DOI:
https://doi.org/10.59247/sjer.v1i2.14Keywords:
BIOMISA dataset, Semi-Supervised Learning, Retinal Disease Detection, Future DirectionAbstract
Proper immediate identification of Age-related Macular Degeneration (AMD) together with Central Serous Retinopathy (CSR) and Macular Edema (ME) is crucial for protecting vision. OCT imaging achieves better condition detection through automated model-based detection processes. The majority of studies in this domain utilize supervised learning because these approaches need large labeled dataset resources. The method confronts two essential obstacles due to limited medical data labeling quality, expensive expert training costs, and with irregular medical condition distributions. The considered factors limit practical implementation of these methods and their meaningful expansions. The study evaluates how semi-supervised learning techniques analyze retinal diseases in images that originate from the BIOMISA Macula database while providing diagnostic details about AMD, CSR, and ME in addition to Normal retinal results. SSL functions uniquely from fully supervised methods through its unique capability to process labeled and unlabeled data, which lowers manual annotation needs while improving generalized output performance. SSL delivers better results than traditional supervised learning practices through its ability to manage class irregularities and process extensive medical image files. The establishment of SSL as an attractive third option in medical settings with limited labeled data proves through research findings. The study provides insights regarding SSL use in diagnosis of retinal diseases alongside demonstrating its medical potential in healthcare environments. Future investigation designs improved deep learning algorithms which would enable higher system scalability and cost-effective diagnostics for ophthalmic disease systems.
References
[1] C. Zheng et al., “Development and Clinical Validation of Semi-Supervised Generative Adversarial Networks for Detection of Retinal Disorders in Optical Coherence Tomography Images Using Small Dataset,” Asia-Pacific Journal of Ophthalmology, vol. 11, no. 3, pp. 219–226, May 2022, doi: 10.1097/APO.0000000000000498.
[2] M. A. Rodríguez, H. AlMarzouqi, and P. Liatsis, “Multi-Label Retinal Disease Classification Using Transformers,” IEEE J Biomed Health Inform, vol. 27, no. 6, pp. 2739–2750, Jun. 2023, doi: 10.1109/JBHI.2022.3214086.
[3] S. Ahn, S. J. Song, and J. Shin, “FundusGAN: Fundus image synthesis based on semi-supervised learning,” Biomed Signal Process Control, vol. 86, p. 105289, Sep. 2023, doi: 10.1016/j.bspc.2023.105289.
[4] C. Zhang, P. Chen, and T. Lei, “Multi-point attention-based semi-supervised learning for diabetic retinopathy classification,” Biomed Signal Process Control, vol. 80, p. 104412, Feb. 2023, doi: 10.1016/j.bspc.2022.104412.
[5] Y. Jeong, Y.-J. Hong, and J.-H. Han, “Review of Machine Learning Applications Using Retinal Fundus Images,” Diagnostics, vol. 12, no. 1, p. 134, Jan. 2022, doi: 10.3390/diagnostics12010134.
[6] M. E. Subasi, S. Patnaik, and A. Subasi, “Optical coherence tomography image classification for retinal disease detection using artificial intelligence,” in Applications of Artificial Intelligence in Healthcare and Biomedicine, Elsevier, 2024, pp. 289–323. doi: 10.1016/B978-0-443-22308-2.00009-3.
[7] S. Jana, R. Parekh, and B. Sarkar, “A semi-supervised approach for automatic detection and segmentation of optic disc from retinal fundus image,” in Handbook of Computational Intelligence in Biomedical Engineering and Healthcare, Elsevier, 2021, pp. 65–91. doi: 10.1016/B978-0-12-822260-7.00012-1.
[8] S. Yao, Y. Zhang, J. Chen, Q. Lu, and Z. Zhao, “Enhancing identification performance of cognitive impairment high-risk based on a semi-supervised learning method,” J Biomed Inform, vol. 157, p. 104699, Sep. 2024, doi: 10.1016/j.jbi.2024.104699.
