{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T12:17:54Z","timestamp":1787833074668,"version":"build-2784847793"},"reference-count":45,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T00:00:00Z","timestamp":1787788800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2023YFB2703702"],"award-info":[{"award-number":["2023YFB2703702"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key R&D Program of Shandong Province, China","award":["2025CXGC020307"],"award-info":[{"award-number":["2025CXGC020307"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>Choroidal neovascularization (CNV) subtype classification from optical coherence tomography (OCT) images is clinically important because treatment response and disease prognosis vary across subtypes. However, automated classification remains challenging owing to subtle inter-class differences and considerable imaging noise. We propose an erasing\u2013refining discriminative feature network (ERDF-Net) that mitigates noisy dominant activations and reveals fine-grained structural cues. The model perturbs salient regions to facilitate subtle feature learning, restores clean salient information, and fuses both representations via channel\u2013spatial attention to form a coherent and discriminative embedding of CNV morphology. Experiments on a clinical OCT dataset show that ERDF-Net consistently surpasses state-of-the-art fine-grained and erasing-based methods across multiple metrics. Ablation and visualization analyses further confirm the benefit and interpretability of controlled salient suppression and refined feature fusion. ERDF-Net provides an effective and reliable solution for fine-grained medical image classification.<\/jats:p>","DOI":"10.3390\/jimaging12090405","type":"journal-article","created":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T10:58:21Z","timestamp":1787828301000},"page":"405","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Erasing and Refining Discriminative Features for CNV Subtype Classification in OCT Images"],"prefix":"10.3390","volume":"12","author":[{"given":"Jiayi","family":"Zhang","sequence":"first","affiliation":[{"name":"Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University, Beijing 100044, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingbo","family":"Wang","sequence":"additional","affiliation":[{"name":"Shandong Institute for Product Quality Inspection, Jinan 250102, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1147-4327","authenticated-orcid":false,"given":"Jiqiang","family":"Liu","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University, Beijing 100044, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6270-4623","authenticated-orcid":false,"given":"Aixi","family":"Qu","sequence":"additional","affiliation":[{"name":"School of Computer and Artificial Intelligence, Shandong Jianzhu University, Jinan 250101, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,27]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"052","DOI":"10.1088\/1757-899X\/546\/5\/052056","article-title":"Choroidal Neovascularisation Classification on Fundus Retinal Images Using Local Linear Estimator","volume":"546","author":"Puspitawati","year":"2019","journal-title":"IOP Conf. Ser. Mater. Sci. Eng."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"2569","DOI":"10.1007\/s11277-021-09086-8","article-title":"Detection of Choroidal Neovascularization (CNV) in Retina OCT Images Using VGG16 and DenseNet CNN","volume":"127","author":"Abirami","year":"2021","journal-title":"Wirel. Pers. Commun."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"121725","DOI":"10.1016\/j.ijpharm.2022.121725","article-title":"Liposomal sunitinib for ocular drug delivery: A potential treatment for choroidal neovascularization","volume":"620","author":"Tavakoli","year":"2022","journal-title":"Int. J. Pharm."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"3029","DOI":"10.1109\/JBHI.2021.3066208","article-title":"Boundary Aware U-Net for Retinal Layers Segmentation in Optical Coherence Tomography Images","volume":"25","author":"Wang","year":"2021","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"6122","DOI":"10.1364\/BOE.400816","article-title":"Ia-net: Informative attention convolutional neural network for choroidal neovascularization segmentation in OCT images","volume":"11","author":"Xi","year":"2020","journal-title":"Biomed. Opt. Express"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Tang, R., Liu, Y., Li, L., Wang, Z., Wang, J., Cui, W., Li, X., Fu, S., and Wang, H. (2026). A multi-scale feature fusion network for CNV segmentation in SD-OCT images toward quantitative assessment of neovascular AMD. Sci. Rep.","DOI":"10.1038\/s41598-026-59215-1"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"7163","DOI":"10.1109\/TMM.2026.3673510","article-title":"Difficulty-aware pseudo-label correction network for fine-grained classification of choroidal neovascularization in OCT images","volume":"28","author":"Meng","year":"2026","journal-title":"IEEE Trans. Multimed."