{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T06:40:13Z","timestamp":1767595213910,"version":"3.48.0"},"reference-count":55,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T00:00:00Z","timestamp":1767571200000},"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:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>\n                      Artificial intelligence (AI), particularly deep learning (DL), offers automated solutions for early detection of plant diseases to improve crop yield. However, training accurate models on real-field data remains challenging due to over fitting and limited generalization. As observed in prior studies, traditional CNNs often struggle with real-environment variability, and transfer learning can lead to instability in training on domain-specific leaf datasets. This study focuses on detecting dome galls, a disease in\n                      <jats:italic>Cordia dichotoma<\/jats:italic>\n                      , by formulating a binary classification task (healthy vs. diseased leaves) using a custom dataset of 3,900 leaf images collected from real field environments.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Initially, both custom CNNs and transfer learning models were trained and compared. Among them, a modified ResNet-50 architecture showed promising results but suffered from over fitting and unstable convergence. To address this, the final sigmoid activation layer was replaced with a Support Vector Machine (SVM), and L2 regularization was applied to reduce over fitting. This hybrid DeepSVM architecture stabilized training and improved model robustness. Image preprocessing and augmentation techniques were applied to increase variability and prevent over fitting.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The final model was evaluated on a separate test set of 400 images, and the results remained stable across repeated runs. DeepSVM achieved an accuracy of 94.50% and an F1-score of 94.47%, outperforming other well-known models like VGG-16, InceptionResNetv2, and MobileNet-V2.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>These results indicate that the proposed DeepSVM approach offers better generalization and training stability than conventional CNN classifiers, potentially aiding in automated disease monitoring for precision agriculture.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frai.2025.1558358","type":"journal-article","created":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T06:38:07Z","timestamp":1767595087000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Anatomical study and early diagnosis of dome galls in Cordia Dichotoma using DeepSVM model"],"prefix":"10.3389","volume":"8","author":[{"given":"Said Khalid","family":"Shah","sequence":"first","affiliation":[]},{"given":"Mazliham Bin Mohd","family":"Su\u2019ud","sequence":"additional","affiliation":[]},{"given":"Aurangzeb","family":"Khan","sequence":"additional","affiliation":[]},{"given":"Muhammad Mansoor","family":"Alam","sequence":"additional","affiliation":[]},{"given":"Muhammad","family":"Ayaz","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2026,1,5]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"5919","DOI":"10.3390\/app12125919","article-title":"Smart agriculture applications using deep learning technologies: a survey","volume":"12","author":"Altalak","year":"2022","journal-title":"Appl. Sci."},{"key":"ref2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12870-020-02777-7","article-title":"Dynamics of limited neoplastic growth on Pongamia pinnata (L.)(Fabaceae) leaf, induced by Aceria pongamiae (Acari: Eriophyidae)","volume":"21","author":"Anand","year":"2021","journal-title":"BMC Plant Biol."},{"key":"ref3","doi-asserted-by":"publisher","first-page":"406","DOI":"10.1016\/j.aej.2023.07.076","article-title":"PLDPNet: end-to-end hybrid deep learning framework for potato leaf disease prediction","volume":"78","author":"Arshad","year":"2023","journal-title":"Alex. Eng. J."},{"key":"ref4","first-page":"278","author":"Ashikuzzaman","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"480","DOI":"10.1016\/j.matpr.2021.05.584","article-title":"Automated plant leaf disease detection and classification using optimal MobileNet based convolutional neural networks","volume":"51","author":"Ashwinkumar","year":"2022","journal-title":"Mater Today Proc"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"342","DOI":"10.1590\/S0102-695X2013005000020","article-title":"Evaluation of reversible contraceptive potential of Cordia dichotoma leaves extract","volume":"23","author":"Bhattacharya","year":"2013","journal-title":"Rev. Bras"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"681","DOI":"10.32604\/cmc.2023.037958","article-title":"Deep learning-based trees disease recognition and classification using hyperspectral data","volume":"77","author":"Bhatti","year":"2023","journal-title":"Comp. Materials Continua"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"5397","DOI":"10.1007\/s11042-024-20327-3","article-title":"Thoracic-net: explainable artificial intelligence (XAI) based few shots learning feature fusion technique for multi-classifying thoracic diseases using medical imaging","volume":"84","author":"Bhosale","year":"2024","journal-title":"Multimed. Tools Appl."