{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T21:21:47Z","timestamp":1793222507927,"version":"4.5.0"},"reference-count":59,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T00:00:00Z","timestamp":1788134400000},"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. Artif. Intell."],"abstract":"<jats:p>\n                    Accurate classification of retinal diseases from optical coherence tomography (OCT) images is important for clinical decision support. However, many studies in deep learning put the primary focus on enhancing accuracy and often provide limited attention to calibration and robustness under real-world variations. This work presents an enhanced ConvNeXt-Tiny framework incorporating a Spatial Adaptive Multi-scale Convolution (SAMC) module for retinal OCT classification. Rather than introducing a new convolutional operation, SAMC combines established multi-scale dilated convolution and feature fusion principles in a lightweight stage-wise configuration within the ConvNeXt hierarchy to refine representations of retinal abnormalities occurring at different spatial scales. The model is evaluated on the OCT-C8 dataset with eight retinal disease classes. It obtains a test accuracy of 98.39% and a macro F1 score of 0.9839. Reliability of classification was also analyzed by measuring Expected Calibration Error (ECE) and Brier score. Temperature scaling is applied as a\n                    <jats:italic>post-hoc<\/jats:italic>\n                    calibration method, while Monte Carlo dropout is used to estimate predictive variability under stochastic inference. Robustness is evaluated under noise, blur, and illumination changes, where minimal performance drop was observed. Computational complexity analysis is performed in terms of model parameters, floating-point operations, and inference efficiency to assess the practicality of the proposed framework. Statistical significance is confirmed using McNemar's test. Interpretability analysis with Grad-CAM and LIME reveals the model attends to clinically significant regions of the retina. Overall, the proposed ConvNeXt-SAMC framework achieves accurate retinal disease classification, while additional calibration, uncertainty, robustness, statistical, and interpretability analyses provide a broader assessment of model behavior.\n                  <\/jats:p>","DOI":"10.3389\/frai.2026.1898978","type":"journal-article","created":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T05:41:06Z","timestamp":1788154866000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["A spatial adaptive multi-scale ConvNeXt framework for robust, calibrated, and statistically validated multi-class retinal OCT classification"],"prefix":"10.3389","volume":"9","author":[{"given":"Mithun","family":"Vijayan","sequence":"first","affiliation":[{"name":"School of Electronics Engineering, Vellore Institute of Technology","place":["Vellore, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Goutham","family":"Veerapu","sequence":"additional","affiliation":[{"name":"School of Electronics Engineering, Vellore Institute of Technology","place":["Vellore, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nisha","family":"J. S.","sequence":"additional","affiliation":[{"name":"School of Electronics Engineering, Vellore Institute of Technology","place":["Vellore, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,31]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1175\/1520-0493(1950)078<0001:VOFEIT>2.0.CO;2","article-title":"Verification of forecasts expressed in terms of probability","volume":"78","author":"Brier","year":"1950","journal-title":"Monthly Weath. Rev"},{"key":"B2","doi-asserted-by":"publisher","first-page":"125","DOI":"10.3390\/info11020125","article-title":"Albumentations: fast and flexible image augmentations","volume":"11","author":"Buslaev","year":"2020","journal-title":"Information"},{"key":"B3","doi-asserted-by":"publisher","first-page":"1605","DOI":"10.1364\/BOE.510464","article-title":"Self-attention CNN for retinal layer segmentation in oct","volume":"15","author":"Cao","year":"2024","journal-title":"Biomed. Opt. Express"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_49","article-title":"\u201cEncoder-decoder with atrous separable convolution for semantic image segmentation,\u201d","author":"Chen","year":"2018","journal-title":"Proceedings of the European conference on computer vision (ECCV)"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2025.108189","article-title":"Wavenet-sf: a hybrid network for retinal disease detection based on wavelet transform in spatial-frequency domain","author":"Cheng","year":"2025","journal-title":"arXiv preprint arXiv:2501.11854"},{"key":"B6","doi-asserted-by":"publisher","first-page":"101605","DOI":"10.1016\/j.bspc.2019.101605","article-title":"Multi-scale deep feature fusion for automated classification of macular pathologies from OCT images","volume":"54","author":"Das","year":"2019","journal-title":"Biomed. Signal Process. Control"},{"key":"B7","doi-asserted-by":"publisher","first-page":"1342","DOI":"10.1038\/s41591-018-0107-6","article-title":"Clinically applicable deep learning for diagnosis and referral in retinal disease","volume":"24","author":"De Fauw","year":"2018","journal-title":"Nat. Med"},{"key":"B8","first-page":"1","article-title":"Statistical comparisons of classifiers over multiple data sets","volume":"7","author":"Dem\u0161ar","year":"2006","journal-title":"J. Mach. Learn. Res"},{"key":"B9","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1109\/CVPR.2009.5206848","article-title":"\u201cImagenet: a large-scale hierarchical image database,\u201d","volume-title":"2009 IEEE conference on computer vision and pattern recognition","author":"Deng","year":"2009"},{"key":"B10","doi-asserted-by":"publisher","first-page":"1895","DOI":"10.1162\/089976698300017197","article-title":"Approximate