{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T04:30:55Z","timestamp":1786336255344,"version":"build-2736575974"},"reference-count":39,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T00:00:00Z","timestamp":1786320000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Early detection of diabetic retinopathy (DR) is crucial for preventing permanent vision impairment, yet widely used screening techniques such as fundus photography and optical coherence tomography (OCT) depend on expensive equipment and expert clinical interpretation, restricting their use in large-scale and low-resource environments. To overcome these challenges, this study introduces ReliaFusion-Net, a reliability-aware multimodal framework for proof-of-concept binary classification of eyes with DR vs. healthy controls, using thermal eye images and radiometric temperature features.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>The proposed ReliaFusion-Net architecture combines bidirectional co-attention with feature-wise linear modulation to effectively model complementary relationships between thermal image features and physiological temperature descriptors. A clinically curated dataset containing 558 thermal eye images, including 278 normal and 280 diabetic samples, was collected with ophthalmologist support. The framework was trained and evaluated for binary classification, and cross-validation experiments were conducted to assess model generalization.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Using an EdgeNeXt backbone, the proposed model achieved 93.18% accuracy, 93.26% F1-score, and 0.9785 AUC on the test set. Cross-validation results further confirmed strong generalization performance. These findings indicate that the reliability-aware multimodal fusion strategy effectively discriminates eyes with DR from healthy controls using non-invasive thermal imaging data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>By dynamically adapting modality contributions based on reliability, ReliaFusion-Net overcomes limitations associated with traditional fixed fusion strategies and improves classification robustness. Overall, the findings demonstrate proof-of-concept of reliability-aware multimodal learning to distinguish eyes with DR from healthy controls using non-invasive thermal imaging, with potential applicability in tele-ophthalmology settings. Future work focuses on multi-stage disease classification and longitudinal disease progression analysis.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1888280","type":"journal-article","created":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T04:21:50Z","timestamp":1786335710000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Reliability-aware fusion of ocular thermal imaging and radiometric features for proof-of-concept classification of diabetic retinopathy vs. healthy controls"],"prefix":"10.3389","volume":"13","author":[{"given":"Persiya","family":"J","sequence":"first","affiliation":[{"name":"School of Electronics Engineering, Vellore Institute of Technology","place":["Chennai, Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sasithradevi","family":"A","sequence":"additional","affiliation":[{"name":"Centre for Advanced Data Science, Vellore Institute of Technology","place":["Chennai, Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anand","family":"Rajendran","sequence":"additional","affiliation":[{"name":"Department of Vitreo-Retina Services, Aravind Eye Hospital","place":["Chennai, Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,10]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1186\/1471-2350-11-158","article-title":"Association analysis of nine candidate gene polymorphisms in Indian patients with type 2 diabetic retinopathy","volume":"11","author":"Balasubbu","year":"2010","journal-title":"BMC Med Genet."},{"key":"B2","doi-asserted-by":"publisher","first-page":"1580","DOI":"10.1016\/j.ophtha.2021.04.027","article-title":"Global prevalence of diabetic retinopathy and projection of burden through 2045: systematic review and meta-analysis","volume":"128","author":"Teo","year":"2021","journal-title":"Ophthalmology."},{"key":"B3","unstructured":""},{"key":"B4","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1016\/j.ophtha.2024.12.020","article-title":"Diabetic retinopathy preferred practice pattern\u00ae","volume":"132","author":"Lim","year":"2025","journal-title":"Ophthalmology."},{"key":"B5","doi-asserted-by":"publisher","first-page":"22","DOI":"10.5935\/0004-2749.20210004","article-title":"Thermography in clinical ophthalmic oncology","volume":"84","author":"Modrzejewska","year":"2021","journal-title":"Arq Bras Oftalmol."},{"key":"B6","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1097\/IAE.0000000000003278","article-title":"Ocular surface temperature differences in retinal vascular diseases","volume":"42","author":"Naidorf-Rosenblatt","year":"2022","journal-title":"Retina."