{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T15:57:25Z","timestamp":1776182245299,"version":"3.50.1"},"reference-count":30,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2025,2,11]],"date-time":"2025-02-11T00:00:00Z","timestamp":1739232000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Pukyong National University","award":["2022"],"award-info":[{"award-number":["2022"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>This study presents a comprehensive comparison of U-Net variants with different backbone architectures for Macular Hole (MH) segmentation in optical coherence tomography (OCT) images. We evaluated eleven architectures, including U-Net combined with InceptionNetV4, VGG16, VGG19, ResNet152, DenseNet121, EfficientNet-B7, MobileNetV2, Xception, and Transformer. Models were assessed using the Dice coefficient and HD95 metrics on the OIMHS dataset. While HD95 proved unreliable for small regions like MH, often returning \u2018nan\u2019 values, the Dice coefficient provided consistent performance evaluation. InceptionNetV4 + U-Net achieved the highest Dice coefficient (0.9672), demonstrating superior segmentation accuracy. Although considered state-of-the-art, Transformer + U-Net showed poor performance in MH and intraretinal cyst (IRC) segmentation. Analysis of computational resources revealed that MobileNetV2 + U-Net offered the most efficient performance with minimal parameters, while InceptionNetV4 + U-Net balanced accuracy with moderate computational demands. Our findings suggest that CNN-based backbones, particularly InceptionNetV4, are more effective than Transformer architectures for OCT image segmentation, with InceptionNetV4 + U-Net emerging as the most promising model for clinical applications.<\/jats:p>","DOI":"10.3390\/jimaging11020053","type":"journal-article","created":{"date-parts":[[2025,2,11]],"date-time":"2025-02-11T11:54:06Z","timestamp":1739274846000},"page":"53","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Comparative Analysis of Deep Learning Architectures for Macular Hole Segmentation in OCT Images: A Performance Evaluation of U-Net Variants"],"prefix":"10.3390","volume":"11","author":[{"given":"H. M. S. S.","family":"Herath","sequence":"first","affiliation":[{"name":"Department of Industry 4.0 Convergence Bionics Engineering, Pukyoung National University, Busan 48513, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9571-6866","authenticated-orcid":false,"given":"S. L. P.","family":"Yasakethu","sequence":"additional","affiliation":[{"name":"Faculty of Technology, Sri Lanka Technological Campus, Padukka 10500, Sri Lanka"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7982-1036","authenticated-orcid":false,"given":"Nuwan","family":"Madusanka","sequence":"additional","affiliation":[{"name":"Digital Healthcare Research Center, Pukyong National University, Busan 48513, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4864-959X","authenticated-orcid":false,"given":"Myunggi","family":"Yi","sequence":"additional","affiliation":[{"name":"Department of Industry 4.0 Convergence Bionics Engineering, Pukyoung National University, Busan 48513, Republic of Korea"},{"name":"Digital Healthcare Research Center, Pukyong National University, Busan 48513, Republic of Korea"},{"name":"Division of Smart Healthcare, College of Information Technology and Convergence, Pukyong National University, Busan 48513, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1574-7145","authenticated-orcid":false,"given":"Byeong-Il","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Industry 4.0 Convergence Bionics Engineering, Pukyoung National University, Busan 48513, Republic of Korea"},{"name":"Digital Healthcare Research Center, Pukyong National University, Busan 48513, Republic of Korea"},{"name":"Division of Smart Healthcare, College of Information Technology and Convergence, Pukyong National University, Busan 48513, Republic of Korea"}]}],"member":"1968","published-online":{"date-parts":[[2025,2,11]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"3044","DOI":"10.1109\/TMI.2024.3383466","article-title":"SASAN: Spectrum-Axial Spatial Approach Networks for Medical Image Segmentation","volume":"43","author":"Huang","year":"2024","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Sampath Kumar, A., Schlosser, T., Langner, H., Ritter, M., and Kowerko, D. (2023). Improving OCT Image Segmentation of Retinal Layers by Utilizing a Machine Learning Based Multistage System of Stacked Multiscale Encoders and Decoders. Bioengineering, 10.","DOI":"10.3390\/bioengineering10101177"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1049\/cvi2.12139","article-title":"A Fine-to-Coarse-to-Fine Weakly Supervised Framework for Volumetric SD-OCT Image Segmentation","volume":"17","author":"Niu","year":"2023","journal-title":"IET Comput. Vis."