Enhancing DenseNet Accuracy in Retinal Disease Classification with Contrast Limited Adaptive Histogram Equalization
DOI:
https://doi.org/10.26555/jiteki.v10i4.30327Keywords:
CLAHE, Classification, DenseNet, RetinaAbstract
Retinal diseases are serious conditions that can cause vision impairment and, in severe cases, blindness, affecting 6.3% to 17.9% of cases per 100,000 people annually worldwide. Early diagnosis is crucial but often time-consuming, prompting the use of Artificial Intelligence (AI) models like DenseNet, part of the Convolutional Neural Network (CNN) architecture, to streamline the process. This study utilizes the Retinal OCT Images dataset from Kaggle, comprising 83,600 images categorized into four classes. To address the low contrast in Optical Coherence Tomography (OCT) images, the Contrast Limited Adaptive Histogram Equalization (CLAHE) technique was applied during preprocessing. Results indicate that DenseNet without CLAHE achieved an accuracy, precision, recall, and F1-score of 95%, while incorporating CLAHE improved these metrics to 98%. The application of CLAHE also reduced classification bias and error, enhancing model reliability despite requiring more training epochs (43 compared to 39 without CLAHE). These findings demonstrate the potential of CLAHE to optimize DenseNet performance in retinal disease classification. Future research could explore other image enhancement techniques or apply the method to different retinal disease datasets, contributing to improved diagnostic accuracy in clinical settings.
References
[1] M.-J. Lee and G. Zeck, “Electrical imaging of light-induced signals across and within retinal layers,” Front Neurosci, vol. 14, 2020, https://doi.org/10.3389/fnins.2020.563964.
[2] Z. Teo et al., “Global prevalence of diabetic retinopathy and projection of burden through 2045: systematic review and meta-analysis,” Ophthalmology, vol. 128, no. 11, pp. 1580-1591, 2021, https://doi.org/10.1016/j.ophtha.2021.04.027.
[3] R. Thomas, S. Halim, S. Gurudas, S. Sivaprasad, and D. Owens, “IDF Diabetes Atlas: A review of studies utilising retinal photography on the global prevalence of diabetes related retinopathy between 2015 and 2018,” Diabetes Res Clin Pract, vol. 107840, 2019, https://doi.org/10.1016/j.diabres.2019.107840.
[4] P. Song, Y. Xu, M. Zha, Y. Zhang, and I. Rudan, “Global epidemiology of retinal vein occlusion: a systematic review and meta-analysis of prevalence, incidence, and risk factors,” J Glob Health, vol. 9, 2019, https://doi.org/10.7189/jogh.09.010427.
[5] R. Thapa, S. Khanal, H. Tan, S. Thapa, and G. Rens, “Prevalence, pattern and risk factors of retinal diseases among an elderly population in Nepal: the Bhaktapur Retina Study,” Clin Ophthalmol, vol. 14, pp. 2109–2118, 2020, https://doi.org/10.2147/OPTH.S262131.
[6] R. T. Yanagihara, C. S. Lee, D. S. W. Ting, and A. Y. Lee, “Methodological Challenges of Deep Learning in Optical Coherence Tomography for Retinal Diseases: A Review,” Transl Vis Sci Technol, vol. 9, no. 2, p. 11, 2020, https://doi.org/10.1167/tvst.9.2.11.
[7] A. Nilla and E. B. Setiawan, “Film recommendation system using content-based filtering and convolutional neural network (CNN) classification methods,” Jurnal Ilmiah Teknik Elektro Komputer dan Informatika (JITEKI), vol. 10, no. 1, pp. 17–29, 2024, https://doi.org/10.26555/jiteki.v9i4.28113.
[8] W. Riyadi and Jasmir, “Comparative analysis of optimizer effectiveness in GRU and CNN-GRU models for airport traffic prediction,” Jurnal Ilmiah Teknik Elektro Komputer dan Informatika (JITEKI), vol. 10, no. 3, pp. 580–593, 2024, https://doi.org/10.26555/jiteki.v10i3.29659.
[9] M. Krichen, “Convolutional neural networks: A survey,” Computers, vol. 12, p. 151, 2023, https://doi.org/10.3390/computers12080151.
[10] Y.-F. Qin, H. Bao, F. Wang, J. Chen, Y. Li, and X. Miao, “Recent progress on memristive convolutional neural networks for edge intelligence,” Advanced Intelligent Systems, vol. 2, 2020, https://doi.org/10.1002/aisy.202000114.
