DLSTM-121 with Principal Component Analysis for Diabetic Retinopathy Classification Using Segmented Retinal Blood Vessel Images
Abstract
Diabetic retinopathy classification using fundus images increasingly relies on deep learning, particularly Convolutional Neural Networks (CNNs). However, the use of high-dimensional retinal images in the processing pipeline may increase computational requirements. This study proposes a DLSTM-121-based approach for diabetic retinopathy classification by applying Principal Component Analysis (PCA) to augmented retinal images before U-Net-based segmentation. The main methodological contribution is the placement of PCA before the segmentation stage, allowing dimensionality reduction to be performed before the images are processed by the subsequent segmentation and classification models. DLSTM-121 combines DenseNet-121 and Long Short-Term Memory (LSTM) to extract spatial features and model dependencies among the extracted features. The proposed pipeline consists of data augmentation, PCA, U-Net-based retinal image segmentation, and DLSTM-121 classification. Four PCA configurations using 25, 50, 75, and 100 principal components were evaluated. The results showed that 75 principal components retained approximately 99% of the image information and achieved the best classification performance, with 96.92% accuracy, 100% sensitivity, 86.67% specificity, 98.18% F1-score, and 99% AUC. This configuration required 1,435.59 s of training time and 261.76 MB of peak GPU memory, compared with 1,456.18 s and 232.41 MB for the configuration without PCA. The inference times were 177.22 and 173.20 ms/image, respectively, while both configurations required 12.713 GFLOPs. These results demonstrate that PCA can reduce the dimensionality of the retinal image representation while maintaining high classification performance. The study used 129 retinal images from a single dataset, which limits the generalizability of the findings. Future research should evaluate the proposed approach using larger and more diverse retinal datasets.
Downloads
References
J. Zhou and B. Chen, “Retinal Cell Damage in Diabetic Retinopathy,” cells, vol. 12, no. 9, p. 1342, 2023, doi: 10.3390/cells12091342.
(WHO) World Health Organization, “Global Report on Diabetes,” Geneva, Switzerland, 2016. [Online]. Available: https://www.who.int/publications/i/item/9789241565257
T. R. Rao and G. N. Tejomurtulada, “Diabetes Mellitus: A Review,” Int. J. Med. Sci. Pharma Res., vol. 10, no. 2, pp. 5–9, 2024, doi: 10.22270/ijmspr.v10i2.97.
F. K. Malerbi et al., “Automated Identification of Different Severity Levels of Diabetic Retinopathy Using a Handheld Fundus Camera and Single-Image Protocol,” Ophthalmol. Sci., vol. 4, no. 4, p. 100481, 2024, doi: 10.1016/j.xops.2024.100481.
Y. Kim, A. F. M. S. Uddin, and S. H. Bae, “Local Augment: Utilizing Local Bias Property of Convolutional Neural Networks for Data Augmentation,” IEEE Access, vol. 9, pp. 15191–15199, 2021, doi: 10.1109/ACCESS.2021.3050758.
A. Desiani, Erwin, B. Suprihatin, S. Yahdin, A. I. Putri, and F. R. Husein, “Bi-path Architecture of CNN Segmentation and Classification Method for Cervical Cancer Disorders Based on Pap-smear Images,” IAENG Int. J. Comput. Sci., vol. 48, no. 3, pp. 782–791, 2021, [Online]. Available: https://www.iaeng.org/IJCS/issues_v48/issue_3/IJCS_48_3_37.pdf
J. Gupta, S. Pathak, and G. Kumar, “Deep Learning (CNN) and Transfer Learning: A Review,” J. Phys. Conf. Ser., vol. 2273, no. 1, p. 012029, 2022, doi: 10.1088/1742-6596/2273/1/012029.
N. Hasan, Y. Bao, A. Shawon, and Y. Huang, “DenseNet Convolutional Neural Networks Application for Predicting COVID-19 Using CT Image,” SN Comput. Sci., vol. 2, no. 5, p. 389, 2021, doi: https://doi.org/10.1007/s42979-021-00782-7.
C. Mohanty et al., “Using Deep Learning Architectures for Detection and Classification of Diabetic Retinopathy,” Sensors, vol. 23, no. 12, p. 5726, 2023, doi: 10.3390/s23125726.
