Retina disorders are among the common types of eye disease that occur due to several reasons such as aging, diabetes and premature born. Besides, Optical Coherence Tomography (OCT) is a medical imaging method that serves as a vehicle for capturing volumetric scans of the human eye retina for diagnoses purposes. This research compared two pretraining approaches including Self-Supervised Learning (SSL) and Transfer Learning (TL) to train ResNet34 neural architecture aiming at building computer aided diagnoses tool for retina disorders recognition. In addition, the research methodology employs convolutional auto-encoder model as a generative SSL pretraining method. The research efforts are implemented on a dataset that contains 109,309 retina OCT images with three medical conditions including Choroidal Neovascularization (CNV), Diabetic Macular Edema (DME), DRUSEN as well as NORMAL condition. The research outcomes showed better performance in terms of overall accuracy, sensitivity and specificity, namely, 95.2%, 95.2% and 98.4% respectively for SSL ResNet34 in comparison to scores of 90.7%, 90.7% and 96.9% respectively for TL ResNet34. In addition, SSL pretraining approach showed significant reduction in the number of epochs required for training in comparison to both TL pretraining as well as the previous research performed on the same dataset with comparable performance.

[1] Albarrak A., Coenen F., and Zheng Y., “Age- related Macular Degeneration Identification in Volumetric Optical Coherence Tomography Using Decomposition and Local Feature Extraction,” in Proceedings of the International Conference on Medical Image, Understanding and Analysis, Aberdeen, pp. 59-64, 2013.

[2] Alqudah A., “A Oct-Net: a Convolutional Network Automated Classification of Multiclass Retinal Diseases Using Spectral-Domain Optical Coherence Tomography Images,” Medical and Biological Engineering and Computing, vol. 58, no. 1, pp. 41-53, 2020.

[3] Alsaih K., Lemaitre G., Rastgoo M., Massich J., Sidibé D., and Meriaudeau F., “Machine Learning Techniques for Diabetic Macular Edema (DME) Classification on SD-OCT Images,” Biomedical Engineering Online, vol. 16, no. 1, pp. 68, 2017.

[4] Apostolopoulos S., Ciller C., De Zanet S., Wolf S., and Sznitman R., “Retinet: Automatic Age- related Macular Degeneration Identification in OCT Volumetric Data,” Investigative Ophthalmology and Visual Science, vol. 58, no. 8, pp. 387, 2017.

[5] Auw-Haedrich C., Staubach F., and Witschel H., “Optic Disk Drusen,” Survey of Ophthalmology, vol. 47, no. 6, pp. 515-532, 2002.

[6] Bhagat N., Grigorian R., Tutela A., and Zarbin M., “Diabetic Macular Edema: Pathogenesis and Treatment,” Survey of Ophthalmology, vol. 54, no. 1, pp. 1-32, 2009.

[7] Chen L., Bentley P., Mori K., Misawa K., Fujiwara M., and Rueckert D., “Self-supervised Learning for Medical Image Analysis Using Image Context Restoration,” Medical Image Analysis, vol. 58, pp. 101539, 2019.

[8] Deng J., Dong W., Socher R., Li L., Li K., and Fei-Fei L., “ImageNet: A Large-Scale Hierarchical Image Database,” in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Miami, pp. 248-255, 2009.

[9] Drexler W. and Fujimoto J., “State-of-the-Art Retinal Optical Coherence Tomography,” Progress in Retinal and Eye Research, vol. 27, no. 1, pp. 45-88, 2008.

[10] Dumar A. and Arias J., “Choroidal Neovascularization: OCT Angiography Findings,” https://eyewiki.aao.org/Choroidal_Neovasculariz Retina Disorders Classification via OCT Scan: A Comparative Study between ... 365 ation:_OCT_Angiography_Findings, Last Visited, 2023.

[11] Ellahham S., Ellahham N., and Simsekler M., “Application of Artificial Intelligence in the Health Care Safety Context: Opportunities and Challenges,” American Journal of Medical Quality, vol. 35, no. 4, pp. 341-348, 2020.

[12] Fang L., Jin Y., Huang L., Guo S., Zhao G., and Chen X., “Iterative Fusion Convolutional Neural Networks for Classification of Optical Coherence Tomography Images,” Journal of Visual Communication and Image Representation, vol. 59, pp. 327-333, 2019.

[13] Farsiu S., Chiu S., O’Connell R., Folgar F., Yuan E., Izatt J., and Toth C., “Quantitative Classification of Eyes with and without Intermediate Macular Degeneration Using Optical Coherence Tomography,” Ophthalmology, vol. 121, no. 1, pp. 162-172, 2014.