},{"key":"ref9","first-page":"1","author":"Bhosale","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"172","DOI":"10.36548\/jscp.2022.3.006","article-title":"Rice leaf diseases classification using discriminative fine tuning and CLR on efficientNet","volume":"4","author":"Bhujel","year":"2022","journal-title":"J. Soft Computing Paradigm"},{"key":"ref11","first-page":"1624","author":"Chakraborty","year":"2021"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"294","DOI":"10.3390\/agriengineering3020020","article-title":"Automatic and reliable leaf disease detection using deep learning techniques","volume":"3","author":"Chowdhury","year":"2021","journal-title":"AgriEngineering"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1007\/s00425-017-2778-5","article-title":"Neovascularization during leafy gall formation on Arabidopsis thaliana upon Rhodococcus fascians infection","volume":"247","author":"Dolzblasz","year":"2018","journal-title":"Planta"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1007\/978-94-017-8783-3_2","article-title":"Developmental anatomy of galls in the Neotropics: arthropods stimuli versus host plant constraints","author":"dos Santos Isaias","year":"2014","journal-title":"Neotropical insect galls"},{"key":"ref15","volume-title":"See discussions, stats, and author profiles for this publication. Net\/publication\/350567414 surface water quality assessment in semi-arid region (el hodna watershed, Algeria) based on water quality index (WQI)","author":"Ferahtia","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1016\/j.flora.2014.06.004","article-title":"Floral-like destiny induced by a galling Cecidomyiidae on the axillary buds of Marcetia taxifolia (Melastomataceae)","volume":"209","author":"Ferreira","year":"2014","journal-title":"Flora-Morphology, Distribution, Functional Ecology of Plants"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"850","DOI":"10.3109\/13880209.2010.551539","article-title":"Use of cordia dichotoma bark in the treatment of ulcerative colitis","volume":"49","author":"Ganjare","year":"2011","journal-title":"Pharm. Biol."},{"key":"ref18","first-page":"230","author":"Ghosal","year":"2020"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"1787","DOI":"10.3390\/plants10091787","article-title":"Calcium oxalate crystals in leaves of the extremophile plant colobanthus quitensis (Kunth) bartl","volume":"10","author":"G\u00f3mez-Espinoza","year":"2021","journal-title":"(caryophyllaceae). Plants"},{"key":"ref20","first-page":"25","author":"Hong","year":"2020"},{"key":"ref21","author":"Hungilo","year":"2019"},{"key":"ref22","first-page":"1","author":"Islam","year":"2017"},{"key":"ref23","first-page":"1","author":"Jakjoud","year":"2019"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"367","DOI":"10.32604\/cmc.2023.037310","article-title":"Plant leaf diseases classification using improved k-means clustering and svm algorithm for segmentation","volume":"76","author":"Jamjoom","year":"2023","journal-title":"Comp. Materials & Continua"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11676-019-01034-4","article-title":"Protective and defensive roles of non-glandular trichomes against multiple stresses: structure\u2013function coordination","volume":"31","author":"Karabourniotis","year":"2020","journal-title":"J. For. Res."},{"key":"ref26","doi-asserted-by":"publisher","first-page":"111275","DOI":"10.1016\/j.envres.2021.111275","article-title":"Rice leaf diseases prediction using deep neural networks with transfer learning","volume":"198","author":"Krishnamoorthy","year":"2021","journal-title":"Environ. Res."},{"key":"ref27","first-page":"1","author":"Kumar","year":"2019"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"981","DOI":"10.1007\/s11045-022-00820-4","article-title":"Deep CNN model for crops\u2019 diseases detection using leaf images","volume":"33","author":"Kurmi","year":"2022","journal-title":"Multidim. Syst. Sign. Process."},{"key":"ref29","doi-asserted-by":"publisher","first-page":"102809","DOI":"10.1016\/j.inffus.2024.102809","article-title":"Cascaded frameworks in underwater optical image restoration","volume":"117","author":"Li","year":"2025","journal-title":"Information Fusion"},{"key":"ref30","first-page":"1","author":"Li","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"5193","DOI":"10.1038\/s41598-019-41656-6","article-title":"Macro-and microscopic analyses of anatomical structures of Chinese gallnuts and their functional adaptation","volume":"9","author":"Lu","year":"2019","journal-title":"Sci. Rep."},{"key":"ref32","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1080\/10807039.2022.2064814","article-title":"A novel framework for potato leaf disease detection using an efficient deep learning model","volume":"29","author":"Mahum","year":"2023","journal-title":"Hum. Ecol. Risk Assess. Int. J."