{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,15]],"date-time":"2025-08-15T00:20:03Z","timestamp":1755217203241,"version":"3.43.0"},"reference-count":40,"publisher":"IOP Publishing","issue":"5","license":[{"start":{"date-parts":[[2025,8,5]],"date-time":"2025-08-05T00:00:00Z","timestamp":1754352000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/page\/copyright"},{"start":{"date-parts":[[2025,8,5]],"date-time":"2025-08-05T00:00:00Z","timestamp":1754352000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["11601372"],"award-info":[{"award-number":["11601372"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"National Key Research and Development Program of China","award":["2022YFF0706003"],"award-info":[{"award-number":["2022YFF0706003"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Biomed. Phys. Eng. Express"],"published-print":{"date-parts":[[2025,9,30]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Low-quality fundus images pose significant challenges for diabetic retinopathy (DR) classification due to noise, blurred boundaries, and the loss of high-frequency details, which hinder both global contextual understanding and local fine-grained feature extraction. To address these limitations, this work proposes a Hierarchical Frequency-Spatial Feature Fusion Network (HFSF-Net) that effectively integrates frequency-domain and spatial-domain information for robust DR classification. Initially, this paper introduces the Spatial Prior-Aware Transformer (SPAT) Block, which incorporates spatial prior knowledge to direct the attention distribution, enabling precise localization of the complex distribution of lesion regions in low-quality fundus images. Subsequently, a novel Wavelet-Enhanced Self-Attention (WESA) module is developed, which utilizes wavelet transforms to extract and enhance high-frequency components such as microvascular textures and edges. Based on WESA, the Wavelet-Enhanced Transformer (WET) Block is constructed to strengthen the ability to recover local details in degraded images. Furthermore, a Hierarchical Frequency-Spatial Fusion (HFSF) module is designed to hierarchically integrate multi-scale features, mitigating information redundancy and resolving feature conflicts between domains. Through this architecture, the model achieves a balanced representation of global and local information. The experiments conducted on the APTOS and DDR datasets yield ACC values of 0.8117 and 0.8021, and Kappa scores of 0.7158 and 0.6731, respectively. Although the model does not achieve exceptionally high Recall, its consistently strong performance in other key metrics supports the claim that the proposed architecture enables a balanced representation of global and local information. Furthermore, the experimental results validate the effectiveness and robustness of HFSF-Net in classifying diabetic retinopathy from low-quality fundus images.<\/jats:p>","DOI":"10.1088\/2057-1976\/adf3b5","type":"journal-article","created":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T22:47:24Z","timestamp":1753397244000},"page":"055005","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Frequency-spatial feature fusion via a hierarchical framework for diabetic retinopathy classification in low-quality fundus images"],"prefix":"10.1088","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-2777-200X","authenticated-orcid":true,"given":"Pengfei","family":"Cai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1361-1404","authenticated-orcid":true,"given":"Biyuan","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinying","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao","family":"Tian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lianhao","family":"Huo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuefeng","family":"Jia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2025,8,5]]},"reference":[{"key":"bpexadf3b5bib1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2025.103511","article-title":"MSTNet: Multi-scale spatial-aware transformer with multi-instance learning for diabetic retinopathy classification","volume":"102","author":"Wei","year":"2025","journal-title":"Med. Image Anal."},{"key":"bpexadf3b5bib2","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2024.107352","article-title":"STMF-DRNet: A multi-branch fine-grained classification model for diabetic retinopathy using Swin-TransformerV2","volume":"103","author":"Liu","year":"2025","journal-title":"Biomed. Signal Process. Control"},{"key":"bpexadf3b5bib3","doi-asserted-by":"publisher","DOI":"10.1016\/j.imu.2020.100377","article-title":"Diabetic retinopathy detection through deep learning techniques: a review","volume":"20","author":"Alyoubi","year":"2020","journal-title":"Informatics in Medicine Unlocked"},{"key":"bpexadf3b5bib4","doi-asserted-by":"publisher","first-page":"2211","DOI":"10.1007\/s11831-022-09862-0","article-title":"A systematic review on diabetic retinopathy detection using deep learning techniques","volume":"30","author":"Vij","year":"2023","journal-title":"Arch. Comput. Meth. Eng."