{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T05:52:26Z","timestamp":1785909146823,"version":"3.56.0"},"reference-count":36,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T00:00:00Z","timestamp":1785888000000},"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                    Precise and reliable diagnosis of leaf diseases in tomato is essential for enhancing crop cultivation and minimizing agricultural losses. While deep learning models have performed well on benchmark datasets, the majority of present techniques rely on flat multi-class classification, which predicts all disease categories simultaneously. Such formulations promotes inter-class confusion, particularly when biologically different diseases with similar visual symptoms are learned within a same model. To overcome this constraint, we propose a biologically structured hierarchical deep learning framework in this study. Instead of directly classifying 10 disease classes, the proposed method first classifies leaf images into meaningful biological groups such as bacterial, fungal, pest-associated and healthy using a vision transformer (ViT) model. Then, specialized convolutional neural network (CNN) experts perform fine-grained classification within each category. The proposed hierarchical model shows an overall accuracy of 97.8%, when validated on PlantVillage tomato dataset. A flat ViT model trained with class-weighted loss obtained 96.3% accuracy, whereas a flat CNN model reached 99.3% under clean conditions but decreased sharply to 41% under Gaussian perturbation (\n                    <jats:italic>\u03c3<\/jats:italic>\n                    \u202f=\u202f0.05). On the other hand, the hierarchical model performed steadily under noise with 97.4% accuracy at the same perturbation level. These results indicate that adding biological structure to model design reduces confusion, helps prevent imbalance effects and increases robustness, providing a more trustworthy and interpretable solution for real-world agricultural disease diagnosis.\n                  <\/jats:p>","DOI":"10.3389\/frai.2026.1880070","type":"journal-article","created":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T05:39:52Z","timestamp":1785908392000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A biologically structured hierarchical vision transformer-CNN framework for robust tomato leaf disease classification"],"prefix":"10.3389","volume":"9","author":[{"given":"Harshinisree","family":"Gunasekaran","sequence":"first","affiliation":[{"name":"School of Biosciences and Technology (SBST), Vellore Institute of Technology (VIT)","place":["Vellore, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sujatha","family":"Rajkumar","sequence":"additional","affiliation":[{"name":"VIT School of Electronics Engineering (SENSE), Vellore Institute of Technology (VIT)","place":["Vellore, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"B.","family":"Lincy Kirubhadharsini","sequence":"additional","affiliation":[{"name":"VIT School of Agricultural Innovations and Advanced Learning (VAIAL), Vellore Institute of Technology (VIT)","place":["Vellore, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,5]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1007\/s40747-024-01764-x","article-title":"A hybrid framework for plant leaf disease detection and classification using convolutional neural networks and vision transformer","volume":"11","author":"Aboelenin","year":"2025","journal-title":"Complex Intell. Syst."},{"key":"ref2","doi-asserted-by":"publisher","first-page":"939","DOI":"10.3390\/sym11070939","article-title":"Solving current limitations of deep learning based approaches for plant disease detection","volume":"11","author":"Arsenovic","year":"2019","journal-title":"Symmetry"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"1763739","DOI":"10.3389\/fpls.2026.1763739","article-title":"ConvGeM-next: a deep learning framework for plant disease detection","volume":"17","author":"Arshad","year":"2026","journal-title":"Front. Plant Sci."},{"key":"ref4","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1016\/j.biosystemseng.2018.05.013","article-title":"Factors influencing the use of deep learning for plant disease recognition","volume":"172","author":"Barbedo","year":"2018","journal-title":"Biosyst. Eng."},{"key":"ref5","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1016\/j.biosystemseng.2019.02.002","article-title":"Plant disease identification from individual lesions and spots using deep learning","volume":"180","author":"Barbedo","year":"2019","journal-title":"Biosyst. Eng."},{"key":"ref6","author":"Chaudhry","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"105393","DOI":"10.1016\/j.compag.2020.105393","article-title":"Using deep transfer learning for image-based plant disease identification","volume":"173","author":"Chen","year":"2020","journal-title":"Comput. Electron. Agric."},{"key":"ref8","first-page":"9268","author":"Cui","year":"2019"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"e0222916","DOI":"10.1371\/journal.pone.0222916","article-title":"Why Cohen\u2019s kappa should be avoided as performance measure in classification","volume":"14","author":"Delgado","year":"2019","journal-title":"PLoS One"},{"key":"ref10","author":"Dosovitskiy","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.48550\/arXiv.2101.03961","article-title":"Switch transformers: scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref12","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1016\/j.compag.2018.01.009","article-title":"Deep learning models for plant disease detection and diagnosis","volume":"145","author":"Ferentinos","year":"2018","journal-title":"Comput. Electron. Agric."},{"key":"ref13","author":"Geirhos","year":"2019"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"4613","DOI":"10.1073\/pnas.1716999115","article-title":"An explainable deep machine vision framework for plant stress phenotyping","volume":"115","author":"Ghosal","year":"2018","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"19316","DOI":"10.1038\/s41598-026-50684-y","article-title":"Deep learning-based citrus plant disease classification using a computationally efficient CNN model","volume":"16","author":"Goyal","year":"2026","journal-title":"Sci. Rep."},{"key":"ref16","doi-asserted-by":"publisher","first-page":"1737208","DOI":"10.3389\/fpls.2025.1737208","article-title":"Lightweight deep learning for tomato disease detection: trends, challenges, and edge AI perspectives","volume":"16","author":"Gunasekaran","year":"2026","journal-title":"Front. Plant Sci."},{"key":"ref17","author":"Hendrycks","year":"2019"},{"key":"ref18","author":"Iwano","year":"2024"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"2252","DOI":"10.3390\/plants14152252","article-title":"ConvTransNet-S: a CNN-transformer hybrid disease recognition model for complex field environments","volume":"14","author":"Jia","year":"2025","journal-title":"Plants"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1186\/s40537-019-0192-5","article-title":"Survey on deep learning with class imbalance","volume":"6","author":"Johnson","year":"2019","journal-title":"J. Big Data"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1016\/j.compag.2018.02.016","article-title":"Deep learning in agriculture: a survey","volume":"147","author":"Kamilaris","year":"2018","journal-title":"Comput. Electron. Agric."},{"key":"ref22","doi-asserted-by":"publisher","first-page":"1640549","DOI":"10.3389\/frai.2025.1640549","article-title":"Enhanced plant disease classification with attention-based convolutional neural network using squeeze and excitation mechanism","volume":"8","author":"Karthikeyan","year":"2025","journal-title":"Front. Artif. Intell."},{"key":"ref23","author":"Lin","year":"2017"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"1419","DOI":"10.3389\/fpls.2016.01419","article-title":"Using deep learning for image-based plant disease detection","volume":"7","author":"Mohanty","year":"2016","journal-title":"Front. Plant Sci."},{"key":"ref25","doi-asserted-by":"publisher","first-page":"268","DOI":"10.3390\/agriengineering7080268","article-title":"A robust lightweight vision transformer for classification of crop diseases","volume":"7","author":"Mookkandi","year":"2025","journal-title":"AgriEngineering"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"468","DOI":"10.3390\/plants8110468","article-title":"Plant disease detection and classification by deep learning","volume":"8","author":"Saleem","year":"2019","journal-title":"Plants"},{"key":"ref27","author":"Shazeer","year":"2017"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"1158933","DOI":"10.3389\/fpls.2023.1158933","article-title":"An advanced deep learning models-based plant disease detection: a review of recent research","volume":"14","author":"Shoaib","year":"2023","journal-title":"Front. Plant Sci."},{"key":"ref29","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1007\/s10618-010-0175-9","article-title":"A survey of hierarchical classification across different application domains","volume":"22","author":"Silla","year":"2011","journal-title":"Data Min. Knowl. Discov."},{"key":"ref30","author":"Singh","year":"2020"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"3289801","DOI":"10.1155\/2016\/3289801","article-title":"Deep neural networks based recognition of plant diseases by leaf image classification","volume":"2016","author":"Sladojevic","year":"2016","journal-title":"Comput. Intell. Neurosci."},{"key":"ref32","author":"Tan","year":"2019"},{"key":"ref33","author":"Thakur","year":"2022"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"272","DOI":"10.1016\/j.compag.2018.03.032","article-title":"A comparative study of fine-tuning deep learning models for plant disease identification","volume":"161","author":"Too","year":"2019","journal-title":"Comput. Electron. Agric."},{"key":"ref35","author":"Touvron","year":"2021"},{"key":"ref36","author":"Wehrmann","year":"2018"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1880070\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T05:39:53Z","timestamp":1785908393000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1880070\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,5]]},"references-count":36,"alternative-id":["10.3389\/frai.2026.1880070"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1880070","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,5]]},"article-number":"1880070"}}