statistical tests for comparing supervised classification learning algorithms","volume":"10","author":"Dietterich","year":"1998","journal-title":"Neural Comput"},{"key":"B11","article-title":"\u201cAn image is worth 16 \u00d7 16 words: transformers for image recognition at scale,\u201d","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-77550-8","author":"Drexler","year":"2008","journal-title":"Optical Coherence Tomography: Technology and Applications"},{"key":"B13","doi-asserted-by":"publisher","first-page":"861","DOI":"10.1016\/j.patrec.2005.10.010","article-title":"An introduction to roc analysis","volume":"27","author":"Fawcett","year":"2006","journal-title":"Pattern Recognit. Lett"},{"key":"B14","first-page":"1050","article-title":"\u201cDropout as a bayesian approximation: representing model uncertainty in deep learning,\u201d","volume-title":"international conference on machine learning","author":"Gal","year":"2016"},{"key":"B15","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1109\/TPAMI.2019.2938758","article-title":"Res2net: a new multi-scale backbone architecture","volume":"43","author":"Gao","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B16","first-page":"1321","article-title":"\u201cOn calibration of modern neural networks,\u201d","volume-title":"International conference on machine learning","author":"Guo","year":"2017"},{"key":"B17","doi-asserted-by":"publisher","first-page":"100170","DOI":"10.1016\/j.fraope.2024.100170","article-title":"Squeeze &excitation joint with combined channel and spatial attention for pathology image super-resolution","volume":"8","author":"Hayat","year":"2024","journal-title":"Franklin Open"},{"key":"B18","doi-asserted-by":"publisher","first-page":"3637","DOI":"10.1038\/s41598-023-30853-z","article-title":"An interpretable transformer network for the retinal disease classification using optical coherence tomography","volume":"13","author":"He","year":"2023","journal-title":"Sci. Rep"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90","article-title":"\u201cDeep residual learning for image recognition,\u201d","author":"He","year":"2016","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"B20","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","author":"Hendrycks","year":"2019","journal-title":"arXiv preprint arXiv:1903.12261"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745","article-title":"\u201cSqueeze-and-excitation networks,\u201d","author":"Hu","year":"2018","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1178","DOI":"10.1126\/science.1957169","article-title":"Optical coherence tomography","volume":"254","author":"Huang","year":"1991","journal-title":"Science"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243","article-title":"\u201cDensely connected convolutional networks,\u201d","author":"Huang","year":"2017","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1143422","DOI":"10.3389\/fnins.2023.1143422","article-title":"Gabnet: global attention block for retinal oct disease classification","volume":"17","author":"Huang","year":"2023","journal-title":"Front. Neurosci"},{"key":"B25","doi-asserted-by":"publisher","first-page":"104176","DOI":"10.1016\/j.bspc.2022.104176","article-title":"Convolution neural networks for optical coherence tomography (oct) image classification","volume":"79","author":"Karthik","year":"2023","journal-title":"Biomed. Signal Process. Control"},{"key":"B26","doi-asserted-by":"publisher","first-page":"1122","DOI":"10.1016\/j.cell.2018.02.010","article-title":"Identifying medical diagnoses and treatable diseases by image-based deep learning","volume":"172","author":"Kermany","year":"2018","journal-title":"Cell"},{"key":"B27","doi-asserted-by":"publisher","first-page":"108726","DOI":"10.1016\/j.compbiomed.2024.108726","article-title":"Htc-retina: a hybrid retinal diseases classification model using transformer-convolutional neural network from optical coherence tomography images","volume":"178","author":"Laouarem","year":"2024","journal-title":"Comput. Biol. Med"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106","article-title":"\u201cFeature pyramid networks for object detection,\u201d","author":"Lin","year":"2017","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01386","article-title":"\u201cEfficientvit: memory efficient vision transformer with cascaded group attention,\u201d","author":"Liu","year":"2023","journal-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition"},{"key":"B30","doi-asserted-by":"crossref","first-page":"9992","DOI":"10.1109\/ICCV48922.2021.00986","article-title":"\u201cSwin transformer: hierarchical vision transformer using shifted windows,\u201d","volume-title":"2021 IEEE\/CVF international conference on computer vision (ICCV)","author":"Liu","year":"2021"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167","article-title":"\u201cA convnet for the 2020s,\u201d","author":"Liu","year":"2022","journal-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition"},{"key":"B32","article-title":"Sgdr: stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2016","journal-title":"arXiv preprint arXiv:1608.03983"},{"key":"B33","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint arXiv:1711.05101"},{"key":"B34","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1007\/BF02295996","article-title":"Note on the sampling error of the difference between correlated proportions or percentages","volume":"12","author":"McNemar","year":"1947","journal-title":"Psychometrika"},{"key":"B35","article-title":"Mixed precision training","author":"Micikevicius","year":"2017","journal-title":"arXiv preprint arXiv:1710.03740"},{"key":"B36","doi-asserted-by":"publisher","first-page":"161","DOI":"10.5114\/reum\/166296","article-title":"Subclinical retinopathy in systemic lupus erythematosus patients - optical coherence tomography study","volume":"61","author":"Mimier-Janczak","year":"2023","journal-title":"Reumatologia"},{"key":"B37","first-page":"15682","article-title":"\u201cRevisiting the calibration of modern neural networks,\u201d","author":"Minderer","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"B38","unstructured":"Mooney\n              P.\n            \n          \n          Retinal oct images (optical coherence tomography)\n          \n          2018"},{"key":"B39","volume-title":"Retinal oct-c8","author":"Naren","year":"2021"},{"key":"B40","article-title":"\u201cCan you trust your model's uncertainty? Evaluating predictive uncertainty under dataset shift,\u201d","author":"Ovadia","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"B41","doi-asserted-by":"publisher","first-page":"107146","DOI":"10.1016\/j.bspc.2024.107146","article-title":"A lightweight model for the retinal disease classification using optical coherence tomography","volume":"101","author":"Pan","year":"2025","journal-title":"Biomed. Signal Process. Control"},{"key":"B42","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","article-title":"A survey on transfer learning","volume":"22","author":"Pan","year":"2009","journal-title":"IEEE Trans. Knowl. Data Eng"},{"key":"B43","article-title":"Evaluation: from precision, recall and f-measure to roc, informedness, markedness and correlation","author":"Powers","year":"2020","journal-title":"arXiv preprint arXiv:2010.16061"},{"key":"B44","doi-asserted-by":"publisher","first-page":"1608325","DOI":"10.3389\/fcell.2025.1608325","article-title":"Msli-net: retinal disease detection network based on multi-segment localization and multi-scale interaction","volume":"13","author":"Qi","year":"2025","journal-title":"Front. Cell Dev. Biol"},{"key":"B45","doi-asserted-by":"publisher","first-page":"1024","DOI":"10.1109\/TMI.2017.2780115","article-title":"Macular OCT classification using a multi-scale convolutional neural network ensemble","volume":"37","author":"Rasti","year":"2017","journal-title":"IEEE Trans. Med. Imaging."},{"key":"B46","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939778","article-title":"\u201c\u2018Why should i trust you?' explaining the predictions of any classifier,\u201d","author":"Ribeiro","year":"2016","journal-title":"Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining"},{"key":"B47","doi-asserted-by":"publisher","DOI":"10.17487\/rfc1321","author":"Rivest","year":"1992","journal-title":"The md5 message-digest algorithm"},{"key":"B48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74","article-title":"\u201cGrad-cam: visual explanations from deep networks via gradient-based localization,\u201d","author":"Selvaraju","year":"2017","journal-title":"Proceedings of the IEEE international conference on computer vision"},{"key":"B49","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-019-0197-0","article-title":"A survey on image data augmentation for deep learning","volume":"6","author":"Shorten","year":"2019","journal-title":"J. Big Data"},{"key":"B50","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1016\/j.ipm.2009.03.002","article-title":"A systematic analysis of performance measures for classification tasks","volume":"45","author":"Sokolova","year":"2009","journal-title":"Inf. Proc. Manag"},{"key":"B51","doi-asserted-by":"publisher","first-page":"e144","DOI":"10.1016\/S2214-109X(20)30489-7","article-title":"Causes of blindness and vision impairment in 2020 and trends over 30 years, and prevalence of avoidable blindness in relation to vision 2020: the right to sight: an analysis for the global burden of disease study","volume":"9","author":"Steinmetz","year":"2021","journal-title":"Lancet Global Health"},{"key":"B52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308","article-title":"\u201cRethinking the inception architecture for computer vision,\u201d","author":"Szegedy","year":"2016","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"B53","first-page":"6105","article-title":"\u201cEfficientnet: rethinking model scaling for convolutional neural networks,\u201d","volume-title":"International conference on machine learning","author":"Tan","year":"2019"},{"key":"B54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_1","article-title":"\u201cCbam: convolutional block attention module,\u201d","author":"Woo","year":"2018","journal-title":"Proceedings of the European conference on computer vision (ECCV)"},{"key":"B55","unstructured":"Blindness and vision impairment: Fact sheet\n          \n          2024"},{"key":"B56","article-title":"Afpn: asymptotic feature pyramid network for object detection","author":"Yang","year":"2023","journal-title":"arXiv preprint arXiv:2306.15988"},{"key":"B57","article-title":"Multi-scale context aggregation by dilated convolutions","author":"Yu","year":"2015","journal-title":"arXiv preprint arXiv:1511.07122"},{"key":"B58","article-title":"Cross-cbam: a lightweight network for scene segmentation","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv:2306.02306"},{"key":"B59","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s12561-025-09505-5","article-title":"Weighted brier score\u2014an overall summary measure for risk prediction models with clinical utility consideration","volume":"2025","author":"Zhu","year":"2025","journal-title":"Stat. Biosci"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1898978\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T05:41:11Z","timestamp":1788154871000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1898978\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,31]]},"references-count":59,"alternative-id":["10.3389\/frai.2026.1898978"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1898978","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,31]]},"article-number":"1898978"}}