S. Das and S. Majumder, “Detection of diabetic retinopathy 5-stages by denseNet, a CNN model,” Franklin Open, vol. 15, pp. 1–8, 2026, doi: 10.1016/j.fraope.2026.100577.
G. Alwakid, W. Gouda, M. Humayun, and N. Z. Jhanjhi, “Deep learning-enhanced diabetic retinopathy image classification,” Digit. Heal., vol. 9, p. 20552076231194944, 2023, doi: 10.1177/20552076231194942.
K. Zhang, Y. Guo, X. Wang, J. Yuan, and Q. Ding, “Multiple Feature Reweight DenseNet for Image Classification,” IEEE Access, vol. 7, pp. 9872–9880, 2019, doi: 10.1109/ACCESS.2018.2890127.
S. M. Al-selwi, M. F. Hassan, S. J. Abdulkadir, and A. Muneer, “LSTM Inefficiency in Long-Term Dependencies Regression Problems,” J. Adv. Res. Appl. Sci. Eng. Technol., vol. 30, no. 3, pp. 16–31, 2023, doi: 10.37934/araset.30.3.1631.
K. Glynis, Z. Kapelan, M. Bakker, and R. Taormina, “Leveraging Transfer Learning in LSTM Neural Networks for Data ‑ Efficient Burst Detection in Water Distribution Systems,” Water Resour. Manag., vol. 37, no. 15, pp. 5953–5972, 2023, doi: 10.1007/s11269-023-03637-3.
T. D. Pham, “Time-frequency time-space LSTM for robust classification of physiological signals,” Sci. Rep., vol. 11, no. 1, p. 6936, 2021, doi: 10.1038/s41598-021-86432-7.
B. M. S. Rani, V. R. Ratna, V. P. Srinivasan, S. Thenmalar, and R. Kanimozhi, “Disease prediction based retinal segmentation using bi-directional ConvLSTMU-Net,” J. Ambient Intell. Humaniz. Comput., vol. 12, pp. 1–10, 2021, doi: 10.1007/s12652-021-03561-5.
R. Vaydande, “Retinal Fundus Image Classification using LSTM - Convolution Neural Network,” National College of Ireland, Ireland, 2022. [Online]. Available: https://norma.ncirl.ie/6332/
T. Palaniswamy and M. Vellingiri, “Internet of Things and Deep Learning Enabled Diabetic Retinopathy Diagnosis Using Retinal Fundus Images,” IEEE Access, vol. 11, pp. 27590–27601, 2023, doi: 10.1109/ACCESS.2023.3257988.
H. A. H. Mahmoud, A. A. AlArfaj, and A. M. Hafez, “A Fast Hybrid Classification Algorithm with Feature Reduction for Medical Images,” Appl. Bionics Biomech., vol. 2022, pp. 1–11, Jan. 2022, doi: 10.1155/2022/1367366.
M. R. Vinutha, J. Chandrika, B. Krishnan, and S. A. Kokatnoor, “EPCA—Enhanced Principal Component Analysis for Medical Data Dimensionality Reduction,” SN Comput. Sci., vol. 4, no. 3, p. 243, 2023, doi: 10.1007/s42979-023-01677-5.
F. Saeed, M. Hussain, and H. A. Aboalsamh, “Automatic Diabetic Retinopathy Diagnosis Using Adaptive Fine-Tuned Convolutional Neural Network,” IEEE Access, vol. 9, pp. 41344–41359, 2021, doi: 10.1109/ACCESS.2021.3065273.
M. Mateen, J. Wen, Nasrullah, S. Song, and Z. Huang, “Fundus Image Classification Using VGG-19 Architecture with PCA and SVD,” Symmetry (Basel)., vol. 11, no. 1, p. 1, 2018, doi: 10.3390/sym11010001.
T. R. Gadekallu et al., “Early Detection of Diabetic Retinopathy Using PCA-Firefly Based Deep Learning Model,” Electron., vol. 9, no. 2, pp. 1–16, 2020, doi: 10.3390/electronics9020274.
R. F. Mansour, “Deep-Learning-Based Automatic Computer-Aided Diagnosis System for Diabetic Retinopathy,” Biomed. Eng. Lett., vol. 8, no. 1, pp. 41–57, 2018, doi: 10.1007/s13534-017-0047-y.