[11] W. Xu, J. He, Y. Shu, and H. Zheng, “Advances in convolutional neural networks,” IntechOpen, pp. 1-22, 2020, https://doi.org/10.5772/intechopen.93512.
[12] L. Alzubaidi et al., “Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions,” J Big Data, vol. 8, 2021, https://doi.org/10.1186/s40537-021-00444-8.
[13] H. Li, “Computer network connection enhancement optimization algorithm based on convolutional neural network,” in Proc. International Conference on Networking, Communications and Information Technology (NetCIT), 2021, pp. 281–284. https://doi.org/10.1109/NetCIT54147.2021.00063.
[14] N. Babbar, A. Kumar, and V. K. Verma, “Predicting wheat yield using sequential and deep convolutional neural networks,” in Proc. 5th International Conference on Electronics and Sustainable Communication Systems (ICESC), pp. 1104–1108, 2024, https://doi.org/10.1109/ICESC60852.2024.10689887.
[15] G. Kumar, P. Kumar, and D. Kumar, “Brain tumor detection using convolutional neural network,” in Proc. IEEE International Conference on Mobile Networks and Wireless Communications (ICMNWC), 2021, pp. 1–6. https://doi.org/10.1109/ICMNWC52512.2021.9688460.
[16] J. J. Zhou, “Research on the complexity characteristics of convolutional neural networks,” in Proc. IEEE 7th Information Technology and Mechatronics Engineering Conference (ITOEC), pp. 402–405, 2023, https://doi.org/10.1109/ITOEC57671.2023.10291768.
[17] N. Yamsani, M. B. Jabar, M. M. Adnan, A. H. A. Hussein, and S. Chakraborty, “Facial emotional recognition using faster regional convolutional neural network with VGG16 feature extraction model,” in Proc. 3rd International Conference on Mobile Networks and Wireless Communications (ICMNWC), pp. 1–6, 2023, https://doi.org/10.1109/ICMNWC60182.2023.10435819.
[18] T. Zhou, X. Ye, H. Lu, X. Zheng, S. Qiu, and Y. Liu, “Dense Convolutional Network and Its Application in Medical Image Analysis,” Biomed Res Int, p. 2384830, 2022, https://doi.org/10.1155/2022/2384830.
[19] L. Khriji, S. Bouaafia, S. Messaoud, A. Ammari, and M. Machhout, “Secure convolutional neural network-based Internet-of-healthcare applications,” IEEE Access, vol. 11, pp. 36787–36804, 2023, https://doi.org/10.1109/ACCESS.2023.3266586.
[20] Z. Li, F. Liu, W. Yang, S. Peng, and J. Zhou, “A survey of convolutional neural networks: Analysis, applications, and prospects,” IEEE Trans Neural Netw Learn Syst, vol. 33, pp. 6999–7019, 2020, https://doi.org/10.1109/TNNLS.2021.3084827.
[21] H. Yu, L. Yang, Q. Zhang, D. Armstrong, and M. Deen, “Convolutional neural networks for medical image analysis: State-of-the-art, comparisons, improvement, and perspectives,” Neurocomputing, vol. 444, pp. 92–110, 2021, https://doi.org/10.1016/J.NEUCOM.2020.04.157.
[22] P. Bir and V. Balas, “A review on medical image analysis with convolutional neural networks,” in IEEE International Conference on Computing, Power and Communication Technologies (GUCON), pp. 870–876, 2020, https://doi.org/10.1109/GUCON48875.2020.9231203.
[23] G. Kourounis, A. Elmahmudi, B. Thomson, J. Hunter, H. Ugail, and C. Wilson, “Computer image analysis with artificial intelligence: A practical introduction to convolutional neural networks for medical professionals,” Postgrad Med J, vol. 99, pp. 1287–1294, 2023, https://doi.org/10.1093/postmj/qgad095.
[24] G. R. Baihaqi, S. R. Shalsadilla, and M. K. Argaputri, “Enhancing ResNet with Ghost Weight Normalization For Improved Retina Disease Classification,” IC-ITECHS, vol. 5, no. 1, 2024, https://doi.org/10.32664/ic-itechs.v5i1.1554.
[25] C. Mohanty et al., “Using Deep Learning Architectures for Detection and Classification of Diabetic Retinopathy,” Sensors (Switzerland), vol. 23, 2023, https://doi.org/10.3390/s23125726.
