Use of dominant activations obtained by processing OCT images with the CNNs and slime mold method in retinal disease detection

• Autorzy: Toğaçar Mesut , Ergen Burhan , Tümen Vedat

Identyfikatory

DOI

10.1016/j.bbe.2022.05.005

• Języki publikacji: EN

Abstrakty

EN

Retinal disease is one of the diseases that cause visual symptoms or loss of vision in humans. This disease can affect the choroid, which severely affects vision. Optical coherence tomography (OCT) images are usually used to detect retinal disease. OCT is an imaging technique that takes high-resolution slices of retinal images. It takes time for experts to examine and interpret the OCT images. Experts need to take advantage of technological capabilities to make this process faster and more accurate. Three datasets were used in this study. Dataset #1 (UCSD dataset) consists of choroidal neovascularization (CNV), diabetic macular edema (DME), drusen, and normal OCT image types. Dataset #2 (Duke dataset) and Dataset #3 consist of age-related macular degeneration (AMD), DME, and normal OCT image types. An artificial intelligence based hybrid approach was proposed for retinal disease detection. In the proposed approach, class-based activations were extracted for each model with nine transfer learning models using the dataset. Next, the dominant activations were selected from the model-based activations of each class using the slime mold algorithm (SMA) and the selected activations were classified using the softmax method. The overall accuracy obtained in classification is as follows: 99.60% for dataset 1, 99.89% for dataset #2 and 97.49% for dataset #3. In this study, it was found that the proposed approach contributes to the performance of transfer learning models.

Słowa kluczowe

EN

retinal disease; slime mold algorithm; transfer learning; selection of dominant activations; optical coherence tomography

PL

choroba siatkówki; transfer uczenia się; optyczna tomografia koherencyjna

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2022
• Tom: Vol. 42, no. 2
• Strony: 646--666
• Opis fizyczny: Bibliogr. 61 poz., rys., tab., wykr.

Twórcy

autor

Toğaçar Mesut

• Computer Technologies Department, Technical Sciences Vocational School, Fırat University, Elazığ , Turkey

• https://orcid.org/0000-0002-8264-3899

autor

Ergen Burhan

• Department of Computer Engineering, Faculty of Engineering, Fırat University Elazig, Turkey

• https://orcid.org/0000-0003-3244-2615

autor

Tümen Vedat

• Department of Computer Engineering, Faculty of Engineering and Architecture, Bitlis Eren University Bitlis, Turkey