M. Mateen, J. Wen, M. Hassan, N. Nasrullah, S. Sun, and S. Hayat, “Automatic Detection of Diabetic Retinopathy: A Review on Datasets, Methods and Evaluation Metrics,” IEEE Access, vol. 8, pp. 48784–48811, 2020, doi: 10.1109/ACCESS.2020.2980055.
A. Imran, J. Li, Y. Pei, J. Yang, and Q. Wang, “Comparative Analysis of Vessel Segmentation Techniques in Retinal Images,” IEEE Access, vol. 7, pp. 114862–114887, 2019, doi: 10.1109/ACCESS.2019.2935912.
H. G. T. Özsoy, E. E. Şen, F. E. Urfalı, G. A. Aydın, B. Akyüz, and E. Dandıl, “Measurement-Oriented Evaluation of Deep Learning Models for Automated Fetal Head Biometry in Prenatal Ultrasound,” J. Clin. Med., vol. 15, no. 18, p. 7127, 2026, doi: 10.3390/jcm15187127.
M. Hayati et al., “Impact of CLAHE-based image enhancement for diabetic retinopathy classification through deep learning,” in 7th International Conference on Computer Science and Computational Intelligence 2022, Elsevier B.V., 2023, pp. 57–66. doi: 10.1016/j.procs.2022.12.111.
J. P. Bharadiya, “A Tutorial on Principal Component Analysis for Dimensionality Reduction in Machine Learning,” Int. J. Innov. Sci. Res. Technol., vol. 8, no. 5, pp. 2028–2032, 2023, doi: 10.5281/zenodo.8002436.
W. Ding, “SVM-Based Feature Selection for Differential Space Fusion and Its Application to Diabetic Fundus Image Classification,” IEEE Access, vol. 7, pp. 149493–149502, 2019, doi: 10.1109/ACCESS.2019.2944899.
H. Zhao, J. Zheng, J. Xu, and W. Deng, “Fault Diagnosis Method Based on Principal Component Analysis and Broad Learning System,” IEEE Access, vol. 7[1] H. Zh, pp. 99263–99272, 2019, doi: 10.1109/ACCESS.2019.2929094.
Y. Zhang, B. Zhang, and Z. Wu, “Multi-Model Modeling of CFB Boiler Bed Temperature System Based on Principal Component Analysis,” IEEE Access, vol. 8, pp. 389–399, 2020, doi: 10.1109/ACCESS.2019.2961414.
G. T. Reddy et al., “Analysis of Dimensionality Reduction Techniques on Big Data,” IEEE Access, vol. 8, pp. 54776–54788, 2020, doi: 10.1109/ACCESS.2020.2980942.
T. Tokuda, B. Goodrich, A. Gelman, and F. Tuerlinckx, “Visualizing Distributions of Covariance Matrices,” J. Data Sci. Stat. Vis., vol. 5, no. 7, pp. 1–30, 2025, doi: 10.52933/jdssv.v5i7.132.
T. A. Soomro et al., “Deep learning models for retinal blood vessels segmentation: a review,” IEEE Access, vol. 7, pp. 71696–71717, 2019, doi: 10.1109/ACCESS.2019.2920616.
M. Mubashar, H. Ali, C. Gronlund, and S. Azmat, “R2U++ : a multiscale recurrent residual U-Net with dense skip connections for medical image segmentation,” Neural Comput. Appl., vol. 34, no. 20, pp. 17723–17739, 2022, doi: 10.1007/s00521-022-07419-7.
M. H. Reza et al., “A comprehensive review of convolutional neural networks : foundations , enhancements and applications,” Neural Comput. Appl., vol. 38, p. 56, 2026, doi: 10.1007/s00521-025-11827-w.
R. Balestriero and R. G. Baraniuk, “Batch Normalization Explained,” ArXiv Prepr., 2022, [Online]. Available: http://10.0.189.166/arXiv.2209.14778
Y. Yuan and Y. Cheng, “Medical image segmentation with UNet-based multi-scale context fusion,” Sci. Rep., vol. 14, p. 15687, 2024, doi: 10.1038/s41598-024-66585-x.
I. Kandel and M. Castelli, “Transfer Learning with Convolutional Neural Networks for Diabetic Retinopathy Image Classification. A Review,” Appl. Sci., vol. 10, no. 6, p. 2021, 2020, doi: 10.3390/app10062021.
