{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T06:04:39Z","timestamp":1789538679014,"version":"build-2803163510"},"reference-count":33,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T00:00:00Z","timestamp":1789516800000},"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. Plant Sci."],"abstract":"<jats:p>Citrus greening or Huanglongbing (HLB) is a major threat to global citrus production, yet its visual symptoms often overlap with those of zinc (Zn) deficiency, complicating accurate diagnosis and disease management. This study presents a biologically validated, image-based deep learning method for distinguishing HLB, Zn deficiency, and their co-occurrence in citrus leaves. A total of 2,500 leaves were collected from commercial orchards and imaged using high-resolution flatbed scanning. Five independent expert observers visually classified each leaf into four categories: healthy, HLB, Zn deficiency, and combined HLB and Zn. All samples were subjected to PCR analysis to confirm HLB infection. Comparison between expert assessment and PCR results revealed substantial inter-observer variability and an overall expert diagnostic accuracy of 80.5%, highlighting the inherent limitations of symptom-based visual diagnosis. A hybrid labeling strategy integrating PCR validation for HLB and expert-defined phenotypic evidence for Zn deficiency was used to generate a class-balanced dataset of 1,600 leaves. A multi-label convolutional neural network (CNN) trained on this dataset demonstrated strong diagnostic performance on a PCR-validated validation set, achieving F1-scores of 0.928 (Healthy), 0.936 (HLB), and 0.929 (Zn deficiency), with a Macro-F1 score of 0.931 and an exact-match accuracy of 0.876. Misclassifications were largely confined to physiologically related classes, consistent with overlapping symptom expression. These results demonstrate that deep learning models trained on molecularly validated ground truth can outperform visual diagnosis and serve as scalable decision-support tools for citrus disease management. By enabling more accurate differentiation between HLB infection and nutrient deficiency, this approach can reduce unnecessary or incorrect chemical applications in orchards. Consequently, it supports more precise crop management practices and contributes to sustainable agriculture and environmentally responsible plant protection.<\/jats:p>","DOI":"10.3389\/fpls.2026.1853541","type":"journal-article","created":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T05:31:04Z","timestamp":1789536664000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep learning\u2013based visual diagnosis of Huanglongbing and zinc deficiency in citrus leaves for sustainable and precision orchard management"],"prefix":"10.3389","volume":"17","author":[{"given":"Wannaporn","family":"Thepbandit","sequence":"first","affiliation":[{"name":"Department of Agricultural Technology, Faculty of Science and Technology, Thammasat University","place":["Pathum Thani, Thailand"]},{"name":"Department of Innovative Agriculture, College of Creative Agriculture for Society, Srinakharinwirot University","place":["Nakhon-Nayok, Thailand"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Martinez Lacasa","sequence":"additional","affiliation":[{"name":"Department of Agricultural Technology, Faculty of Science and Technology, Thammasat University","place":["Pathum Thani, Thailand"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anthikan","family":"Klomchit","sequence":"additional","affiliation":[{"name":"Department of Agricultural Technology, Faculty of Science and Technology, Thammasat University","place":["Pathum Thani, Thailand"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dusit","family":"Athinuwat","sequence":"additional","affiliation":[{"name":"Department of Agricultural Technology, Faculty of Science and Technology, Thammasat University","place":["Pathum Thani, Thailand"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,16]]},"reference":[{"key":"B1","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1016\/B978-0-12-816086-2.00009-6","article-title":"Chapter 9 - Medical images analysis based on multilabel classification","volume-title":"Machine Learning in Bio-Signal Analysis and Diagnostic Imaging","author":"Abdel Maksoud","year":"2019"},{"key":"B2","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1016\/j.compag.2018.08.013","article-title":"Impact of dataset size and variety on the effectiveness of deep learning and transfer learning for plant disease classification","volume":"153","author":"Barbedo","year":"2018","journal-title":"Comput. Electron. Agric."},{"key":"B3","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1007\/s40858-020-00343-y","article-title":"Overview of citrus huanglongbing spread and management strategies in Brazil","volume":"45","author":"Bassanezi","year":"2020","journal-title":"Trop. Plant Pathol."},{"key":"B4","first-page":"7","article-title":"Huanglongbing: a destructive, newly-emerging, century-old disease of citrus","volume":"88","author":"Bov\u00e9","year":"2006","journal-title":"J. Plant Pathol."