},{"key":"B7","doi-asserted-by":"publisher","first-page":"112379","DOI":"10.1016\/j.diabres.2025.112379","article-title":"Which treatment modality offers the best outcomes for diabetic retinopathy? A systematic review and network meta-analysis","volume":"227","author":"Chen","year":"2025","journal-title":"Diabetes Res Clin Pract."},{"key":"B8","doi-asserted-by":"publisher","first-page":"6262","DOI":"10.62347\/GBFO5856","article-title":"Inflammatory mechanisms in diabetic retinopathy: pathogenic roles and therapeutic perspectives","volume":"17","author":"Qian","year":"2025","journal-title":"Am J Transl Res."},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.3949\/ccjm.91a.24028","article-title":"Diabetic retinopathy: screening, prevention, and treatment","author":"Chong","year":"2024","journal-title":"Cleve Clin J Med."},{"key":"B10","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1107\/jhsmr.v42i6.1102","article-title":"Optical coherence tomography (OCT) and OCT angiography (OCTA) biomarkers for diabetic retinopathy in type 2 diabetes mellitus: a scoping review","volume":"42","author":"Naqaweh","year":"2024","journal-title":"J Heal Sci Med Res."},{"key":"B11","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1016\/j.oret.2020.06.016","article-title":"Diabetic retinopathy screening with automated retinal image analysis in a primary care setting improves adherence to ophthalmic care","volume":"5","author":"Liu","year":"2021","journal-title":"Ophthalmol Retin."},{"key":"B12","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1016\/S2213-8587(19)30411-5","article-title":"Screening for diabetic retinopathy: new perspectives and challenges","volume":"8","author":"Vujosevic","year":"2020","journal-title":"Lancet Diabetes Endocrinol."},{"key":"B13","doi-asserted-by":"publisher","first-page":"110943","DOI":"10.1016\/j.diabres.2023.110943","article-title":"Diagnostic accuracy of smartphone-based artificial intelligence systems for detecting diabetic retinopathy: a systematic review and meta-analysis","volume":"205","author":"Hasan","year":"2023","journal-title":"Diabetes Res Clin Pract."},{"key":"B14","doi-asserted-by":"publisher","first-page":"109099","DOI":"10.1016\/j.exer.2022.109099","article-title":"The ocular surface and diabetes, the other 21st Century epidemic","volume":"220","author":"Bu","year":"2022","journal-title":"Exp Eye Res."},{"key":"B15","doi-asserted-by":"publisher","first-page":"103867","DOI":"10.1016\/j.jtherbio.2024.103867","article-title":"Thermal mapping the eye : a critical review of advances in infrared imaging for disease detection","volume":"121","author":"Persiya","year":"2024","journal-title":"J Therm Biol."},{"key":"B16","doi-asserted-by":"publisher","first-page":"104280","DOI":"10.1016\/j.jtherbio.2025.104280","article-title":"Artificial intelligence-based multimodal framework for non-invasive detection of digital eye strain using thermal imaging and behavioral metrics","volume":"133","author":"Persiya","year":"2025","journal-title":"J Therm Biol."},{"key":"B17","doi-asserted-by":"publisher","first-page":"878","DOI":"10.1136\/bjo.2007.114397","article-title":"Evaluation of ocular surface temperature and retrobulbar haemodynamics by infrared thermography and colour Doppler imaging in patients with glaucoma","volume":"91","author":"Galassi","year":"2007","journal-title":"Br J Ophthalmol."},{"key":"B18","doi-asserted-by":"publisher","first-page":"1004","DOI":"10.1177\/112067210901900617","article-title":"Ocular surface temperature in diabetic retinopathy: a pilot study by infrared thermography","volume":"19","author":"Sodi","year":"2009","journal-title":"Eur J Ophthalmol."},{"key":"B19","doi-asserted-by":"publisher","first-page":"20251234","DOI":"10.31584\/jhsmr.20251234","article-title":"Impact of diabetic retinopathy on ocular surface temperature: insights from medical thermography","volume":"44","author":"Madura Meenakshi","year":"2025","journal-title":"J Heal Sci Med Res"},{"key":"B20","doi-asserted-by":"publisher","first-page":"108749","DOI":"10.1016\/j.exer.2021.108749","article-title":"Ocular surface temperature measurement in diabetic retinopathy","volume":"211","author":"Chandrasekar","year":"2021","journal-title":"Exp Eye Res."},{"key":"B21","doi-asserted-by":"publisher","first-page":"281010","DOI":"10.1155\/2014\/281010","article-title":"Ocular surface temperature in age-related macular degeneration","volume":"2014","author":"Sodi","year":"2014","journal-title":"J Ophthalmol."},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.21611\/QIRT.2023.13","article-title":"Diagnostic tool for diabetic retinopathy using thermal eye images","author":"Rajagopalan","year":"2023","journal-title":"Proceedings of the 2023 International Conference on Quantitative InfraRed Thermography (QIRT 2023)"},{"key":"B23","doi-asserted-by":"publisher","first-page":"106878","DOI":"10.1016\/j.bspc.2024.106878","article-title":"Bispectrum analysis of thermal images for the classification of retinal vascular diseases","volume":"99","author":"Madura Meenakshi","year":"2025","journal-title":"Biomed signal process Control."