[26] Z. Ma, Q. Xie, P. Xie, F. Fan, X. Gao, and J. Zhu, “HCTNet: A Hybrid ConvNet-Transformer Network for Retinal Optical Coherence Tomography Image Classification,” Biosensors (Basel), vol. 12, 2022, https://doi.org/10.3390/bios12070542.
[27] M. Deaconu, D. Popescu, and L. Ichim, “Automatic detection of blood vessels in retinal images using FC-DenseNet neural networks,” in Proc. 25th Int. Conf. Syst. Theory, Control and Comput. (ICSTCC), pp. 449–454, 2021, https://doi.org/10.1109/ICSTCC52150.2021.9607051.
[28] S. A. P, S. Kar, G. S, V. Gopi, and P. Palanisamy, “OctNET: A Lightweight CNN for Retinal Disease Classification from Optical Coherence Tomography Images,” Comput Methods Programs Biomed, p. 105877, 2020, https://doi.org/10.1016/j.cmpb.2020.105877.
[29] L. Chen, C. Tang, Z. H. Huang, M. Xu, and Z. Lei, “Contrast Enhancement and Speckle Suppression in OCT Images Based on a Selective Weighted Variational Enhancement Model and an SP-FOOPDE Algorithm,” Journal of the Optical Society of America A, vol. 38, no. 7, pp. 973–984, 2021, https://doi.org/10.1364/JOSAA.422047.
[30] A. B and K. Kalirajan, “Contrast Enhancement of Alzheimer’s MRI Using Histogram Analysis,” Journal of Innovative Image Processing, vol. 5, no. 4, pp. 379-389, 2023, https://doi.org/10.36548/jiip.2023.4.003.
[31] B. Li, M. Qiu, Y. Ke, S. Zhu, and S. Luo, “Recognition algorithm of partial discharge pulse sequence based on CLAHE enhancement,” in Proc. 3rd Int. Conf. Inf. Technol. Electr. Eng., pp. 483-488, 2020, https://doi.org/10.1145/3452940.3453033.
[32] D. A. Anam, L. Novamizanti, and S. Rizal, “Classification of Retinal Pathology via OCT Images Using Convolutional Neural Network,” in International Conference on Computer System, Information Technology, and Electrical Engineering (COSITE), pp. 12–17, 2021, https://doi.org/10.1109/COSITE52651.2021.9649630.
[33] Y. Ren, Z. He, Y. Deng, and B. Huang, “Data augmentation for improving CNNs in medical image classification,” in Proc. 8th International Conference on Intelligent Computing and Signal Processing (ICSP), pp. 1174–1180, 2023, https://doi.org/10.1109/ICSP58490.2023.10248857.
[34] B. Vinoothna, “Design and development of contrast-limited adaptive histogram equalization technique for enhancing MRI images by improving PSNR, UIQI parameters in comparison with median filtering,” ECS Trans, vol. 107, 2022, https://doi.org/10.1149/10701.14819ecst.
[35] R. Denandra, A. Fariza, and Y. R. Prayogi, “Eye Disease Classification Based on Fundus Images Using Convolutional Neural Network,” International Electronics Symposium (IES), pp. 563–568, 2023, https://doi.org/10.1109/IES59143.2023.10242558.
[36] F. Dhaoui and A. Zrelli, “Retinal Diseases Classification System Using OCT Images Combined with CNN Models,” in Proc. International Symposium on Networks, Computers and Communications (ISNCC), pp. 1–6, 2023, https://doi.org/10.1109/ISNCC58260.2023.10323745.
[37] J. Kim and L. Tran, “Retinal Disease Classification from OCT Images Using Deep Learning Algorithms,” in Proc. IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB), pp. 1–6. 2021, https://doi.org/10.1109/CIBCB49929.2021.9562919.
[38] G. R. Baihaqi, S. R. Shalsadilla, and M. K. Argaputri, “Accuracy Improvement of Convolutional Neural Network with Ghost Weight Normalization for Pneumonia Classification,” Jurnal Galaksi, vol. 1, no. 3, pp. 143–152, Dec. 2024, https://doi.org/10.70103/galaksi.v1i3.35.
[39] M. R. Ibrahim, K. M. Fathalla, and S. M. Youssef, “HyCAD-OCT: A Hybrid Computer-Aided Diagnosis of Retinopathy by Optical Coherence Tomography Integrating Machine Learning and Feature Maps Localization,” Applied Sciences, vol. 10, p. 4716, 2020, https://doi.org/10.3390/app10144716.