[9] F. Hosseini, F. Asadi, R. Rabiei, F. Kiani, and R. E. Harari, “Applications of artificial intelligence in diagnosis of uncommon cystoid macular edema using optical coherence tomography imaging: A systematic review,” Surv Ophthalmol, vol. 69, no. 6, pp. 937–944, Nov. 2024, doi: 10.1016/j.survophthal.2024.06.005.
[10] K. M. Adal, D. Sidibé, S. Ali, E. Chaum, T. P. Karnowski, and F. Mériaudeau, “Automated detection of microaneurysms using scale-adapted blob analysis and semi-supervised learning,” Comput Methods Programs Biomed, vol. 114, no. 1, pp. 1–10, Apr. 2014, doi: 10.1016/j.cmpb.2013.12.009.
[11] M. H. Shahriari, H. Sabbaghi, F. Asadi, A. Hosseini, and Z. Khorrami, “Artificial intelligence in screening, diagnosis, and classification of diabetic macular edema: A systematic review,” Surv Ophthalmol, vol. 68, no. 1, pp. 42–53, Jan. 2023, doi: 10.1016/j.survophthal.2022.08.004.
[12] W. Li et al., “Semi-supervised segmentation of orbit in CT images with paired copy-paste strategy,” Comput Biol Med, vol. 171, p. 108176, Mar. 2024, doi: 10.1016/j.compbiomed.2024.108176.
[13] Á. S. Hervella, J. Rouco, J. Novo, and M. Ortega, “Self-supervised multimodal reconstruction pre-training for retinal computer-aided diagnosis,” Expert Syst Appl, vol. 185, p. 115598, Dec. 2021, doi: 10.1016/j.eswa.2021.115598.
[14] Y. Tang, S. Wang, Y. Qu, Z. Cui, and W. Zhang, “Consistency and adversarial semi-supervised learning for medical image segmentation,” Comput Biol Med, vol. 161, p. 107018, Jul. 2023, doi: 10.1016/j.compbiomed.2023.107018.
[15] Z. Qi et al., “Automated Classification of Inherited Retinal Diseases in Optical Coherence Tomography Images Using Few-shot Learning,” Biomedical and Environmental Sciences, vol. 36, no. 5, pp. 431–440, 2023.
[16] S. Suman, A. K. Tiwari, and K. Singh, “Computer-aided diagnostic system for hypertensive retinopathy: A review,” Comput Methods Programs Biomed, vol. 240, p. 107627, Oct. 2023, doi: 10.1016/j.cmpb.2023.107627.
[17] X. Liu, X. Zhu, Y. Zhang, and M. Wang, “Point based weakly semi-supervised biomarker detection with cross-scale and label assignment in retinal OCT images,” Comput Methods Programs Biomed, vol. 251, p. 108229, Jun. 2024, doi: 10.1016/j.cmpb.2024.108229.
[18] R. Mohanasundaram, A. S. Malhotra, R. Arun, and P. S. Periasamy, “Deep Learning and Semi-Supervised and Transfer Learning Algorithms for Medical Imaging,” in Deep Learning and Parallel Computing Environment for Bioengineering Systems, Elsevier, 2019, pp. 139–151. doi: 10.1016/B978-0-12-816718-2.00015-4.
[19] Y. Wang et al., “AMSC-Net: Anatomy and multi-label semantic consistency network for semi-supervised fluid segmentation in retinal OCT,” Expert Syst Appl, vol. 249, p. 123496, Sep. 2024, doi: 10.1016/j.eswa.2024.123496.
[20] D. Mahapatra, “Semi-supervised learning and graph cuts for consensus based medical image segmentation,” Pattern Recognit, vol. 63, pp. 700–709, Mar. 2017, doi: 10.1016/j.patcog.2016.09.030.
[21] T. Hassan, H. Raja, B. Hassan, M. U. Akram, J. Dias, and N. Werghi, “A Composite Retinal Fundus and OCT Dataset to Grade Macular and Glaucomatous Disorders,” in 2022 2nd International Conference on Digital Futures and Transformative Technologies (ICoDT2), IEEE, May 2022, pp. 1–6. doi: 10.1109/ICoDT255437.2022.9787482.
