Automated Detection and Segmentation of Choroidal Neovascularization in OCT Using Deep Learning

Article Sidebar

PDF
Published: Sep 29, 2025
Keywords:
Choroidal neovascularization Deep learning methods Optical coherence tomography

Main Article Content

Pawaris Panyasombat
School of Information Computer and Communication Technology, Sirindhorn International Institute of Technology, Thammasat University Pathum Thani 12120, Thailand
Anawin Srivoranan
School of Information Computer and Communication Technology, Sirindhorn International Institute of Technology, Thammasat University Pathum Thani 12120, Thailand
Chanyanud Sriyota
School of Information Computer and Communication Technology, Sirindhorn International Institute of Technology, Thammasat University Pathum Thani 12120, Thailand
Teerachot Khusuwan
School of Information Computer and Communication Technology, Sirindhorn International Institute of Technology, Thammasat University Pathum Thani 12120, Thailand
Pakinee Aimmanee
School of Information Computer and Communication Technology, Sirindhorn International Institute of Technology, Thammasat University Pathum Thani 12120, Thailand

Abstract

Choroidal neovascularization (CNV) is a hallmark of age-related macular degeneration (AMD), marked by the growth of abnormal blood vessels beneath the retina that can severely impair vision. Optical Coherence Tomography (OCT), a non-invasive imaging technique, is widely used to detect CNV due to its ability to capture detailed cross-sectional images of the retina. However, the variability in lesion appearance and the presence of artifacts make manual interpretation challenging and time-consuming. To address these limitations, this study explored the application of deep learning models for automated CNV image detection and CNV localization in OCT images. We compared several architectures widely used for segmentation tasks: U-Net, Attention U-Net, DeepLabV3+, DeepLabV3++, Mask R-CNN, and Mask R-CNN+, tested on a balanced dataset of 500 images. Among the tested models, DeepLabV3++ achieved the highest performance with a CNV image detection accuracy of 99.4% and a CNV localization F1-score of 0.80. These findings suggest that deep learning can significantly enhance the efficiency and consistency of CNV diagnosis, paving the way for its integration into clinical workflows to support early screening and treatment of AMD.

Article Details

How to Cite
Pawaris Panyasombat, Anawin Srivoranan, Chanyanud Sriyota, Teerachot Khusuwan, & Pakinee Aimmanee. (2025). Automated Detection and Segmentation of Choroidal Neovascularization in OCT Using Deep Learning. Science & Technology Asia, 30(3), 40–50. retrieved from https://ph02.tci-thaijo.org/index.php/SciTechAsia/article/view/261438
Issue
Vol.30 No.3 (July-September 2025)
Section
Articles
Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

References

Wu L, Dahl AA, editors. Choroidal neovascularization (CNV). Updated 2023 Jan 5 [cited 2025 Jun 14]. In: Medscape Reference. Available from: https://emedicine.medscape.com/article/-1190818-overview.

Spirn MJ, Feldman BH, Kozak A, Shah VA, Kim LA, Tripathy K, Khadamy J, de Carlo T, Lim JI, Ichlangod AM, Bose A. Optical coherence tomography. Eyewiki; 2024 [cited 2025 Apr 29]. Available from: https://eyewiki.org/Optical_Coherence_-Tomography.

Ismail AM, El-Samie FEA, Omer AO, El-Sayed HS. Ensemble transfer learning networks for disease classification from retinal optical coherence tomography images. J Opt. 2024.

Xi X, Meng X, Yang L, Nie X, Yang G, Chen H, Fan X, Yin Y, Chen X. Automated segmentation of choroidal neovascularization in optical coherence tomography images using multi-scale convolutional neural networks with structure prior. Multimed Syst. 2019;25:95–102.

Zhang Y, Ji Z, Wang Y, Niu S, Fan W, Yuan S, Chen Q. MPB-CNN: a multi-scale parallel branch CNN for choroidal neovascularization segmentation in SD-OCT images. OSA Contin. 2019;2(3):1011–27.

Meng Q, Wang L, Wang T, Wang M, Zhu W, Shi F, Chen Z, Chen X. MF-Net: multi-scale information fusion network for CNV segmentation in retinal OCT images. Front Neurosci. 2021;15:743769.