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"3408","DOI":"10.1109\/JBHI.2020.3023144","article-title":"Automatic segmentation and visualization of choroid in OCT with knowledge infused deep learning","volume":"24","author":"Hui","year":"2020","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Maunz, A., Benmansour, F., Li, Y., Albrecht, T., Zhang, Y., Arcadu, F., Zheng, Y., Adhusudhan, S., and Sahni, J. (2021). Accuracy of a machine-learning algorithm for detecting and classifying choroidal neovascularization on spectral-domain optical coherence tomography. J. Pers. Med., 11.","DOI":"10.3390\/jpm11060524"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"414","DOI":"10.1111\/aos.13364","article-title":"Identification and clinical role of choroidal neovascularization characteristics based on optical coherence tomography angiography","volume":"94","author":"Sulzbacher","year":"2017","journal-title":"Acta Ophthalmol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1667","DOI":"10.1109\/JBHI.2017.2702603","article-title":"Choroid neovascularization growth prediction with treatment based on reaction-diffusion model in 3-D OCT images","volume":"21","author":"Shuxia","year":"2017","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Douglas, V., Garg, I., Douglas, K., and John, M. (2022). Subthreshold Exudative Choroidal Neovascularization (CNV): Presentation of This Uncommon Subtype and Other CNVs in Age-Related Macular Degeneration (AMD). J. Clin. Med., 11.","DOI":"10.3390\/jcm11082083"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"557","DOI":"10.1097\/00006982-200210000-00005","article-title":"The nature of focal areas of hyperfluorescence or \u2018hot sports\u2019 imaged with indocyanine green angiography","volume":"22","author":"Fernandes","year":"2002","journal-title":"RETINA"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Chen, Y., Bai, Y., Zhang, W., and Mei, T. (2019). Destruction and construction learning for fine-grained image recognition. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2019.00530"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"103570","DOI":"10.1016\/j.jvcir.2022.103570","article-title":"Progressive Erasing Network with consistency loss for fine-grained visual classification","volume":"87","author":"Peng","year":"2022","journal-title":"J. Vis. Commun. Image Represent."},{"key":"ref_16","first-page":"2217","article-title":"Choroidal neovascularization classification system based on machine learning to distinguish pachychoroid neovasculopathy from age-related macular degeneration","volume":"60","author":"Miyake","year":"2019","journal-title":"Investig. Ophthalmol. Vis. Sci."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Xu, C., Xi, X., Yang, X., Sun, L., Meng, L., and Nie, X. (2022). Local Detail Enhancement Network for CNV Typing in OCT Image. Proceedings of the 15th International Conference on Human System Interaction, IEEE.","DOI":"10.1109\/HSI55341.2022.9869483"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"205007","DOI":"10.1088\/1361-6560\/ac9448","article-title":"Feature enhancement network for CNV typing in optical coherence tomography images","volume":"67","author":"Xu","year":"2022","journal-title":"Phys. Med. Biol."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"6558","DOI":"10.1109\/TCSVT.2023.3263870","article-title":"Semantic-guided Information Alignment Network for Fine-grained Image Recognition","volume":"33","author":"Wang","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"127054","DOI":"10.1016\/j.eswa.2025.127054","article-title":"A review of few-shot fine-grained image classification","volume":"275","author":"Lim","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhang, X., Cai, Z., He, X., Chen, S., Lai, Z., Yu, K., and Lai, R. (2026). Fine-Grained Age-Class Identification of Moso Bamboo Using an Improved Lightweight YOLO11 Model. J. Imaging, 12.","DOI":"10.3390\/jimaging12030102"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Ding, Y., Zhou, Y., Zhu, Y., Ye, Q., and Jiao, J. (2019). Selective sparse sampling for fine-grained image recognition. Proceedings of the IEEE\/CVF International Conference on Computer Vision, IEEE.","DOI":"10.1109\/ICCV.2019.00670"},{"key":"ref_23","unstructured":"Loshchilov, I., and Hutter, F. (2017, January 24\u201326). Sgdr: Stochastic gradient descent with warm restarts. Proceedings of the International Conference on Learning Representations, Toulon, France."