},{"key":"ref33","doi-asserted-by":"publisher","first-page":"542","DOI":"10.1016\/j.bjp.2015.05.012","article-title":"The genus cordia: botanists, ethno, chemical and pharmacological aspects","volume":"25","author":"Matias","year":"2015","journal-title":"Rev. Bras"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1007\/s13198-020-00972-1","article-title":"Systematic review of deep learning techniques in plant disease detection","volume":"11","author":"Nagaraju","year":"2020","journal-title":"Int. J. Syst. Assur. Eng. Manag."},{"key":"ref35","doi-asserted-by":"publisher","first-page":"254","DOI":"10.1007\/s11515-012-1224-0","article-title":"Plant calcium oxalate crystal formation, function, and its impact on human health","volume":"7","author":"Nakata","year":"2012","journal-title":"Front. Biol."},{"key":"ref36","first-page":"165","author":"Nandhini","year":"2021"},{"key":"ref37","first-page":"1161","author":"Naveenkumar","year":"2021"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"413","DOI":"10.3390\/ai2030026","article-title":"A deep learning enabled multi-class plant disease detection model based on computer vision","volume":"2","author":"Roy","year":"2021","journal-title":"Ai"},{"key":"ref39","first-page":"72","author":"Rozaqi","year":"2020"},{"key":"ref40","author":"Sandler","year":"2018"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"129","DOI":"10.13005\/ojcst13.0203.11","article-title":"Early prediction of potato leaf diseases using ANN classifier","volume":"13","author":"Sanjeev","year":"2021","journal-title":"Oriental J. Computer Sci. Technol."},{"key":"ref42","first-page":"2537","author":"Shijie","year":"2017"},{"key":"ref43","volume-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref44","first-page":"012121","author":"Singh","year":"2021"},{"key":"ref45","doi-asserted-by":"publisher","first-page":"9828","DOI":"10.1038\/s41598-025-93505-4","article-title":"Exploring the impact of hyperparameter and data augmentation in YOLO V10 for accurate bone fracture detection from X-ray images","volume":"15","author":"Srinivasu","year":"2025","journal-title":"Sci. Rep."},{"key":"ref46","doi-asserted-by":"publisher","first-page":"103615","DOI":"10.1016\/j.micpro.2020.103615","article-title":"Performance of deep learning vs machine learning in plant leaf disease detection","volume":"80","author":"Sujatha","year":"2021","journal-title":"Microprocess. Microsyst."},{"key":"ref47","doi-asserted-by":"publisher","first-page":"927","DOI":"10.1007\/s10489-021-02452-w","article-title":"Citrus disease detection and classification using end-to-end anchor-based deep learning model","volume":"52","author":"Syed-Ab-Rahman","year":"2022","journal-title":"Appl. Intell."},{"key":"ref48","volume-title":"Deep learning using support vector machines. CoRR, abs\/1306.0239","author":"Tang","year":"2013"},{"key":"ref49","doi-asserted-by":"crossref","first-page":"1212747","DOI":"10.3389\/fpls.2023.1212747","article-title":"An effective approach for plant leaf diseases classification based on a novel DeepPlantNet deep learning model","volume":"14","author":"Ullah","year":"2023","journal-title":"Front. Plant Sci."},{"key":"ref50","doi-asserted-by":"publisher","first-page":"73019","DOI":"10.1109\/ACCESS.2022.3189676","article-title":"An efficient approach for crops pests\u2019 recognition and classification based on novel deeppestnet deep learning model","volume":"10","author":"Ullah","year":"2022","journal-title":"IEEE Access"},{"key":"ref51","doi-asserted-by":"publisher","first-page":"3969","DOI":"10.32604\/cmc.2023.041819","article-title":"A lightweight deep learning-based model for tomato leaf disease classification","volume":"77","author":"Ullah","year":"2023","journal-title":"Computers, Materials & Continua"},{"key":"ref52","doi-asserted-by":"publisher","first-page":"260991","DOI":"10.3389\/fpls.2017.01505","article-title":"A comparative study of sample preparation for staining and immunodetection of plant cell walls by light microscopy","volume":"8","author":"Verhertbruggen","year":"2017","journal-title":"Front. Plant Sci."},{"key":"ref53","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2021\/9981437","article-title":"Deep learning-based image processing for cotton leaf disease and pest diagnosis","volume":"2021","author":"Zekiwos","year":"2021","journal-title":"J. Electric. Computer Eng."},{"key":"ref54","doi-asserted-by":"crossref","first-page":"1100403","DOI":"10.1007\/s11431-024-2824-x","article-title":"FDNet: Fourier transform guided dual-channel underwater image enhancement diffusion network","volume":"68","author":"Zhu","year":"2025","journal-title":"SCIENCE CHINA Technol. Sci."},{"key":"ref55","doi-asserted-by":"publisher","first-page":"102385","DOI":"10.1016\/j.inffus.2024.102385","article-title":"PODB: a learning-based polarimetric object detection benchmark for road scenes in adverse weather conditions","volume":"108","author":"Zhu","year":"2024","journal-title":"Information Fusion"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1558358\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T06:38:09Z","timestamp":1767595089000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1558358\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,5]]},"references-count":55,"alternative-id":["10.3389\/frai.2025.1558358"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1558358","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,5]]},"article-number":"1558358"}}