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Garcia-Marin, Y.F., Alonso-Caneiro, D., Fisher, D., Vincent, S.J., and Collins, M.J. (2023). Patch-Based CNN for Corneal Segmentation of AS-OCT Images: Effect of the Number of Classes and Image Quality upon Performance. Comput. Biol. Med., 152.","DOI":"10.1016\/j.compbiomed.2022.106342"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Fang, J., Xing, A., Chen, Y., and Zhou, F. (2024). SeqCorr-EUNet: A Sequence Correction Dual-Flow Network for Segmentation and Quantification of Anterior Segment OCT Image. Comput. Biol. Med., 171.","DOI":"10.1016\/j.compbiomed.2024.108143"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Li, S., Ma, F., Yan, F., Dong, X., Guo, Y., Meng, J., and Liu, H. (2024). SFNet: Spatial and Frequency Domain Networks for Wide-Field OCT Angiography Retinal Vessel Segmentation. J. Biophotonics, 18.","DOI":"10.1002\/jbio.202400420"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Fazekas, B., Aresta, G., Lachinov, D., Riedl, S., Mai, J., Schmidt-Erfurth, U., and Bogunovi\u0107, H. (2025). SD-LayerNet: Robust and Label-Efficient Retinal Layer Segmentation via Anatomical Priors. Comput. Methods Programs Biomed., 261.","DOI":"10.1016\/j.cmpb.2025.108586"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"123496","DOI":"10.1016\/j.eswa.2024.123496","article-title":"AMSC-Net: Anatomy and Multi-Label Semantic Consistency Network for Semi-Supervised Fluid Segmentation in Retinal OCT","volume":"249","author":"Wang","year":"2024","journal-title":"Expert. Syst. Appl."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"110507","DOI":"10.1016\/j.patcog.2024.110507","article-title":"Mirrored X-Net: Joint Classification and Contrastive Learning for Weakly Supervised GA Segmentation in SD-OCT","volume":"153","author":"Ji","year":"2024","journal-title":"Pattern Recognit."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Chen, Q., Zeng, L., and Lin, C. (2023). A Deep Network Embedded with Rough Fuzzy Discretization for OCT Fundus Image Segmentation. Sci. Rep., 13.","DOI":"10.1038\/s41598-023-27479-6"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Sheeba, T.M., Albert Antony Raj, S., and Anand, M. (2023, January 2\u20134). Analysis of Various Image Segmentation Techniques on Retinal OCT Images. Proceedings of the 2023 Third International Conference on Artificial Intelligence and Smart Energy (ICAIS), Coimbatore, India.","DOI":"10.1109\/ICAIS56108.2023.10073657"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Liu, J., Yan, S., Lu, N., Yang, D., Lv, H., Wang, S., Zhu, X., Zhao, Y., Wang, Y., and Ma, Z. (2022). Automated Retinal Boundary Segmentation of Optical Coherence Tomography Images Using an Improved Canny Operator. Sci. Rep., 12.","DOI":"10.1038\/s41598-022-05550-y"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"5374","DOI":"10.1002\/mp.17012","article-title":"Two-Stage Adversarial Learning Based Unsupervised Domain Adaptation for Retinal OCT Segmentation","volume":"51","author":"Diao","year":"2024","journal-title":"Med. Phys."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"37702","DOI":"10.1109\/ACCESS.2024.3372863","article-title":"DiffusionDCI: A Novel Diffusion-Based Unified Framework for Dynamic Full-Field OCT Image Generation and Segmentation","volume":"12","author":"Yang","year":"2024","journal-title":"IEEE Access"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Niu, Z., Deng, Z., Gao, W., Bai, S., Gong, Z., Chen, C., Rong, F., Li, F., and Ma, L. (2024). FNeXter: A Multi-Scale Feature Fusion Network Based on ConvNeXt and Transformer for Retinal OCT Fluid Segmentation. Sensors, 24.","DOI":"10.3390\/s24082425"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Su, W., Zhili, H., Zixuan, W., Qiyong, L., and Jinsong, L. (2024). MAPI-Net: A Context and Location Fusion Network for Multi-Lesion Segmentation in Intravascular OCT. Biomed. Signal Process. Control., 96.","DOI":"10.1016\/j.bspc.2024.106559"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"769","DOI":"10.1038\/s41597-023-02675-1","article-title":"OIMHS: An Optical Coherence Tomography Image Dataset Based on Macular Hole Manual Segmentation","volume":"10","author":"Ye","year":"2023","journal-title":"Sci. Data"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Cao, G., Peng, Z., Wu, Y., and