},{"key":"bpexadf3b5bib5","doi-asserted-by":"publisher","first-page":"84785","DOI":"10.1109\/ACCESS.2024.3415617","article-title":"Deep learning in automatic diabetic retinopathy detection and grading systems: a comprehensive survey and comparison of methods","volume":"12","author":"Abushawish","year":"2024","journal-title":"IEEE Access"},{"key":"bpexadf3b5bib6","doi-asserted-by":"publisher","first-page":"3","DOI":"10.3390\/jcm10010003","article-title":"The severity of diabetic retinopathy is an independent factor for the progression of diabetic nephropathy","volume":"10","author":"Hsing","year":"2020","journal-title":"Journal of Clinical Medicine"},{"key":"bpexadf3b5bib7","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1167\/tvst.8.6.4","article-title":"Automatic detection of diabetic retinopathy in retinal fundus photographs based on deep learning algorithm","volume":"8","author":"Li","year":"2019","journal-title":"Translational Vision Science & Technology"},{"key":"bpexadf3b5bib8","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2019.07.002","article-title":"Referable diabetic retinopathy identification from eye fundus images with weighted path for convolutional neural network","volume":"99","author":"Liu","year":"2019","journal-title":"Artif. Intell. Med."},{"key":"bpexadf3b5bib9","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2020.102115","article-title":"A lightweight CNN for Diabetic Retinopathy classification from fundus images","volume":"62","author":"Gayathri","year":"2020","journal-title":"Biomed. Signal Process. Control"},{"key":"bpexadf3b5bib10","doi-asserted-by":"publisher","first-page":"8747","DOI":"10.1007\/s12652-020-02647-y","article-title":"Classification of retinal fundus image using MS-DRLBP features and CNN-RBF classifier","volume":"12","author":"Hemalakshmi","year":"2021","journal-title":"Journal of Ambient Intelligence and Humanized Computing"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2020","author":"Dosovitskiy","key":"bpexadf3b5bib11"},{"key":"bpexadf3b5bib12","doi-asserted-by":"publisher","first-page":"7850","DOI":"10.1002\/mp.15312","article-title":"Vision Transformer-based recognition of diabetic retinopathy grade","volume":"48","author":"Wu","year":"2021","journal-title":"Med. Phys."},{"key":"bpexadf3b5bib13","doi-asserted-by":"publisher","first-page":"736","DOI":"10.1007\/978-3-031-43898-1_70","article-title":"Laplacian-former: Overcoming the limitations of vision transformers in local texture detection","author":"Azad","year":"2023"},{"key":"bpexadf3b5bib14","doi-asserted-by":"publisher","first-page":"639","DOI":"10.1007\/s13246-021-01012-3","article-title":"Diabetic retinopathy classification based on multipath CNN and machine learning classifiers","volume":"44","author":"Gayathri","year":"2021","journal-title":"Physical and Engineering Sciences in Medicine"},{"key":"bpexadf3b5bib15","doi-asserted-by":"publisher","first-page":"9825","DOI":"10.1007\/s12652-020-02727-z","article-title":"Composite deep neural network with gated-attention mechanism for diabetic retinopathy severity classification","volume":"12","author":"Bodapati","year":"2021","journal-title":"Journal of Ambient Intelligence and Humanized Computing"},{"key":"bpexadf3b5bib16","doi-asserted-by":"publisher","first-page":"2216","DOI":"10.1109\/JBHI.2021.3119519","article-title":"Joint learning of multi-level tasks for diabetic retinopathy grading on low-resolution fundus images","volume":"26","author":"Wang","year":"2021","journal-title":"IEEE Journal of Biomedical and Health Informatics"},{"key":"bpexadf3b5bib17","doi-asserted-by":"publisher","first-page":"61408","DOI":"10.1109\/ACCESS.2021.3074422","article-title":"Diabetic retinopathy detection using VGG-NIN a deep learning architecture","volume":"9","author":"Khan","year":"2021","journal-title":"IEEE Access"},{"key":"bpexadf3b5bib18","doi-asserted-by":"publisher","first-page":"1739","DOI":"10.1007\/s10278-023-00813-0","article-title":"Diabetic retinopathy prediction based on wavelet decomposition and modified capsule network","volume":"36","author":"Oulhadj","year":"2023","journal-title":"Journal of Digital Imaging"},{"key":"bpexadf3b5bib19","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.105602","article-title":"Applying supervised contrastive learning for the detection of diabetic retinopathy and its severity levels from fundus images","volume":"146","author":"Islam","year":"2022","journal-title":"Comput. Biol. Med."},{"key":"bpexadf3b5bib20","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2024.106714","article-title":"MSEF-Net: a multi-scale efficientnet fusion for diabetic retinopathy grading","volume":"98","author":"Fu","year":"2024","journal-title":"Biomed. Signal Process. Control"},{"key":"bpexadf3b5bib21","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2024.106564","article-title":"DFCAFNet: Dual-feature co-attentive fusion network for diabetic retinopathy grading","volume":"96","author":"Madarapu","year":"2024","journal-title":"Biomed. Signal Process. Control"},{"key":"bpexadf3b5bib22","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.123523","article-title":"A deep integrative approach for diabetic retinopathy classification with synergistic channel-spatial and self-attention mechanism","volume":"249","author":"Madarapu","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"bpexadf3b5bib23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/ISPACS51563.2021.9651024","article-title":"Diabetic retinopathy detection using CNN, transformer and MLP based architectures","author":"Kumar","year":"2021"},{"key":"bpexadf3b5bib24","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2023.103956","article-title":"MIL-ViT: A multiple instance vision transformer for fundus image classification","volume":"97","author":"Bi","year":"2023","journal-title":"J. Visual Commun. Image Represent."