• https://orcid.org/0000-0003-0271-216X

Bibliografia

• [1] Ibrahim MR, Fathalla KM, Youssef SM. A hybrid computer-aided diagnosis of retinopathy by optical coherence tomography integrating machine learning and feature maps localization. Appl Sci 2020;10:4716.
• [2] Saeedi P, Petersohn I, Salpea P, Malanda B, Karuranga S, Unwin N, et al. Global and regional diabetes prevalence estimates for 2019 and projections for 2030 and 2045: Results from the International Diabetes Federation Diabetes Atlas, 9th edition. Diabetes Res Clin Pract 2019;157:107843.
• [3] Tsuji T, Hirose Y, Fujimori K, Hirose T, Oyama A, Saikawa Y, et al. Classification of optical coherence tomography images using a capsule network. BMC Ophthalmol 2020;20:114. https://doi.org/10.1186/s12886-020-01382-4.
• [4] Tasnim N, Hasan M, Islam I. Comparisonal study of Deep Learning approaches on Retinal OCT Image 2019:23–4.
• [5] Bhende M, Shetty S, Parthasarathy MK, Ramya S. Optical coherence tomography: A guide to interpretation of common macular diseases. Indian J Ophthalmol 2018;66:20–35. https://doi.org/10.4103/ijo.IJO_902_17.
• [6] Feijóo C, Kwon Y, Bauer JM, Bohlin E, Howell B, Jain R, et al. Harnessing artificial intelligence (AI) to increase wellbeing for all: The case for a new technology diplomacy. Telecomm Policy 2020;44(6). https://doi.org/10.1016/j.telpol.2020.101988.
• [7] Davenport T, Guha A, Grewal D, Bressgott T. How artificial intelligence will change the future of marketing. J Acad Mark Sci 2020;48:24–42. https://doi.org/10.1007/s11747-019-00696-0.
• [8] Elsharkawy M, Sharafeldeen A, Soliman A, Khalifa F, Ghazal M, El-Daydamony E, et al. A novel computer-aided diagnostic system for early detection of diabetic retinopathy using 3DOCT higher-order spatial appearance model. Diagnostics 2022;12:461. https://doi.org/10.3390/diagnostics12020461.
• [9] Han J, Choi S, Park JI, Hwang JS, Han JM, Lee HJ, et al. Classifying neovascular age-related macular degeneration with a deep convolutional neural network based on optical coherence tomography images. Sci Rep 2022;12:2232. https://doi.org/10.1038/s41598-022-05903-7.
• [10] Pin K, Ho Chang J, Nam Y. Comparative study of transfer learning models for retinal disease diagnosis from fundus images. Comput Mater Contin 2022;70:5821–34. https://doi.org/10.32604/cmc.2022.021943.
• [11] Motozawa N, An G, Takagi S, Kitahata S, Mandai M, Hirami Y, et al. Optical coherence tomography-based deep-learning models for classifying normal and age-related macular degeneration and exudative and non-exudative age-related macular degeneration changes. Ophthalmol Ther 2019;8:527–39. https://doi.org/10.1007/s40123-019-00207-y.
• [12] Yoo TK, Choi JY, Kim HK. Feasibility study to improve deep learning in OCT diagnosis of rare retinal diseases with few-shot classification. Med Biol Eng Comput 2021;59:401–15. https://doi.org/10.1007/s11517-021-02321-1.
• [13] Yoo TK, Choi JY, Seo JG, Ramasubramanian B, Selvaperumal S, Kim DW. The possibility of the combination of OCT and fundus images for improving the diagnostic accuracy of deep learning for age-related macular degeneration: a preliminary experiment. Med Biol Eng Comput 2019;57:677–87. https://doi.org/10.1007/s11517-018-1915-z.
• [14] De Fauw J, Ledsam JR, Romera-Paredes B, Nikolov S, Tomasev N, Blackwell S, et al. Clinically applicable deep learning for diagnosis and referral in retinal disease. Nat Med 2018;24:1342–50. https://doi.org/10.1038/s41591-018-0107-6.
• [15] Wang J, Deng G, Li W, Chen Y, Gao F, Liu H, et al. Deep learning for quality assessment of retinal OCT images. Biomed Opt Express 2019;10:6057. https://doi.org/10.1364/BOE.10.006057.
• [16] Lin AC, Lee CS, Blazes M, Lee AY, Gorin MB. Assessing the clinical utility of expanded macular OCTs using machine learning. Transl Vis Sci Technol 2021;10:32. https://doi.org/10.1167/tvst.10.6.32.
• [17] Li F, Chen H, Liu Z, Zhang X-D, Jiang M-S, Wu Z-Z, et al. Deep learning-based automated detection of retinal diseases using optical coherence tomography images. Biomed Opt Express 2019;10(12):6204. https://doi.org/10.1364/BOE.10.006204.
• [18] A p S, Kar S, S G, Gopi VP, Palanisamy P. OctNET: A lightweight CNN for retinal disease classification from optical coherence tomography images. Comput Methods Programs Biomed 2021;200:105877. https://doi.org/10.1016/j.cmpb.2020.105877.
• [19] Mittal P, Bhatnagar C. Retinal disease classification using convolutional neural networks algorithm. Turk J Comput Math Educ 2021;12:5681–9.
• [20] Mooney P. Retinal OCT Images (optical coherence tomography). Kaggle 2018. https://www.kaggle.com/paultimothymooney/kermany2018 (accessed June 10, 2021).
• [21] Srinivasan PP, Kim LA, Mettu PS, Cousins SW, Comer GM, Izatt JA, et al. Fully automated detection of diabetic macular edema and dry age-related macular degeneration from optical coherence tomography images. Biomed Opt Express 2014;5:3568. https://doi.org/10.1364/BOE.5.003568.
• [22] Rasti R, Rabbani H, Mehridehnavi A, Hajizadeh F. Macular OCT classification using a multi-scale convolutional neural network ensemble. IEEE Trans Med Imaging 2018;37:1024–34. https://doi.org/10.1109/tmi.2017.2780115.
• [23] Tsiakmaki M, Kostopoulos G, Kotsiantis S, Ragos O. Transfer learning from deep neural networks for predicting student performance. Appl Sci 2020;10:2145. https://doi.org/10.3390/app10062145.
• [24] Toğaçar M, Ergen B. Biyomedikal Görüntülerde Derin Öğrenme ile Mevcut Yöntemlerin Kıyaslanması. Fırat Üniversitesi Mühendislik Bilim Derg 2019;31:109–21.
• [25] Lundervold AS, Lundervold A. An overview of deep learning in medical imaging focusing on MRI. Z Med Phys 2019;29:102–27. https://doi.org/10.1016/j.zemedi.2018.11.002.
• [26] Alshazly H, Linse C, Barth E, Martinetz T. Ensembles of deep learning models and transfer learning for ear recognition. Sensors (Basel) 2019;19:4139. https://doi.org/10.3390/s19194139.
• [27] Baykal E, Dogan H, Ercin ME, Ersoz S, Ekinci M. Transfer learning with pre-trained deep convolutional neural networks for serous cell classification. Multimed Tools Appl 2020;79:15593–611. https://doi.org/10.1007/s11042-019-07821-9.
• [28] Diker A, Comert Z, Avci E, Togacar M, Ergen B. A novel application based on spectrogram and convolutional neural network for ECG classification. In: 1st Int. Informatics Softw. Eng. Conf., IEEE; 2019, p. 1–6. doi:10.1109/UBMYK48245.2019.8965506.
• [29] Shao S, Li Z, Zhang T, Peng C, Yu G, Zhang X, et al. Objects365: A large-scale, high-quality dataset for object detection. In: 2019 IEEE/CVF Int. Conf. Comput. Vis., 2019, p. 8429–38. doi:10.1109/iccv.2019.00852.
• [30] Wang Y, Wang C, Zhang H. Ship classification in high-resolution SAR images using deep learning of small datasets. Sensors (Basel) 2018;18:2929. https://doi.org/10.3390/s18092929.
• [31] Pretrained Deep Neural Networks - MATLAB & Simulink. MathWorks 2021. https://www.mathworks.com/help/deeplearning/ug/pretrained-convolutional-neural-networks.html (accessed June 11, 2021).
• [32] Yamashita R, Nishio M, Do RKG, Togashi K. Convolutional neural networks: an overview and application in radiology. Insights Imaging 2018;9:611–29. https://doi.org/10.1007/s13244-018-0639-9.
• [33] dos Santos CFG, Moreira TP, Colombo D, Papa JP. Does removing pooling layers from convolutional neural networks improve results? SN Comput Sci 2020;1:275. https://doi.org/10.1007/s42979-020-00295-9.
• [34] Rachapudi V, Lavanya Devi G. Improved convolutional neural network based histopathological image classification. Evol Intell 2021;14(3):1337–43.
• [35] Wang M, Lu S, Zhu D, Lin J, Wang Z. A high-speed and low-complexity architecture for softmax function in deep learning. In: IEEE Asia Pacific Conf. Circuits Syst., 2018, p. 223–6. doi:10.1109/apccas.2018.8605654.
• [36] Kandel I, Castelli M. The effect of batch size on the generalizability of the convolutional neural networks on a histopathology dataset. ICT Express 2020;6:312–5. https://doi.org/10.1016/j.icte.2020.04.010.
• [37] Li S, Chen H, Wang M, Heidari AA, Mirjalili S. Slime mould algorithm: A new method for stochastic optimization. Futur Gener Comput Syst 2020;111:300–23. https://doi.org/10.1016/j.future.2020.03.055.
• [38] Dhawale D, Kamboj VK, Anand P. An effective solution to numerical and multi-disciplinary design optimization problems using chaotic slime mold algorithm. Eng Comput 2021. https://doi.org/10.1007/s00366-021-01409-4.
• [39] Ewees AA, Abualigah L, Yousri D, Algamal ZY, Al-qaness MAA, Ibrahim RA, et al. Improved Slime Mould Algorithm based on Firefly Algorithm for feature selection: A case study on QSAR model. Eng Comput 2021. https://doi.org/10.1007/s00366-021-01342-6.
• [40] Nguyen T-T, Wang H-J, Dao T-K, Pan J-S, Liu J-H, Weng S. An improved slime mold algorithm and its application for optimal operation of cascade hydropower stations. IEEE Access 2020;8:226754–72. https://doi.org/10.1109/access.2020.3045975.
• [41] Heidari AA. Slime mould algorithm a new method for stochastic optimization. GitHub 2020. https://github.com/aliasghar68/Slime-Mould-Algorithm-A-New-Method-for-Stochastic-Optimization- (accessed June 10, 2021).
• [42] Toğaçar M, Ergen B, Sertkaya ME. Zatürre Hastalığının Derin Öğrenme Modeli ile Tespiti. Fırat Üniversitesi Mühendislik Bilim Derg 2019;31:223–30.
• [43] Rahmad F, Suryanto Y, Ramli K. Performance comparison of anti-spam technology using confusion matrix classification. IOP Conf Ser Mater Sci Eng 2020;879:12076. https://doi.org/10.1088/1757-899x/879/1/012076.
• [44] Chicco D, Jurman G. The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC Genomics 2020;21:6. https://doi.org/10.1186/s12864-019-6413-7.
• [45] Alsaggaf W, Cömert Z, Nour M, Polat K, Brdesee H, Toğaçar M. Predicting fetal hypoxia using common spatial pattern and machine learning from cardiotocography signals. Appl Acoust 2020;167. https://doi.org/10.1016/j.apacoust.2020.107429 107429.
• [46] Toğaçar M, Ergen B, Cömert Z. Tumor type detection in brain MR images of the deep model developed using hypercolumn technique, attention modules, and residual blocks. Med Biol Eng Comput 2021;59:57–70. https://doi.org/10.1007/s11517-020-02290-x.
• [47] Lawrence T, Zhang L. IoTNet: an efficient and accurate convolutional neural network for IoT devices. Sensors (Basel) 2019;19:5541. https://doi.org/10.3390/s19245541.
• [48] Xu S. Bayesian Naïve Bayes classifiers to text classification. J Inf Sci 2018;44:48–59. https://doi.org/10.1177/0165551516677946.
• [49] Li Y, Li L, Fang Y, Peng H, Yang Y. Bagged tree based frame-wise beforehand prediction approach for HEVC intra-coding unit partitioning. Electron 2020;9:1523. https://doi.org/10.3390/electronics9091523.
• [50] Gul N, Khan MS, Kim SM, Kim J, Elahi A, Khalil Z. Boosted trees algorithm as reliable spectrum sensing scheme in the presence of malicious users. Electron 2020;9(6):1038. https://doi.org/10.3390/electronics9061038.
• [51] Mounce SR, Ellis K, Edwards JM, Speight VL, Jakomis N, Boxall JB. Ensemble decision tree models using RUSBoost for estimating risk of iron failure in drinking water distribution systems. Water Resour Manag 2017;31:1575–89. https://doi.org/10.1007/s11269-017-1595-8.
• [52] Ashour AS, Guo Y, Hawas AR, Xu G. Ensemble of subspace discriminant classifiers for schistosomal liver fibrosis staging in mice microscopic images. Heal Inf Sci Syst 2018;6:21. https://doi.org/10.1007/s13755-018-0059-8.
• [53] Adem K. Diagnosis of breast cancer with stacked autoencoder and subspace kNN. Phys A Stat Mech Its Appl 2020;551. https://doi.org/10.1016/j.physa.2020.124591 124591.
• [54] Peralta B, Saavedra A, Caro L, Soto A. Mixture of experts with entropic regularization for data classification. Entropy 2019;21:190. https://doi.org/10.3390/e21020190.
• [55] Shibui Y. Mixture of experts source code. Github 2021. https://github.com/shibuiwilliam/mixture_of_experts_keras/blob/master/MoE_MNIST2.ipynb (accessed September 20, 2021).
• [56] Choi JY, Yoo TK, Seo JG, Kwak J, Um TT, Rim TH, et al. Multi-categorical deep learning neural network to classify retinal images: A pilot study employing small database. PLoS ONE 2017;12.
• [57] Mou L, Liang L, Gao Z, Wang X. A multi-scale anomaly detection framework for retinal OCT images based on the Bayesian neural network. Biomed Signal Process Control 2022;75. https://doi.org/10.1016/j.bspc.2022.103619 103619.
• [58] Tasnim N, Hasan M, Islam I. Comparisonal study of deep learning approaches on retinal OCT image. Int Conf Innov Eng Technol 2019:23–4.
• [59] He T, Zhou Q, Zou Y. Automatic detection of age-related macular degeneration based on deep learning and local outlier factor algorithm. Diagnostics 2022;12(2):532.
• [60] Sun Y, Li S, Sun Z. Fully automated macular pathology detection in retina optical coherence tomography images using sparse coding and dictionary learning. J Biomed Opt 2017;22. https://doi.org/10.1117/1.jbo.22.1.016012.
• [61] Thomas A, Harikrishnan PM, Ramachandran R, Ramachandran S, Manoj R, Palanisamy P, et al. A novel multiscale and multipath convolutional neural network based age-related macular degeneration detection using OCT images. Comput Methods Programs Biomed 2021;209. https://doi.org/10.1016/j.cmpb.2021.106294.