Zhou, Z. (2023, January 23\u201325). Retinal OCT Image Layer Segmentation Based on Attention Mechanism. Proceedings of the 2023 8th International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS), Okinawa, Japan.","DOI":"10.1109\/ICIIBMS60103.2023.10347593"},{"key":"ref_19","first-page":"114","article-title":"A Feature Pyramid Fusion Network Based on Dynamic Perception Transformer for Retinal OCT Biomarker Image Segmentation","volume":"Volume 1964","author":"Luo","year":"2024","journal-title":"Neural Information Processing"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Kumar Vupparaboina, K., Chandra Bollepalli, S., Ibrahim, M.N., Selvam, A., Vaishnavi Kurakula, S., Mohammed, A.R., Mayer, N., Sahel, J.-A., and Chhablani, J. (2024). Protecting Privacy While Improving Choroid Layer Segmentation in OCT Images: A GAN-Based Image Synthesis Approach, SSRN. Available online: https:\/\/ssrn.com\/abstract=4705376.","DOI":"10.2139\/ssrn.4705376"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Xiao, Z., Du, M., Liu, J., Sun, E., Zhang, J., Gong, X., and Chen, Z. (2023). EA-UNet Based Segmentation Method for OCT Image of Uterine Cavity. Photonics, 10.","DOI":"10.3390\/photonics10010073"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"18087","DOI":"10.1007\/s00521-024-10044-1","article-title":"Enhancing OCT Patch-Based Segmentation with Improved GAN Data Augmentation and Semi-Supervised Learning","volume":"36","author":"Kugelman","year":"2024","journal-title":"Neural Comput. Appl."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Montazerin, M., Sajjadifar, Z., Khalili Pour, E., Riazi-Esfahani, H., Mahmoudi, T., Rabbani, H., Movahedian, H., Dehghani, A., Akhlaghi, M., and Kafieh, R. (2021). Livelayer: A Semi-Automatic Software Program for Segmentation of Layers and Diabetic Macular Edema in Optical Coherence Tomography Images. Sci. Rep., 11.","DOI":"10.1038\/s41598-021-92713-y"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Alex, V., Motevasseli, T., Freeman, W.R., Jayamon, J.A., Bartsch, D.U.G., and Borooah, S. (2021). Assessing the Validity of a Cross-Platform Retinal Image Segmentation Tool in Normal and Diseased Retina. Sci. Rep., 11.","DOI":"10.1038\/s41598-021-01105-9"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Cao, G., Zhou, Z., Wu, Y., Peng, Z., Yan, R., Zhang, Y., and Jiang, B. (2024). GCN-Enhanced Spatial-Spectral Dual-Encoder Network for Simultaneous Segmentation of Retinal Layers and Fluid in OCT Images. Biomed. Signal Process Control, 98.","DOI":"10.1016\/j.bspc.2024.106702"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"102480","DOI":"10.1016\/j.compmedimag.2024.102480","article-title":"General Retinal Layer Segmentation in OCT Images via Reinforcement Constraint","volume":"120","author":"Hao","year":"2025","journal-title":"Comput. Med. Imaging Graph."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"e33911","DOI":"10.1016\/j.heliyon.2024.e33911","article-title":"ScLNet: A Cornea with Scleral Lens OCT Layers Segmentation Dataset and New Multi-Task Model","volume":"10","author":"Cao","year":"2024","journal-title":"Heliyon"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Geetha, A., Carmel Sobia, M., Santhi, D., and Ahilan, A. (2025). DEEP GD: Deep Learning Based Snapshot Ensemble CNN with EfficientNet for Glaucoma Detection. Biomed. Signal Process Control, 100.","DOI":"10.1016\/j.bspc.2024.106989"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Tanthanathewin, R., Wongrattanapipat, W., Khaing, T.T., and Aimmanee, P. (2024). Automatic Exudate and Aneurysm Segmentation in OCT Images Using UNET++ and Hyperreflective-Foci Feature Based Bagged Tree Ensemble. PLoS ONE, 19.","DOI":"10.1371\/journal.pone.0304146"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"31719","DOI":"10.1109\/ACCESS.2024.3369913","article-title":"Performance Evaluation of Retinal OCT Fluid Segmentation, Detection, and Generalization Over Variations of Data Sources","volume":"12","author":"Ndipenoch","year":"2024","journal-title":"IEEE Access"}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/11\/2\/53\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T16:30:48Z","timestamp":1760027448000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/11\/2\/53"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,11]]},"references-count":30,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,2]]}},"alternative-id":["jimaging11020053"],"URL":"https:\/\/doi.org\/10.3390\/jimaging11020053","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,11]]}}}