Glaucoma is a chronic ocular degenerative disease that can cause blindness if left untreated in its early stages. Deep Convolutional Neural Networks (Deep CNNs) and its variants have provided superior performance in glaucoma classification, segmentation, and detection. In this paper, we propose a two-staged glaucoma classification scheme based on Deep CNN architectures. In stage one, four different ImageNet pre-trained Deep CNN architectures, i.e., AlexNet, InceptionV3, InceptionResNetV2, and NasNet-Large are used and it is observed that NasNet-Large architecture provides superior performance in terms of sensitivity (99.1%), specificity (99.4%), accuracy (99.3%), and area under the receiver operating characteristic curve (97.8%) metrics. A detailed performance comparison is also presented among these on public datasets, i.e., ACRIMA, ORIGA-Light, and RIM-ONE as well as locally available datasets, i.e., AFIO, and HMC. In the second stage, we propose an ensemble classifier with two novel ensembling techniques, i.e., accuracy based weighted voting, and accuracy/score based weighted averaging to further improve the glaucoma classification results. It is shown that ensemble with accuracy/score based scheme improves the accuracy (99.5%) for diverse databases. As an outcome of this study, it is presented that the NasNet-Large architecture is a feasible option in terms of its performance as a single classifier while ensemble classifier further improves the generalized performance for automatic glaucoma classification.
Citation: Aziz-ur-Rehman, Imtiaz A. Taj, Muhammad Sajid, Khasan S. Karimov. An ensemble framework based on Deep CNNs architecture for glaucoma classification using fundus photography[J]. Mathematical Biosciences and Engineering, 2021, 18(5): 5321-5346. doi: 10.3934/mbe.2021270
Glaucoma is a chronic ocular degenerative disease that can cause blindness if left untreated in its early stages. Deep Convolutional Neural Networks (Deep CNNs) and its variants have provided superior performance in glaucoma classification, segmentation, and detection. In this paper, we propose a two-staged glaucoma classification scheme based on Deep CNN architectures. In stage one, four different ImageNet pre-trained Deep CNN architectures, i.e., AlexNet, InceptionV3, InceptionResNetV2, and NasNet-Large are used and it is observed that NasNet-Large architecture provides superior performance in terms of sensitivity (99.1%), specificity (99.4%), accuracy (99.3%), and area under the receiver operating characteristic curve (97.8%) metrics. A detailed performance comparison is also presented among these on public datasets, i.e., ACRIMA, ORIGA-Light, and RIM-ONE as well as locally available datasets, i.e., AFIO, and HMC. In the second stage, we propose an ensemble classifier with two novel ensembling techniques, i.e., accuracy based weighted voting, and accuracy/score based weighted averaging to further improve the glaucoma classification results. It is shown that ensemble with accuracy/score based scheme improves the accuracy (99.5%) for diverse databases. As an outcome of this study, it is presented that the NasNet-Large architecture is a feasible option in terms of its performance as a single classifier while ensemble classifier further improves the generalized performance for automatic glaucoma classification.