Diao S, Su J, Yang C, Zhu W, Xiang D, Chen X, Peng Q, Shi F. Classification and segmentation of OCT images for age-related macular degeneration based on dual guidance networks. Biomed Signal Process Control. 2023;84:104810.

Liu X, Liu Q, Zhang Y, Wang M, Tang J. TSSK-Net: Weakly supervised biomarker localization and segmentation with image-level annotation in retinal OCT images. Comput Biol Med. 2023;153:106467.

Fu G, Cui W, Yang M, Zhang Y, Zhou Y, Sun Y, Xu X, Wang F, Lin H, Shen Y. Imaging-aware extreme interaction network for choroidal neovascularization segmentation in OCT images. Opt Commun. 2025;583:131615.

Shen Y, Li J, Zhu W, Yu K, Wang M, Peng Y, Zhou Y, Guan L, Chen X. Graph attention U-Net for retinal layer surface detection and choroid neovascularization segmentation in OCT images. IEEE Trans Med Imaging. 2023;42(11):3140–54.

Mori Y, Modi N. Enhancing OCT image classification for retinal disease diagnosis: a novel approach using squeeze-andexcitation ResNet. In: Proceedings of the 2024 IEEE 3rd World Conference on Applied Intelligence and Computing (AIC); 2024 Jul 27; Rajkot, India. Piscataway (NJ): IEEE; 2024. p. 940–5.

Paul D, Tewari A, Ghosh S, Santosh K. OCTx: ensembled deep learning model to detect retinal disorders. In: Proceedings of the 2020 IEEE 33rd International Symposium on Computer-Based Medical Systems (CBMS); 2020 Jul 1; Rochester, MN, USA. Piscataway (NJ): IEEE; 2020. p. 526–31.

Ronneberger O, Fischer P, Brox T. U-Net: Convolutional networks for biomedical image segmentation [Preprint]. arXiv:1505.04597 [cs.CV]. 2015 [cited 2025 Jun 13]. Available from: https://arxiv.org/abs/1505.04597.

Oktay O, Schlemper J, Le Folgoc L, Lee M, Heinrich M, Misawa K, Mori K, McDonagh S, Hammerla NY, Kainz B, Glocker B, Rueckert D. Attention U-Net: learning where to look for the pancreas [Preprint]. arXiv:1804.03999 [cs.CV]. 2018. Available from: https://arxiv.org/abs/1804.03999.

Chen LC, Zhu Y, Papandreou G, Schroff F, Adam H. Encoder-decoder with atrous separable convolution for semantic image segmentation [Preprint]. arXiv:1802.02611 [cs.CV]. 2018. Available from: https://arxiv.org/abs/1802.02611.

He K, Gkioxari G, Dollár P, Girshick R. Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV); 2017. p. 2980–8.

Hussain M, Khan MA, Khan W. Binary cross entropy with deep learning technique for image classification. Int J Adv Trends Comput Sci Eng. 2020;9(4):4561–7.

Sudre CH, Li W, Vercauteren T, Ourselin S, Cardoso MJ. Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations. In: Deep learning in medical image analysis and multimodal learning for clinical decision support. Cham: Springer; 2017. p. 240–8.

Kermany DS, Goldbaum M, Cai W, Lewis MA, Xia H, Zhang K. Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell. 2018;172(5):1122–31.e9.

Steen D. Understanding the ROC curve and AUC [Internet]. Towards Data Science. 2025 Jul 22 [cited 2025 Jul 22]. Available from: https://towardsdatascience.com/understandingthe-roc-curve-and-auc-dd4f9a192ecb.

Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D. Grad-CAM: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV); 2017 [cited 2025 Jul 22]. Available from: https://doi.org/10.1109/ICCV.2017.74.

Lundberg SM, Lee S-I. A unified approach to interpreting model predictions. In: Proceedings of the 31st International Conference on Neural Information Processing Systems (NeurIPS); 2017 [cited 2025 Jul 22]. Available from: https://doi.org/10.48550/arXiv.1705.07874.