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Yang, Z., Luo, T., Wang, D., Hu, Z., Gao, J., and Wang, L. (2018). Learning to navigate for fine-grained classification. Proceedings of the European Conference on Computer Vision, Springer.","DOI":"10.1007\/978-3-030-01264-9_26"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"4683","DOI":"10.1109\/TIP.2020.2973812","article-title":"The devil is in the channels: Mutual-channel loss for fine-grained image classification","volume":"29","author":"Chang","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"103658","DOI":"10.1016\/j.cviu.2023.103658","article-title":"Siamese self-supervised learning for fine-grained visual classification","volume":"229","author":"Ji","year":"2023","journal-title":"Comput. Vis. Image Underst."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Du, R., Chang, D., Bhunia, A.K., Xie, J., Ma, Z., Song, Y.Z., and Guo, J. (2020). Fine-grained visual classification via progressive multi-granularity training of jigsaw patches. Proceedings of the European Conference on Computer Vision, Springer.","DOI":"10.1007\/978-3-030-58565-5_10"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Jiang, Z., Men, A., and Ju, G. (2019). Pyramid real image denoising network. Proceedings of the IEEE Visual Communications and Image Processing, IEEE.","DOI":"10.1109\/VCIP47243.2019.8965754"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.Y., and Kweon, I.S. (2018). Cbam: Convolutional block attention module. Proceedings of the European Conference on Computer Vision (ECCV), Springer.","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Zheng, H., Fu, J., Zha, Z.J., and Luo, J. (2019). Looking for the devil in the details: Learning trilinear attention sampling network for fine-grained image recognition. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2019.00515"},{"key":"ref_32","unstructured":"DeVries, T., and Taylor, G.W. (2017). Improved regularization of convolutional neural networks with cutout. arXiv."},{"key":"ref_33","unstructured":"Zhong, Z., Zheng, L., Kang, G., Li, S., and Yang, Y. (2020, January 7\u201312). Random erasing data augmentation. Proceedings of the AAAI Conference on Artificial Intelligence, New York, NY, USA."},{"key":"ref_34","unstructured":"Singh, K.K., Yu, H., Sarmasi, A., Pradeep, G., and Lee, Y.J. (2018). Hide-and-seek: A data augmentation technique for weakly-supervised localization and beyond. arXiv."},{"key":"ref_35","unstructured":"Chen, P., Liu, S., Zhao, H., Wang, X., and Jia, J. (2020). Gridmask data augmentation. arXiv."},{"key":"ref_36","unstructured":"Krizhevsky, A., Sutskever, I., and Hinton, G.E. (2012). Imagenet classification with deep convolutional neural networks. Proceedings of the Advances in Neural Information Processing Systems, Curran Associates, Inc."},{"key":"ref_37","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv."},{"key":"ref_38","unstructured":"Tan, M., and Le, Q. (2019, January 9\u201315). Efficientnet: Rethinking model scaling for convolutional neural networks. Proceedings of the International Conference on Machine Learning, Long Beach, CA, USA."},{"key":"ref_39","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., and Polosukhin, I. (2017). Attention is all you need. Proceedings of the Advances in Neural Information Processing Systems, Curran Associates, Inc."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., and He, K. (2018). Non-local neural networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., and Sun, G. (2018). Squeeze-and-excitation networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Ma, W., Cui, Y., Shao, N., He, S., Zhang, W.N., Liu, T., Wang, S., and Hu, G. (2019). TripleNet: Triple attention network for multi-turn response selection in retrieval-based chatbots. arXiv.","DOI":"10.18653\/v1\/K19-1069"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Fu, J., Liu, J., Tian, H., Li, Y., Bao, Y., Fang, Z., and Lu, H. (2019). Dual attention network for scene segmentation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"699","DOI":"10.1109\/TMI.2020.3035253","article-title":"CA-Net: Comprehensive attention convolutional neural networks for explainable medical image segmentation","volume":"40","author":"Gu","year":"2020","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"1140","DOI":"10.52202\/068431-0084","article-title":"Segnext: Rethinking convolutional attention design for semantic segmentation","volume":"Volume 35","author":"Guo","year":"2022","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/9\/405\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T11:22:55Z","timestamp":1787829775000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/9\/405"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,27]]},"references-count":45,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["jimaging12090405"],"URL":"https:\/\/doi.org\/10.3390\/jimaging12090405","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,27]]}}}