| [1] | S. Kingman, Glaucoma is second leading cause of blindness globally, Bull. World Health Organ., 82 (2014), 887–888. |
| [2] |
Y. C. Tham, X. Li, T. Y. Wong, H. A. Quigley, T. Aung, C. Y. Cheng, Global prevalence of glaucoma and projections of glaucoma burden through 2040: a systematic review and Meta-analysis, Ophthalmology, 121 (2014), 2081–2090. doi: 10.1016/j.ophtha.2014.05.013
|
| [3] |
H. Quigley, A. T. Broman, The number of people with glaucoma worldwide in 2010 and 2020, Br. J. Ophthalmol., 90 (2006), 262–267. doi: 10.1136/bjo.2005.081224
|
| [4] | J. Fuente-Arriaga, E. M Felipe-Riverón, E. Garduño-Calderón, Application of vascular bundle displacement in the optic disc for glaucoma detection using fundus images, Comput. Biol. Med., 47 (2014), 27–35. |
| [5] |
M. D. Abramoff, M. K. Garvin, M. Sonka, Retinal imaging and image analysis, IEEE Rev. Biomed. Eng., 3 (2010), 169–208. doi: 10.1109/RBME.2010.2084567
|
| [6] |
M. S. Haleem, L. Han, J. Van Hemert, B. Li, Automatic extraction of retinal features from colour retinal images for glaucoma diagnosis: a review, Comput. Med. Imaging Graphics, 37 (2013), 581–596. doi: 10.1016/j.compmedimag.2013.09.005
|
| [7] | M. Shakeri, S. Tsogkas, E. Ferrante, S. Lippe, S. Kadoury, N. Paragios, et al., Sub-cortical brain structure segmentation using f-cnn's, in 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI), (2016), 269–272. |
| [8] | M. Jaderberg, A. Vedaldi, A. Zisserman, Speeding up convolutional neural networks with low rank expansions, preprint, arXiv: 1405.3866. |
| [9] |
J. Lemley, S. Bazrafkan, P. Corcoran, Smart augmentation learning an optimal data augmentation strategy, IEEE Access, 5 (2017), 5858–5869. doi: 10.1109/ACCESS.2017.2696121
|
| [10] |
S. J. Pan, Q. Yang, A survey on transfer learning, IEEE Trans. Knowl. Data Eng., 22 (2010), 1345–1359. doi: 10.1109/TKDE.2009.191
|
| [11] | C. Li, D. Xue, X. Zhou, J. Zhang, H. Zhang, Y. Yao, et al., Transfer learning based classification of cervical cancer immunohistochemistry images, in ACM International Conference Proceeding Series, (2019), 102–106. |
| [12] |
A. Ghoneim, G. Muhammad, M. S. Hossain, Cervical cancer classification using convolutional neural networks and extreme learning machines, Future Gener. Comput. Syst., 102 (2020), 643–649. doi: 10.1016/j.future.2019.09.015
|
| [13] |
H. Parvin, M. MirnabiBaboli, H. A. Rokny, Proposing a classifier ensemble framework based on classifier selection and decision tree, Eng. Appl. Artif. Intell., 37 (2015), 34–42. doi: 10.1016/j.engappai.2014.08.005
|
| [14] | S. Maheshwari, V. Kanhangad, R. B. Pachori, Cnn-based approach for glaucoma diagnosis using transfer learning and lbp-based data augmentation, preprint, arXiv: 2002.08013. |
| [15] | A. Singh, S. Sengupta, V. Lakshminarayanan, Glaucoma diagnosis using transfer learning methods, in Applications of Machine Learning, International Society for Optics and Photonics, (2019). |
| [16] | A. Serener, S. Serte, Transfer learning for early and advanced glaucoma detection with convolutional neural networks, in 2019 Medical Technologies Congress (TIPTEKNO), (2019), 1–4. |
| [17] |
O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, et al., ImageNet large scale visual recognition challenge, Int. J. Comput. Vision, 115 (2015), 211–252. doi: 10.1007/s11263-015-0816-y
|
| [18] | H. N. Veena, A. Muruganandham, T. S. Kumaran, A novel optic disc and optic cup segmentation technique to diagnose glaucoma using deep learning convolutional neural network over retinal fundus images, J. King Saud Univ. Comput. Inf. Sci., (2021), forthcoming. |