},{"key":"B24","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1007\/s40009-023-01381-1","article-title":"A multicentric case\u2013control study for diagnostic utility of non-contact infrared thermography (IRT) in type 2 diabetes","volume":"47","author":"Sinha","year":"2024","journal-title":"Natl Acad Sci Lett."},{"key":"B25","doi-asserted-by":"publisher","first-page":"e1013745","DOI":"10.1371\/journal.pcbi.1013745","article-title":"Graphenhanced deep learning for diabetic retinopathy diagnosis: a quality-aware and uncertainty-driven approach","volume":"21","author":"Akter","year":"2025","journal-title":"PLoS Comput Biol."},{"key":"B26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/IJCNN60899.2024.10650642","article-title":"Enhancing diabetic retinopathy detection through transformer based knowledge distillation and explainable AI","volume":"2024","author":"Shafi","year":"2024","journal-title":"International Joint Conference on Neural Networks (IJCNN)"},{"key":"B27","unstructured":"Nieuwland\n            \n            \n              flyr\n              3"},{"key":"B28","doi-asserted-by":"publisher","first-page":"3","DOI":"10.3390\/life13030723","article-title":"Applications of infrared thermography in ophthalmology","volume":"13","author":"Gulias-Ca\u00f1izo","year":"2023","journal-title":"Life."},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-008-9181-5","article-title":"Analysis of normal human eye with different age groups using infrared images","author":"Acharya","year":"2009","journal-title":"J Med Syst."},{"key":"B30","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1016\/j.infrared.2009.10.006","article-title":"Study of normal ocular thermogram using textural parameters","volume":"53","author":"Tan","year":"2010","journal-title":"Infrared Phys Technol."},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.3390\/s25030891","article-title":"Artificial intelligence in ir thermal imaging and sensing for medical applications","author":"Nowakowski","year":"2025","journal-title":"Sensors."},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2015.12.298","article-title":"Implementation of GLCM features in thermal imaging for human affective state detection","author":"Abd Latif","year":"2015","journal-title":"Procedia Comput Sci."},{"key":"B33","doi-asserted-by":"publisher","first-page":"660","DOI":"10.1109\/IMCEC59810.2024.10575449","article-title":"Enhancing skin lesion classification with streamlined self-attention and multi-scale features","volume":"6","author":"Liu","year":"2024","journal-title":"IEEE 6th advanced information management, communicates, electronic and automation control conference (IMCEC)"},{"key":"B34","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1007\/978-3-031-25082-8_1","article-title":"EdgeNeXt: efficiently amalgamated CNN-transformer architecture for mobile vision applications","author":"Maaz","year":"2023","journal-title":"Computer vision - ECCV 2022 workshops. Lecture notes in computer science, Vol.13807"},{"key":"B35","doi-asserted-by":"publisher","first-page":"7907","DOI":"10.1109\/CVPR52729.2023.00764","article-title":"MobileOne: an improved one millisecond mobile backbone","author":"Vasu","year":"2023","journal-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)"},{"key":"B36","doi-asserted-by":"publisher","first-page":"15909","DOI":"10.1109\/CVPR52733.2024.01506","article-title":"Rep ViT: Revisiting mobile CNN from ViT perspective","volume":"2024","author":"Wang","year":"2024","journal-title":"IEEE\/CVF conference on computer vision and pattern recognition (CVPR)"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1704.04861","article-title":"MobileNets: efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv"},{"key":"B38","doi-asserted-by":"publisher","first-page":"1577","DOI":"10.1109\/CVPR42600.2020.00165","article-title":"GhostNet: more features from cheap operations","author":"Han","year":"2020","journal-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)."},{"key":"B39","unstructured":"EfficientNet: Rethinking model scaling for convolutional neural networks\n          \n          6105\n          14\n          \n            \n              Tan\n              M\n            \n            \n              Le\n              QV\n            \n          \n          \n            \n              Kamalika Chaudhuri\n              RS\n            \n          \n          PMLR\n          Proceedings of the 36th international conference on machine learning, ICML 2019, 9-15 June 2019, Long Beach, California, USA\n          \n          2019"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1888280\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T04:21:51Z","timestamp":1786335711000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1888280\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,10]]},"references-count":39,"alternative-id":["10.3389\/fmed.2026.1888280"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1888280","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,10]]},"article-number":"1888280"}}