosis of macular edema. Intell Based Med 6:100053
Wu J, Zhang Q, Liu M, Xiao Z, Zhang F, Geng L, Liu Y, Wang W (2021) Diabetic macular edema grading based on improved Faster R-CNN and MD-ResNet. Signal Image Video Process 15:743–751
Altan G (2022) DeepOCT: an explainable deep learning architecture to analyze macular edema on OCT images. Eng Sci Technol Int J 34:101091
Saini DJ, Sivakami R, Venkatesh R, Raghava CS, Dwarkanath PS, Anwer TM, Smirani LK, Ahammad SH, Pamula U, Hossain MA, Rashed AN (2023) Convolution neural network model for predicting various lesion-based diseases in diabetic macula edema in optical coherence tomography images. Biomed Signal Process Control 86:105180
Narin A, Kaya C, Pamuk Z (2021) Automatic detection of coronavirus disease (covid-19) using x-ray images and deep convolutional neural networks. Pattern Anal Appl 24:1207–1220
Funding
There is no funding for this study.
Author information
Authors and Affiliations
Contributions
SC contributed to conceptualization, methodology, writing—original draft preparation, writing—review and editing. SC and NC contributed to formal analysis and investigation. NC supervised the study. All the authors have participated in writing the manuscript and have revised the final version. All authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Conflict of interest
Authors declares that they have no conflict of interest.
Ethical approval
This article does not contain any studies with human participants and/or animals performed by any of the authors.
Informed consent
There is no informed consent for this study.
Additional information
Managed By Massimo Federici.
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Chavan, S., Choubey, N. Self-supervised category selective attention classifier network for diabetic macular edema classification. Acta Diabetol (2024). https://doi.org/10.1007/s00592-024-02257-6
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s00592-024-02257-6