| [19] | X. Chen, Y. Xu, D. W. K. Wong, T. Y. Wong, J. Liu, Glaucoma detection based on deep convolutional neural network, in 2015 37th annual international conference of the IEEE engineering in medicine and biology society (EMBC), (2015), 715–718. |
| [20] |
R. Asaoka, H. Murata, A. Iwase, M. Araie, Detecting preperimetric glaucoma with standard automated perimetry using a deep learning classifier, Ophthalmology, 123 (2016), 1974–1980. doi: 10.1016/j.ophtha.2016.05.029
|
| [21] | X. Chen, Y. Xu, S. Yan, D. Wong, T. Wong, J. Liu, Automatic feature learning for glaucoma detection based on deep learning, in International Conference on Medical Image Computing and Computer-Assisted Intervention, (2015), 669–677. |
| [22] | Q. Abbas, Glaucoma-deep: detection of glaucoma eye disease on retinal fundus images using deep learning, Int. J. Adv. Comput. Sci. Appl., 8 (2017), 41–45. |
| [23] | J. Orlando, E. Prokofyeva, M. del Fresno, M. B. Blaschko, Convolutional neural network transfer for automated glaucoma identification, in 12th international symposium on medical information processing and analysis, (2017). |
| [24] | A. Chakravarty, J. Sivswamy, A deep learning based joint segmentation and classification framework for glaucoma assesment in retinal color fundus images, preprint, arXiv: 1808.01355. |
| [25] |
Z. Li, Y. He, S. Keel, W. Meng, R. T. Chang, M. He, Efficacy of a deep learning system for detecting glaucomatous optic neuropathy based on color fundus photographs, Ophthalmology, 125 (2018), 1199–1206. doi: 10.1016/j.ophtha.2018.01.023
|
| [26] |
Y. Chai, H. Liu, J. Xu, Glaucoma diagnosis based on both hidden features and domain knowledge through deep learning models, Knowl. Based Syst., 161 (2018), 147–156. doi: 10.1016/j.knosys.2018.07.043
|
| [27] | M. Christopher, A. Belghith, C. Bowd, J. Proudfoot, M. Goldbaum, R. N. Weinreb, et al., Performance of deep learning architectures and transfer learning for detecting glaucomatous optic neuropathy in fundus photographs, Sci. Rep., 8 (2018), 1–13. |
| [28] |
N. Shibata, M. Tanito, K. Mitsuhashi, Y. Fujino, M. Matsuura, H. Murata, et al., Development of a deep residual learning algorithm to screen for glaucoma from fundus photography, Sci. Rep., 8 (2018), 14665. doi: 10.1038/s41598-018-33013-w
|
| [29] |
S. Liu, S. Graham, A. Schulz, M. Kalloniatis, B. Zangerl, W. Cai, et al., A deep learning-based algorithm identifies glaucomatous discs using monoscopic fundus photographs, Ophthalmol. Glaucoma, 1 (2018), 15–22. doi: 10.1016/j.ogla.2018.04.002
|
| [30] |
S. Gheisari, S. Shariflou, J. Phu, P. Kennedy, A. Agar, M. Kalloniatis, et al., A combined convolutional and recurrent neural network for enhanced glaucoma detection, Sci. Rep., 11 (2021), 1945. doi: 10.1038/s41598-021-81554-4
|
| [31] |
F. Li, L. Yan, Y. Wang, J. Shi, H. Chen, X. Zhang, et al., Deep learning-based automated detection of glaucomatous optic neuropathy on color fundus photographs, Graefe's Arch. Clin. Exp. Ophthalmol., 258 (2020), 851–867. doi: 10.1007/s00417-020-04609-8
|
| [32] | H. I. Elshazly, M. Waly, A. M. Elkorany, A. E. Hassanien, Chronic eye disease diagnosis using ensemble-based classifier, in 2014 International Conference on Engineering and Technology (ICET), (2014). |
| [33] |