S. Albahli, T. Nazir, A. Irtaza, and A. Javed, “Recognition and detection of diabetic retinopathy using densenet-65 based faster-RCNN,” Comput. Mater. Contin., vol. 67, no. 2, pp. 1333–1351, 2021, doi: 10.32604/cmc.2021.014691.
W. Hou, “Statistical and machine learning methods for multi-step earthquake frequency forecasting in indonesian regions,” Nat. Hazards, vol. 122, no. 40, pp. 1–21, 2026, doi: 10.1007/s11069-025-07744-9.
C. Vasile, A. Ulm, and C. Bira, “Image Processing Hardware Acceleration — A Review of Operations Involved and Current Hardware Approaches,” J. Imaging, vol. 10, no. 12, p. 298, 2024, doi: 10.3390/jimaging10120298.
Y. Wang, Y. Zhao, and S. Addepalli, “Practical Options for Adopting Recurrent Neural Network and Its Variants on Remaining Useful Life Prediction,” Chinese J. Mech. Eng., vol. 34, p. 69, 2021, doi: 10.1038/s41598-024-66585-x.
A. Desiani et al., “Weighted Voting Ensemble for Enchanced Diabetic Retinopathy Classification using CNN Architectures,” J. Infotel, vol. 16, no. 1, pp. 136–155, 2024, doi: 10.20895/infotel.v16i1.999.
D. Nagpal, S. N. Panda, M. Malarvel, P. A. Pattanaik, and M. Z. Khan, “A review of diabetic retinopathy: Datasets, approaches, evaluation metrics and future trends,” J. King Saud Univ. – Comput. Inf. Sci., vol. 34, no. 9, pp. 7138–7152, 2022, doi: 10.1016/j.jksuci.2021.06.006.
V. Raudonis et al., “Automatic Detection of Microaneurysms in Fundus Images Using an Ensemble-Based Segmentation Method,” Sensors, vol. 23, no. 7, p. 3431, 2023, doi: 10.3390/s23073431.
M. A. A. Albadr, M. Ayob, S. Tiun, F. T. AL-Dhief, and M. K. Hasan, “Gray wolf optimization-extreme learning machine approach for diabetic retinopathy detection,” Front. Public Heal., vol. 10, p. 925901, 2022, doi: 10.3389/fpubh.2022.925901.
R. Arasy and Basari, “Detection of hypertensive retinopathy using principal component analysis ( PCA ) and backpropagation neural network methods,” in 3rd International Symposium of Biomedical Engineering’s Recent Progress in Biomaterials, Drugs Development, and Medical Devices, ISBE 2018, P. K. Praswasti P.D.K. Wulan, Misri Gozan, Sotya Astutiningsih, Ghiska Ramahdita, Radon Dhelika, Ed., Jakarta, Indonesia: American Institute of Physics Inc., 2019, p. 040002. doi: 10.1063/1.5096735.
G. Vinuja, R. Devi, N. Salm, A. Niyaz, and R. Kamnani, “Improved Detection of Early Diabetic Retinopathy using Contrast Limited Adaptive Histogram Equalization and Principal Component Analysis with Bag of Visual Words based SVM,” in 2025 International Conference on Intelligent Computing and Knowledge Extraction (ICICKE), IEEE, 2025, pp. 1–8. doi: 10.1109/ICICKE65317.2025.11136603.
T. M. Usman, Y. K. Saheed, D. Ignace, and A. Nsang, “Diabetic retinopathy detection using principal component analysis multi-label feature extraction and classification,” Int. J. Cogn. Comput. Eng., vol. 4, pp. 78–88, 2023, doi: 10.1016/j.ijcce.2023.02.002.
L. Costaner, Lisnawita, and Guntoro, “Diabetic Retinopathy Detection via PCA-MLP Using Independent GLCM and EfficientNetB3 Descriptors,” J. Teknol. Inf. dan Komun., vol. 17, no. 1, pp. 37–48, 2026, doi: 10.31849/digitalzone.v17i1.33099.
Copyright (c) 2026 Muhammad Arhami, Marwan Ramli, Melinda Melinda, Anita Desiani, Musta’inul Abdi, Husaini Husaini
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlikel 4.0 International (CC BY-SA 4.0) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
.png)
.png)
.png)
.png)
.png)