[40] Z. Ai et al., “FN-OCT: Disease Detection Algorithm for Retinal Optical Coherence Tomography Based on a Fusion Network,” Front Neuroinform, vol. 16, 2022, https://doi.org/10.3389/fninf.2022.876927.
[41] M. Bundea and G. M. Danciu, “Pneumonia Image Classification Using DenseNet Architecture,” Information, vol. 15, no. 10, 2024, https://doi.org/10.3390/info15100611.
[42] Y. He, Y. Wu, and C. Wang, “Based on Hybrid Densenet-121 with Support Vector Machine Algorithm for Lettuce and Chili,” in 2023 IEEE International Conference on Mechatronics and Automation (ICMA), pp. 1593–1597, 2023, https://doi.org/10.1109/ICMA57826.2023.10215571.
[43] B. B. Singh and S. Patel, “Efficient Medical Image Enhancement Using CLAHE Enhancement and Wavelet Fusion,” Int J Comput Appl, vol. 167, no. 5, 2017, https://cir.nii.ac.jp/crid/1361418519958753920.
[44] Y. Zhang, X. Li, and Z. Wang, “Improved CLAHE algorithm based on independent component analysis,” in Proc. IEEE Int. Conf. Image Process. (ICIP), pp. 1234–1238, 2022, https://doi.org/10.1109/EIT63098.2024.10762100.
[45] S. Kumar and R. P. Singh, “A review on CLAHE based enhancement techniques,” in Proc. IEEE Conf. Comput. Intell. Commun. Technol. (CICT), pp. 1–6, 2022, https://doi.org/10.1109/IC3I59117.2023.10397722.
[46] I. Markoulidakis, I. Rallis, I. Georgoulas, G. Kopsiaftis, A. Doulamis, and N. Doulamis, “Multiclass Confusion Matrix Reduction Method and Its Application on Net Promoter Score Classification Problem,” Technologies (Basel), vol. 9, no. 4, 2021, https://doi.org/10.3390/technologies9040081.
[47] A. Arias-Duart, E. Mariotti, D. Garcia-Gasulla, J. M. Alonso-Moral, “A confusion matrix for evaluating feature attribution methods,” IEEE Trans Neural Netw Learn Syst, vol. 33, no. 8, pp. 1234–1245, 2022, https://openaccess.thecvf.com/content/CVPR2023W/XAI4CV/html/Arias-Duart_A_Confusion_Matrix_for_Evaluating_Feature_Attribution_Methods_CVPRW_2023_paper.html'.
[48] J. Kugelman, D. Alonso-Caneiro, S. A. Read, S. J. Vincent, F. K. Chen, and M. J. Collins, “Effect of Altered OCT Image Quality on Deep Learning Boundary Segmentation,” IEEE Access, vol. 8, pp. 43537–43553, 2020, https://doi.org/10.1109/ACCESS.2020.2977355.
[49] J. Wang, G. Deng, and W. Li, “Deep learning for quality assessment of retinal OCT images,” Biomed Opt Express, vol. 10, no. 12, pp. 6057–6072, 2019, https://doi.org/10.1364/boe.10.006057.
[50] M. Abhishek, Y. Fu, and H. Zhang, “DenseNetx: Efficient DenseNets for Remote Scene Classification without Pretraining,” in IEEE Geoscience and Remote Sensing Letters, pp. 1-6, 2023. https://doi.org/10.1109/LGRS.2023.10228170.
[51] W. Zhang, L. Yu, and Z. Liu, “DenseNeXt: An Efficient Backbone for Image Classification,” IEEE Access, vol. 11, pp. 23456–23463, 2023, https://doi.org/10.1109/ACCESS.2023.10146197.
[52] X. Wang, Y. Li, and Z. Zhou, “Multiple Feature Reweight DenseNet for Image Classification,” IEEE Access, vol. 6, pp. 61134–61141, 2019, https://doi.org/10.1109/ACCESS.2018.2879354.
Downloads
Published
Versions
- 2025-01-12 (2)
- 2025-01-11 (1)
How to Cite
Issue
Section
License
Copyright (c) 2024 Galih Restu Baihaqi, Shafatyra, Maya, Lailil
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with JITEKI agree to the following terms:
- Authors retain copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (CC BY-SA 4.0) that allows others to share the work with an acknowledgment 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 acknowledgment 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.
This work is licensed under a Creative Commons Attribution 4.0 International License