},{"key":"bpexadf3b5bib25","doi-asserted-by":"publisher","first-page":"6768","DOI":"10.1109\/ACCESS.2024.3351473","article-title":"A novel transformer model with multiple instance learning for diabetic retinopathy classification","volume":"12","author":"Yang","year":"2024","journal-title":"IEEe Access"},{"key":"bpexadf3b5bib26","first-page":"15316","article-title":"Augmented shortcuts for vision transformers","volume":"34","author":"Tang","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"bpexadf3b5bib27","doi-asserted-by":"publisher","first-page":"12094","DOI":"10.1109\/CVPR52688.2022.01178","article-title":"Multi-scale high-resolution vision transformer for semantic segmentation","author":"Gu","year":"2022"},{"article-title":"Retentive network: A successor to transformer for large language models","year":"2023","author":"Sun","key":"bpexadf3b5bib28"},{"key":"bpexadf3b5bib29","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2022.109462","article-title":"Classification of diabetic retinopathy with feature selection over deep features using nature-inspired wrapper methods","volume":"128","author":"Canayaz","year":"2022","journal-title":"Appl. Soft Comput."},{"key":"bpexadf3b5bib30","doi-asserted-by":"publisher","first-page":"511","DOI":"10.1016\/j.ins.2019.06.011","article-title":"Diagnostic assessment of deep learning algorithms for diabetic retinopathy screening","volume":"501","author":"Li","year":"2019","journal-title":"Inf. Sci."},{"key":"bpexadf3b5bib31","doi-asserted-by":"publisher","first-page":"11976","DOI":"10.1109\/CVPR52688.2022.01167","article-title":"A convnet for the 2020s","author":"Liu","year":"2022"},{"key":"bpexadf3b5bib32","first-page":"32097","article-title":"Peripheral vision transformer","volume":"35","author":"Min","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"bpexadf3b5bib33","first-page":"4203","article-title":"Focal modulation networks","volume":"35","author":"Yang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"bpexadf3b5bib34","doi-asserted-by":"publisher","first-page":"12581","DOI":"10.1109\/TPAMI.2023.3282631","article-title":"Uniformer: Unifying convolution and self-attention for visual recognition","volume":"45","author":"Li","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"bpexadf3b5bib35","doi-asserted-by":"publisher","first-page":"10323","DOI":"10.1109\/CVPR52729.2023.00995","article-title":"Biformer: Vision transformer with bi-level routing attention","author":"Zhu","year":"2023"},{"key":"bpexadf3b5bib36","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.105534","article-title":"HiFuse: Hierarchical multi-scale feature fusion network for medical image classification","volume":"87","author":"Huo","year":"2024","journal-title":"Biomed. Signal Process. Control"},{"key":"bpexadf3b5bib37","doi-asserted-by":"publisher","first-page":"17773","DOI":"10.1109\/CVPR52733.2024.01683","article-title":"Transnext: Robust foveal visual perception for vision transformers","author":"Shi","year":"2024"},{"key":"bpexadf3b5bib38","doi-asserted-by":"publisher","first-page":"5641","DOI":"10.1109\/CVPR52733.2024.00539","article-title":"Rmt: Retentive networks meet vision transformers","author":"Fan","year":"2024"},{"key":"bpexadf3b5bib39","first-page":"4484","article-title":"Mambaout: Do we really need mamba for vision?","author":"Yu","year":"2025"},{"key":"bpexadf3b5bib40","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1007\/s40200-025-01596-7","article-title":"Artificial intelligence for early detection of diabetes mellitus complications via retinal imaging","volume":"24","author":"Sobhi","year":"2025","journal-title":"Journal of Diabetes & Metabolic Disorders"}],"container-title":["Biomedical Physics &amp; Engineering Express"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/adf3b5","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/adf3b5\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/adf3b5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/adf3b5\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/adf3b5\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/adf3b5\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/adf3b5\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/adf3b5\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,5]],"date-time":"2025-08-05T07:51:12Z","timestamp":1754380272000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/adf3b5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,5]]},"references-count":40,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2025,8,5]]},"published-print":{"date-parts":[[2025,9,30]]}},"URL":"https:\/\/doi.org\/10.1088\/2057-1976\/adf3b5","relation":{},"ISSN":["2057-1976"],"issn-type":[{"type":"electronic","value":"2057-1976"}],"subject":[],"published":{"date-parts":[[2025,8,5]]},"assertion":[{"value":"Frequency-spatial feature fusion via a hierarchical framework for diabetic retinopathy classification in low-quality fundus images","name":"article_title","label":"Article Title"},{"value":"Biomedical Physics & Engineering Express","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2025 IOP Publishing Ltd. All rights, including for text and data mining, AI training, and similar technologies, are reserved.","name":"copyright_information","label":"Copyright Information"},{"value":"2025-05-09","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-07-24","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-08-05","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}