J. Zilly, J. Buhmann, D. Mahapatra, Glaucoma detection using entropy sampling and ensemble learning for automatic optic cup and disc segmentation, Comput. Med. Imaging Graphics, 55 (2017), 28–41. doi: 10.1016/j.compmedimag.2016.07.012
|
| [34] |
H. Fu, J. Cheng, Y. Xu, C. Zhang, D. Wong, J. Liu, et al., Disc-aware ensemble network for glaucoma screening from fundus image, IEEE Trans. Med. Imaging, 37 (2018), 2493–2501. doi: 10.1109/TMI.2018.2837012
|
| [35] |
N. Gour, P. Khanna, Multi-class multi-label ophthalmological disease detection using transfer learning based convolutional neural network, Biomed. Signal Process. Control, 66 (2021), 102329. doi: 10.1016/j.bspc.2020.102329
|
| [36] | A. Bhuiyan, A. Govindaiah, R. T. Smith, An artificial intelligence and telemedicine based screening tool to identify glaucoma suspects from color fundus imaging, J. Ophthalmol., 2021 (2021), 6694784. |
| [37] |
A. Diaz-Pinto, S. Morales, V. Naranjo, T. Köhler, J. M. Mossi, A. Navea, Cnns for automatic glaucoma assessment using fundus images: an extensive validation, Biomed. Eng. Online, 18 (2019), 29. doi: 10.1186/s12938-019-0649-y
|
| [38] | Z. Zhang, F. S. Yin, J. Liu, W. K. Wong, N. M. Tan, B. H. Lee, et al., Origa-light: An online retinal fundus image database for glaucoma analysis and research, in 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology, IEEE, (2010). |
| [39] | F. Fumero, S. Alayón, J. L. Sanchez, J. Sigut, M. G.-Hernandez, Rim-one: An open retinal image database for optic nerve evaluation, in 2011 24th international symposium on computer-based medical systems (CBMS), IEEE, (2011). |
| [40] | P. R. Rajarapollu, V. R. Mankar, Bicubic interpolation algorithm implementation for image appearance enhancement, Int. J., 8 (2017). |
| [41] | J. Orlando, E. Prokofyeva, M. del Fresno, M. B. Blaschko, Convolutional neural network transfer for automated glaucoma identification, in 12th international symposium on medical information processing and analysis, (2017). |
| [42] | A. Krizhevsky, I. Sutskever, G. E. Hinton, Imagenet classification with deep convolutional neural networks, Adv. Neural Inf. Process. Syst., 25 (2012), 1097–1105. |
| [43] |
Y. LeCun, L. Bottou, Y. Bengio, P. Haffner, Gradient-based learning applied to document recognition, Proceed. IEEE, 86 (1998), 2278–2324. doi: 10.1109/5.726791
|
| [44] | C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, Z. Wojna, Rethinking the inception architecture for computer vision, in Proceedings of the IEEE conference on computer vision and pattern recognition, (2016), 2818–2826. |
| [45] | C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, et al., Going deeper with convolutions, in Proceedings of the IEEE conference on computer vision and pattern recognition, (2015), 1–9. |
| [46] |
H. C. Shin, H. R. Roth, M. Gao, L. Lu, Z. Xu, I. Nogues, et al., Deep convolutional neural networks for computer-aided detection: Cnn architectures, dataset characteristics and transfer learning, IEEE Trans. Med. Imaging, 35 (2016), 1285–1298. doi: 10.1109/TMI.2016.2528162
|
| [47] |
A. Kumar, J. Kim, D. Lyndon, M. Fulham, D. Feng, An ensemble of fine-tuned convolutional neural networks for medical image classification, IEEE J. Biomed. Health Inf., 21 (2017), 31–40. doi: 10.1109/JBHI.2016.2635663
|
| [48] | C. Szegedy, S. Ioffe, V. Vanhoucke, A. A. Alemi, Inception-v4, inception-resnet and the impact of residual connections on learning, in Thirty-first AAAI conference on artificial intelligence, (2017). |
| [49] | K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in Proceedings of the IEEE conference on computer vision and pattern recognition, (2016), 770–778. |