[22] B. Hassan and T. Hassan, “Fully automated detection, grading and 3D modeling of maculopathy from OCT volumes,” in 2019 2nd International Conference on Communication, Computing and Digital systems (C-CODE), IEEE, Mar. 2019, pp. 252–257. doi: 10.1109/C-CODE.2019.8680996.
[23] A. M. Syed, T. Hassan, M. U. Akram, S. Naz, and S. Khalid, “Automated diagnosis of macular edema and central serous retinopathy through robust reconstruction of 3D retinal surfaces,” Comput Methods Programs Biomed, vol. 137, pp. 1–10, Dec. 2016, doi: 10.1016/j.cmpb.2016.09.004.
[24] Y. Wang, Y. Zhang, Z. Yao, R. Zhao, and F. Zhou, “Machine learning based detection of age-related macular degeneration (AMD) and diabetic macular edema (DME) from optical coherence tomography (OCT) images,” Biomed Opt Express, vol. 7, no. 12, p. 4928, Dec. 2016, doi: 10.1364/BOE.7.004928.
[25] S. Khalid, M. U. Akram, T. Hassan, A. Nasim, and A. Jameel, “Fully Automated Robust System to Detect Retinal Edema, Central Serous Chorioretinopathy, and Age Related Macular Degeneration from Optical Coherence Tomography Images,” Biomed Res Int, vol. 2017, pp. 1–15, 2017, doi: 10.1155/2017/7148245.
[26] T. Hassan, M. U. Akram, N. Werghi, and M. N. Nazir, “RAG-FW: A Hybrid Convolutional Framework for the Automated Extraction of Retinal Lesions and Lesion-Influenced Grading of Human Retinal Pathology,” IEEE J Biomed Health Inform, vol. 25, no. 1, pp. 108–120, Jan. 2021, doi: 10.1109/JBHI.2020.2982914.
[27] B. Nelson, H. Pandiyapallil Abdul Khadir, and S. Odattil, “Detection of CSR from Blue Wave Fundus Autofluorescence Images using Deep Neural Network Based on Transfer Learning,” International journal of electrical and computer engineering systems, vol. 14, no. 3, pp. 277–284, Mar. 2023, doi: 10.32985/ijeces.14.3.5.
[28] T. Hassan, M. U. Akram, A. Shaukat, S. Gul Khawaja, and B. Hassan, “Structure Tensor Graph Searches Based Fully Automated Grading and 3D Profiling of Maculopathy From Retinal OCT Images,” IEEE Access, vol. 6, pp. 44644–44658, 2018, doi: 10.1109/ACCESS.2018.2862626.
[29] S. Khalid, M. U. Akram, T. Hassan, A. Jameel, and T. Khalil, “Automated Segmentation and Quantification of Drusen in Fundus and Optical Coherence Tomography Images for Detection of ARMD,” J Digit Imaging, vol. 31, no. 4, pp. 464–476, Aug. 2018, doi: 10.1007/s10278-017-0038-7.
[30] T. Hassan, M. U. Akram, and N. Werghi, “Exploiting the Transferability of Deep Learning Systems Across Multi-modal Retinal Scans for Extracting Retinopathy Lesions,” in 2020 IEEE 20th International Conference on Bioinformatics and Bioengineering (BIBE), IEEE, Oct. 2020, pp. 577–581. doi: 10.1109/BIBE50027.2020.00099.
[31] J. Kugelman, D. Alonso-Caneiro, S. A. Read, S. J. Vincent, and M. J. Collins, “Enhancing OCT patch-based segmentation with improved GAN data augmentation and semi-supervised learning,” Neural Comput Appl, vol. 36, no. 29, pp. 18087–18105, Oct. 2024, doi: 10.1007/s00521-024-10044-1.
[32] A. M. Nakib, Y. Li, and Y. Luo, “Retinopathy Identification in OCT Images with A Semi-supervised Learning Approach via Complementary Expert Pooling and Expert-wise Batch Normalization,” in 2024 9th Optoelectronics Global Conference (OGC), IEEE, Sep. 2024, pp. 170–174. doi: 10.1109/OGC62429.2024.10738779.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Arman Mohammad Nakib, Shahed Jahidul Haque
This work is licensed under a Creative Commons Attribution 4.0 International License.