[14] Goodfellow I., Bengio Y., and Courville Y., Deep Learning, The MIT Press, 2016.

[15] Hameed S., Ashraf M., and Ya-nan Q., “Multi- lingual Language Variety Identification Using Conventional Deep Learning and Transfer Learning Approaches,” The International Arab Journal on Information Technology, vol. 19, no. 5, pp. 705-712, 2022.

[16] He K., Zhang X., Ren S., and Sun J., “Deep Residual Learning for Image Recognition,” in Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, Las Vegas, pp. 770-778, 2016.

[17] Hussain M., Bhuiyan A., Luu C., Smith R., Guymer R., Ishikawa H., Schuman J., and Ramamohanarao K., “Classification of Healthy and Diseased Retina Using SD-OCT Imaging and Random Forest Algorithm,” PloS One, vol. 13, no. 6, pp. 0198281, 2018.

[18] Karpathy A., “Cs231n: Convolutional Neural Networks for Visual Recognition,” http://cs231n.stanford.edu/2016/, 2016, Last Visited, 2023.

[19] Ker J., Wang L., Rao J., and Lim T., “Deep Learning Applications in Medical Image Analysis,” IEEE Access, vol. 6, pp. 9375-9389, 2017.

[20] Kermany D., Goldbaum M., Cai W., Valentim C., Liang H., Baxter S., McKeown A., Yang G., and et al., “Identifying Medical Diagnoses and Treatable Diseases by Image-based Deep Learning,” Cell, vol. 172, no. 5, pp. 1122-1131, 2018.

[21] Kermany D., Zhang K., and Goldbaum M., “Large Dataset of Labeled Optical Coherence Tomography and Chest X-Ray Images,” Mendeley Data, vol. 172, no. 5, pp. 1122-1131, 2018.

[22] Koh J., Acharya U., Hagiwara Y., Raghavendra U., Tan J., Sree S., Bhandary S., Rao A., Sivaprasad S., Chua K., Laude A., and Tong L., “Diagnosis of Retinal Health in Digital Fundus Images Using Continuous Wavelet Transform and Entropies,” Computers in Biology and Medicine, vol. 84, pp. 89-97, 2017.

[23] LeCun Y., Bengio Y., and Hinton G., “Deep Learning,” Nature, vol. 521, no. 7553, pp. 436- 444, 2015.

[24] Lee C., Baughman D., and Lee A., “Deep Learning is Effective for Classifying Normal Versus Age-related Macular Degeneration OCT Images,” Ophthalmology Retina, vol. 1, no. 4, pp. 322-327, 2017.

[25] Lemaitre G., Rastgoo M., Massich J., Sankar S., Mériaudeau F., and Sidibé D., “Classification of SD-OCT volumes with LBP: application to DME Detection,” in Proceedings of the Ophthalmic Medical Image Analysis International Workshop, Munich, pp. 9-16, 2015.

[26] Lemaître G., Rastgoo M., Massich J., Cheung C., Wong T., Lamoureux E., Milea D., Mériaudeau F., and Sidibé D., “Classification of SD-OCT Volumes Using Local Binary Patterns: Experimental Validation for DME Detection,” Journal of Ophthalmology, vol. 2016, 2016.

[27] Li F., Chen H., Liu Z., Zhang X., and Wu Z., “Fully Automated Detection of Retinal Disorders by Image-based Deep Learning,” Graefe’s Archive for Clinical and Experimental Ophthalmology, vol. 257, no. 3, pp. 495-505, 2019.

[28] Liu Y., Chen M., Ishikawa H., Wollstein G., Schuman J., and Rehg J., “Automated Macular Pathology Diagnosis in Retinal OCT Images Using Multi-Scale Spatial Pyramid and Local Binary Patterns in Texture and Shape Encoding,” Medical Image Analysis, vol. 15, no. 5, pp. 748- 759, 2011.

[29] Liu X., Zhang F., Hou Z., Wang Z., Mian L., Zhang J., and Tang J., “Self-supervised Learning: Generative or Contrastive,” arXiv preprint arXiv:2006.08218, 2020.

[30] Maggipinto M., Masiero C., Beghi A., and Susto G., “A Convolutional Autoencoder Approach for Feature Extraction in Virtual Metrology,” Procedia Manufacturing, vol. 17, pp. 126-133, 2018.

[31] Micikevicius P., Narang S., Alben J., Diamos G., Elsen E., Garcia D., Ginsburg B., Houston M., Kuchaiev O., Venkatesh G., and Wu H., “Mixed Precision Training,” in Proceedings of the 6th International Conference on Learning Representations, Vancouver, pp. 1-12, 2018.

[32] Nugroho K., “A Comparison of Handcrafted and Deep Neural Network Feature Extraction for Classifying Optical Coherence Tomography 366 The International Arab Journal of Information Technology, Vol. 20, No. 3, May 2023 (OCT) Images,” in Proceedings of the 2nd International Conference on Informatics and Computational Sciences, Semarang, pp. 1-6, 2018.

[33] Olivas E., Guerrero J., Martinez-Sober M., Magdalena-Benedito J., Serrano L., Benedito J., and Lopez A., Handbook of Research on Machine Learning Applications and Trends: Algorithms, Methods, and Technique, IGI Global, 2009.

[34] Perdomo O., Rios H., Rodríguez F., Otálora S., Meriaudeau F., Müller H., and González F., “Classification of Diabetes-Related Retinal Diseases Using a Deep Learning Approach in Optical Coherence Tomography,” Computer Methods and Programs in Biomedicine, vol. 178, pp. 181-189, 2019.

[35] Rastogi D., Padhy R., and Sa P., “Detection of Retinal Disorders in Optical Coherence Tomography Using Deep Learning,” in Proceedings of the 10th International Conference on Computing, Communication and Networking Technologies, Kharagpur, pp. 1-7, 2019.

[36] Schlegl T., Waldstein S., Bogunovic H., Endstraßer F., Sadeghipour A., Philip A., Podkowinski D., Gerendas B., Langs G., and Schmidt-Erfurth U., “Fully Automated Detection and Quantification of Macular Fluid in OCT Using Deep Learning,” Ophthalmology, vol. 125, no. 4, pp. 549-558, 2018.

[37] Shah S., “Blindness and Visual Impairment due to Retinal Diseases,” Community Eye Health, vol. 22, no. 69, pp. 8, 2009.

[38] Shiraishi J., Li Q., Appelbaum D., and Doi K., “Computer-Aided Diagnosis and Artificial Intelligence in Clinical Imaging,” Seminars in Nuclear Medicine, vol. 41, n. 6, pp. 449-462, 2011.

[39] Silvestri G., Williams M., McAuley C., Oakes K., Sillery E., Henderson D., Ferguson S., Silvestri V., and Muldrew K., “Drusen Prevalence and Pigmentary Changes in Caucasians Aged 18-54 Years,” Eye, vol. 26, no. 10, pp. 1357-1362, 2012.

[40] Srinivasan P., Kim L., Mettu P., Cousins S., Comer G., Izatt J., and Farsiu S., “Fully Automated Detection of Diabetic Macular Edema and Dry Age-related Macular Degeneration from Optical Coherence Tomography Images,” Biomedical Optics Express, vol. 5, no. 10, pp. 3568-3577, 2014.

[41] Sun Z., and Sun Y., “Automatic Detection of Retinal Regions Using Fully Convolutional Networks for Diagnosis of Abnormal Maculae in Optical Coherence Tomography Images,” Journal of Biomedical Optics, vol. 24, no. 5, pp. 056003, 2019.

[42] Venhuizen F., Ginneken B., Bloemen B., Grinsven M., Philipsen R., Hoyng C., Theelen T., and Sánchez C., “Automated Age-related Macular Degeneration Classification in OCT Using Unsupervised Feature Learning,” Medical Imaging: Computer-Aided Diagnosis, International Society for Optics and Photonics, vol. 9414, pp. 391-397, 2015.

[43] Venhuizen F., Ginneken B., Asten F., Grinsven M., Fauser S., Hoyng C., Theelen T., and Sánchez C., “Automated Staging of Age-related Macular Degeneration Using Optical Coherence Tomography,” Investigative Ophthalmology and Visual Science, vol. 58, no. 4, pp. 2318-2328, 2017.

[44] Wilkinson C., Ferris F., Klein R., Lee P., Agardh C., Davis M., Dills D., Kampik A., Pararajasegaram R., and Verdaguer J., “Proposed International Clinical Diabetic Retinopathy and Diabetic Macular Edema Disease Severity Scales,” Ophthalmology, vol. 110, no. 9, pp. 1677-1682, 2003.

[45] Xiang D., Tian H., Yang X., Shi F., Zhu W., Chen H., and Chen X., “Automatic Segmentation of Retinal Layer in OCT Images with Choroidal Neovascularization,” IEEE Transactions on Image Processing, vol. 27, no. 12, pp. 5880-5891, 2018.

[46] Yang X., He X., Liang Y., Yang Y., Zhang S., and Xie P., “Transfer Learning or Self- supervised Learning? A Tale of Two Pre- training Paradigms,” arXiv preprint arXiv:2007.04234, 2020.