| [50] | B. Zoph, Q. V. Le, Neural architecture search with reinforcement learning, preprint, arXiv: 1611.01578. |
| [51] | D. T. Bui, T. D. Tran, T. T. Nguyen, Q. L. Tran, D. V. Nguyen, Aerial image semantic segmentation using neural search network architecture, in International Conference on Multi-disciplinary Trends in Artificial Intelligence, (2018), 113–124. |
| [52] |
S. Sabzi, R. Pourdarbani, D. Kalantari, T. Panagopoulos, Designing a fruit identification algorithm in orchard conditions to develop robots using video processing and majority voting based on hybrid artificial neural network, Appl. Sci., 10 (2020), 383. doi: 10.3390/app10010383
|
| [53] | N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, R. Salakhutdinov, Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res., 15 (2014), 1929–1958. |
| [54] |
A. Moayedikia, K. L. Ong, Y. L. Boo, W. Yeoh, R. Jensen, Feature selection for high dimensional imbalanced class data using harmony search, Eng. Appl. Artif. Intell., 57 (2017), 38–49. doi: 10.1016/j.engappai.2016.10.008
|
| [55] | D. M. W. Powers, Evaluation: from precision, recall and F-measure to Roc, informedness, markedness & correlation, preprint, arXiv: 2010.16061. |
| [56] |
U. Raghavendra, H. Fujita, S. V. Bhandary, A. Gudigar, J. H. Tan, U. R. Acharya, Deep convolution neural network for accurate diagnosis of glaucoma using digital fundus images, Inf. Sci., 441 (2018), 41–49. doi: 10.1016/j.ins.2018.01.051
|
| [57] | I. Memon, A. A. Ursani, M. A. Bohyo, R. Chandio, Automated diagnosis of glaucoma using deep learning architecture, Eng. Sci. Technol. Res. J., 3 (2019), 58–62. |
| [58] |
M. N. Bajwa, M. I. Malik, S. A. Siddiqui, A. Dengel, F. Shafait, W. Neumeier, et al., Two-stage framework for optic disc localization and glaucoma classification in retinal fundus images using deep learning, BMC Med. Inf. Decis. Making, 19 (2019), 136. doi: 10.1186/s12911-019-0842-8
|
| [59] | A. Cerentinia, D. Welfera, M. C. d'Ornellasa, C. J. P. Haygertb, G. N. Dottob, Automatic identification of glaucoma using deep learning methods, in MEDINFO 2017: Precision Healthcare Through Informatics: Proceedings of the 16th World Congress on Medical and Health Informatics, (2018). |
| [60] | B. A. Bander, W. A. Nuaimy, M. A. A. Taee, Y. Zheng, Automated glaucoma diagnosis using deep learning approach, in 2017 14th International Multi-Conference on Systems, Signals & Devices (SSD), IEEE, 2017. |
| [61] | M. Christopher, K. Nakahara, C. Bowd, J. A. Proudfoot, A. Belghith, M. H. Goldbaum, et al., Effects of study population, labeling and training on glaucoma detection using deep learning algorithms, Transl. Vision Sci. Technol., 9 (2020), 27. |
| [62] |
J. M. Ahn, S. Kim, K. S. Ahn, S. H. Cho, K. B. Lee, U. S. Kim, A deep learning model for the detection of both advanced and early glaucoma using fundus photography, Plos one, 13 (2018), e0207982. doi: 10.1371/journal.pone.0207982
|
| [63] |
S. Serte, A. Serener, Graph-based saliency and ensembles of convolutional neural networks for glaucoma detection, IET Image Process., 15 (2021), 797–804. doi: 10.1049/ipr2.12063
|
Figures(16) / Tables(8)
Aziz-ur-Rehman, Imtiaz A. Taj, Muhammad Sajid, Khasan S. Karimov. An ensemble framework based on Deep CNNs architecture for glaucoma classification using fundus photography[J]. Mathematical Biosciences and Engineering, 2021, 18(5): 5321-5346. doi: 10.3934/mbe.2021270
DownLoad: