Densenet Model for Binary Glaucoma Classification Performance Assessment with Texture Feature
Main Article Content
Abstract
The retina is an important portion of the eye because images of it are used by doctors to diagnose numerous eye diseases such as glaucoma, diabetic retinopathy, and cataracts. Indeed, segmented retinal imaging is a powerful tool for detecting unusual growths in the eye area as well as determining the size and structure of the optic disc. The combination of digital image processing and deep learning techniques enables the development of automated approaches for detecting glaucoma. Within this framework, the objective of this study is to achieve prompt detection of glaucoma by utilizing a DenseNet-121 Network in conjunction with texture qualities derived from local binary patterns (LBP). The proposed method can be categorized into four steps: (i) obtaining images from the OIH public database; (ii) preprocessing the images by extracting texture attributes using LBP; (iii) classifying glaucoma images and normal images using a DenseNet-121 network; and (iv) validating the proposal based on performance metrics. Based on the results of the proposed strategy, the accuracy remains approximately 96%.
Received 04/10/2023
Revised 26/04/2024
Accepted 28/04/2024
Published Online First 20/05/2024
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
How to Cite
References
- Ayzenberg V, Kamps FS, Dilks DD, Lourenco SF. Skeletal representations of shape in the human visual cortex. Neuropsychologia. 2022 Jan 7; 164: 108092.https://doi.org/10.1016/j.neuropsychologia.2021.108092
- Congdon, Nathan, et al. Causes and prevalence of visual impairment among adults in the United States. Arch. Ophth. (Chicago, Ill.: 1960). 2004 Apr 1; 122(4): 477-85.https://doi.org/10.1001/archopht.122.4.477
- Abdel-Hamid L. Glaucoma detection from retinal images using statistical and textural wavelet features. J Digit Imaging. 2020; 33(1): 151-158. https://doi.org/10.1007/s10278-019-00189-0
- Kumar BN, Chauhan RP, Dahiya N. Detection of glaucoma using image processing techniques: A critique. Semin Ophthalmol. 2018; 33(2): 275–228.https://doi.org/10.1080/08820538.2016.1229801
- Kavya N, Padmaja KV. Glaucoma detection using texture features extraction. Proceedings of the 51st IEEE Asilomar Conference on Signals, Systems, and Computers. 2017; 1471–1475.https://doi.org/10.1109/ACSSC.2017.8335600
- Khalaf M, Dhannoon B N. MSRD-Unet: Multiscale Residual Dilated U-Net for Medical Image Segmentation. Baghdad Sci J. 2022; 19(6 (Suppl.)): 1603-1603.https://doi.org/10.21123/bsj.2022.7559
- Kadhem S M. Iraqi sign language translator system using deep learning. AJEST. 2023; 2(1): 109-116. https://doi.org/10.55145/ajest.2023.01.01.0013
- Khalaf M, Dhannoon BN. Skin lesion segmentation based on U-shaped network. Karbala Int J Mod Sci. 2022; 8(3): 493-502. https://doi.org/10.33640/2405-609X.3248
- Shamsan A, Senan EM, Shatnawi HS. Automatic classification of colour fundus images for prediction eye disease types based on hybrid features. Diagnostics. 2023 May 11; 13(10): 1706. https://doi.org/10.3390/diagnostics13101706
- Varghese NR, Gopan NR. Performance analysis of automated detection of diabetic retinopathy using machine learning and deep learning techniques. InInnovative Data Communication Technologies and Application: ICIDCA 2019 2020 (pp. 156-164). Springer International Publishing. https://doi.org/10.1007/978-3-030-38040-3_18
- Iyyanarappan A, Tamilpavai G. Glaucomatous image classification using wavelet-based energy features and PNN. IJTEEE. 2014; 2(4). https://doi.org/10.1109/TITB.2011.2176540
- Biswal B, Vyshnavi E, Sairam MV. Robust retinal optic disc and optic cup segmentation via stationary wavelet transform and maximum vessel pixel sum. IET Image Process. 14 (4): 592–602. https://doi.org/10.1049/iet-ipr.2019.0845
- Singh A, Dutta MK, ParthaSarathi M, Uher V, Burget R. Image processing based automatic diagnosis of glaucoma using wavelet features of segmented optic disc from fundus image. Comput. Methods Programs Biomed. 2016 Feb 1; 124: 108-20. https://doi.org/10.1016/j.cmpb.2015.10.010
- Dutta MK, Mourya AK, Singh A, Parthasarathi M, Burget R, Riha K. Glaucoma detection by segmenting the super pixels from fundus colour retinal images. In2014 international conference on medical imaging, m-health and emerging communication systems (MedCom) 2014 Nov 7 (pp. 86-90). IEEE. https://doi.org/10.1109/MedCom.2014.7005981
- Dey N, Roy AB, Das A, Chaudhuri SS. Optical cup to disc ratio measurement for glaucoma diagnosis using harris corner. In2012 Third International Conference on Computing, Communication and Networking Technologies (ICCCNT'12) 2012 Jul 26 (pp. 1-5). IEEE. https://doi.org/10.1109/ICCCNT.2012.6395971 .
- Guru Prasad MS, Naveen Kumar HN, Raju K, Santhosh Kumar DK, Chandrappa S. Glaucoma detection using clustering and segmentation of the optic disc region from retinal fundus images. SN Comput. Sci. 2023 Feb 2; 4(2): 192. https://doi.org/10.1007/s42979-022-01592-1
- Nawaldgi S, Lalitha YS. Automated glaucoma assessment from color fundus images using structural and texture features. Biomed Signal Process. Control. 2022 Aug 1; 77:103875. https://doi.org/10.1016/j.bspc.2022.103875
- Bechar ME, Settouti N, Barra V, Chikh MA. Semi-supervised superpixel classification for medical images segmentation: application to detection of glaucoma disease. Multidimension Syst Signal Process. 2018 Jul; 29: 979-98. https://doi.org/10.1007/s11045-017-0483-y
- Thakur N, Juneja M. Survey on segmentation and classification approaches of optic cup and optic disc for diagnosis of glaucoma. Biomed Signal Process Control. 2018 Apr 1; 42: 162-89. https://doi.org/10.1016/j.bspc.2018.01.014
- Spaeth GL, Lopes JF, Junk AK, Grigorian AP, Henderer J. Systems for staging the amount of optic nerve damage in glaucoma: a critical review and new material. Surv Ophthalmol. 2006 Jul 1; 51(4): 293-315. https://doi.org/10.1016/j.survophthal.2006.04.008
- Khalil T, Usman Akram M, Khalid S, Jameel A. Improved automated detection of glaucoma from fundus image using hybrid structural and textural features. IET Image Proc. 2017 Sep; 11(9): 693-700. https://doi.org/10.1049/iet-ipr.2016.0812
- Barros DM, Moura JC, Freire CR, Taleb AC, Valentim RA, Morais PS. Machine learning applied to retinal image processing for glaucoma detection: review and perspective. Biomed Eng Online. 2020 Dec; 19: 1-21. https://doi.org/10.1186/s12938-020-00767-2
- Ojala T, Pietikainen M, Maenpaa T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans Pattern Anal Mach Intell. 2002 Jul; 24(7): 971-87. https://doi.org/10.1109/TPAMI.2002.1017623
- Vu HN, Nguyen MH, Pham C. Masked face recognition with convolutional neural networks and local binary patterns. Appl Intell. 2022 Mar; 52(5): 5497-512. https://doi.org/10.1007/s10489-021-02728-1
- Chauhan T, Palivela H, Tiwari S. Optimization and fine-tuning of DenseNet model for classification of COVID-19 cases in medical imaging. InInt JInf Manage Data Insights. 2021 Nov 1; 1(2): 100020. https://doi.org/10.1016/j.jjimei.2021.100020
- Zhang C, Benz P, Argaw DM, Lee S, Kim J, Rameau F, Bazin JC, Kweon IS. Resnet or densenet? introducing dense shortcuts to resnet. InProceedings of the IEEE/CVF winter conference on applications of computer vision 2021 (pp. 3550-3559).https://doi.org/10.1109/WACV48630.2021.00359
- Huang G, Chen D, Li T, Wu F, Van Der Maaten L, Weinberger KQ. Multi-scale dense networks for resource efficient image classification. arXiv preprint arXiv:1703.09844. 2017 Mar 29. 2017; 1703: 09844. https://doi.org/10.48550/arXiv.1703.09844
- Huang G, Liu Z, Van Der Maaten L, Weinberger KQ. Densely connected convolutional networks. InProceedings of the IEEE conference on computer vision and pattern recognition 2017 (pp. 4700-4708). https://doi.org/10.1109/CVPR.2017.243
- Sreena VG, Ponraj DN. Optimization of Fine Tuned Deep Learning Model for Multiclass Classification of Chest X-Rays. In2023 4th International Conference on Signal Processing and Communication (ICSPC) 2023 Mar 23 (pp. 173-177). IEEE. https://doi.org/10.1109/ICSPC57692.2023.10126060
- Kingma DP, Ba J. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980. 2014 Dec 22. https://doi.org/10.48550/arXiv.1412.6980
- Bhardwaj C, Jain S, Sood M. Hierarchical severity grade classification of non-proliferative diabetic retinopathy. J Ambient Intell. Hum Comput.. 2021 Feb; 12(2): 2649-70. https://doi.org/10.1007/s12652-020-02426-9
- Liu S, Graham SL, Schulz A, Kalloniatis M, Zangerl B, Cai W, et al. A deep learning-based algorithm identifies glaucomatous discs using monoscopic fundus photographs. Ophthalmol Glaucoma. 2018; 1(1) : 15-22. https://doi.org/10.3390/healthcare10122345
- Junayed MS, Islam MB, Sadeghzadeh A, Rahman S. CataractNet: An automated cataract detection system using deep learning for fundus images. IEEE access. 2021 Sep 15; 9: 128799-808. https://doi.org/10.1109/ACCESS.2021.3112938
- Sundaram R, Ks R, Jayaraman P. Extraction of blood vessels in fundus images of retina through hybrid segmentation approach. Mathematics. 2019 Feb 13; 7(2): 169. https://doi.org/10.3390/math7020169
- Olayah F, Senan EM, Ahmed IA, Awaji B. AI techniques of dermoscopy image analysis for the early detection of skin lesions based on combined CNN features. Diagnostics. 2023 Apr 1; 13(7): 1314. https://doi.org/10.3390/diagnostics13071314