},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1101\/pdb.prot5177","article-title":"Cetyltrimethyl ammonium bromide (CTAB) DNA miniprep for plant DNA isolation","volume":"2009","author":"Clarke","year":"2009","journal-title":"Cold Spring Harbor Protoc."},{"key":"B6","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1146\/annurev.py.29.090191.000545","article-title":"Citrus greening disease","volume":"29","author":"Da Graca","year":"1991","journal-title":"Annu. Rev. Phytopathol."},{"key":"B7","article-title":"The Asian citrus greening disease (Huanglongbing): evidence note on invasiveness and potential economic impacts for East Africa","author":"Djeddour","year":"2021"},{"key":"B8","doi-asserted-by":"publisher","first-page":"803","DOI":"10.1016\/s2095-3119(15)61276-x","article-title":"Physiological changes and expression characteristics of ZIP family genes under zinc deficiency in navel orange (Citrus sinensis)","volume":"15","author":"Fei","year":"2016","journal-title":"J. Integr. Agric."},{"key":"B9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/plants12010160","article-title":"Huanglongbing pandemic: current challenges and emerging management strategies","volume":"12","author":"Ghosh","year":"2023","journal-title":"Plants"},{"key":"B10","first-page":"83","article-title":"Citrus greening: Overview of the most severe disease of citrus","volume":"2","author":"Ghosh","year":"2018","journal-title":"Advanced Agric. Res. Technol. J."},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1145\/2716262","article-title":"A tutorial on multilabel learning","volume":"47","author":"Gibaja","year":"2015","journal-title":"ACM Comput. Surv."},{"key":"B12","doi-asserted-by":"publisher","first-page":"863","DOI":"10.1080\/03235400802021116","article-title":"Symptom-based diagnosis of Huanglongbing (citrus greening) disease by PCR in sweet orange (Citrus sinensis Osbeck) and acid lime (Citrus aurantifolia Swingle)","volume":"43","author":"Gopal","year":"2010","journal-title":"Arch. Phytopathol. Plant Prot."},{"key":"B13","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1094\/php-2007-0906-01-rv","article-title":"Citrus Huanglongbing: The pathogen and its impact","volume":"8","author":"Gottwald","year":"2007","journal-title":"Plant Health Prog."},{"key":"B14","doi-asserted-by":"publisher","first-page":"330","DOI":"10.1653\/0015-4040(2004)087[0330:acpspa]2.0.co;2","article-title":"Asian citrus psyllids (Sternorrhyncha: Psyllidae) and greening disease of citrus: a literature review and assessment of risk in Florida","volume":"87","author":"Halbert","year":"2004","journal-title":"Florida Entomologist"},{"key":"B15","doi-asserted-by":"publisher","first-page":"1101","DOI":"10.1093\/jn\/137.4.1101","article-title":"Zinc deficiency: A special challenge1","volume":"137","author":"Hambidge","year":"2007","journal-title":"J. Nutr."},{"key":"B16","first-page":"1281","article-title":"Comprehensive performance evaluation of YOLOv11, YOLOv10, YOLOv9, YOLOv8 and YOLOv5 on object detection of power equipment","author":"He","year":"2025"},{"key":"B17","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"B18","first-page":"1314","article-title":"Searching for mobilenetv3","author":"Howard","year":"2019"},{"key":"B19","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1016\/j.mimet.2005.10.018","article-title":"Quantitative real-time PCR for detection and identification of Candidatus Liberibacter species associated with citrus huanglongbing","volume":"66","author":"Li","year":"2006","journal-title":"J. Microbiol. Methods"},{"key":"B20","first-page":"11976","article-title":"A convnet for the 2020s","author":"Liu","year":"2022"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2023.1176513","article-title":"Real-time on-site detection of the three \u2018Candidatus Liberibacter\u2019species associated with HLB disease: a rapid and validated method","volume":"14","author":"Mor\u00e1n","year":"2023","journal-title":"Front. Plant Sci."},{"key":"B22","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1094\/phyto-08-21-0354-fi","article-title":"Candidatus Liberibacter: From movement, host responses, to symptom development of citrus Huanglongbing","volume":"112","author":"Pandey","year":"2022","journal-title":"Phytopathology\u00ae"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1127\/entomologia\/2024\/2877","article-title":"Global strategies to manage huanglongbing (HLB) and its vectors: insights and implications for the Mediterranean region","volume":"45","author":"P\u00e9rez-Hedo","year":"2025","journal-title":"Entomol. Gen."},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.3733\/ucanr.8218","article-title":"Citrus bacterial canker disease and Huanglongbing (citrus greening)","author":"Polek","year":"2007"},{"key":"B25","first-page":"78","article-title":"MobileNetV4: Universal models for the mobile ecosystem","author":"Qin","year":"2024"},{"key":"B26","first-page":"618","article-title":"Grad-CAM: Visual explanations from deep networks via gradient-based localization","author":"Selvaraju","year":"2017"},{"key":"B27","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","author":"Tan","year":"2019"},{"key":"B28","first-page":"10096","article-title":"Efficientnetv2: Smaller models and faster training","author":"Tan","year":"2021"},{"key":"B29","article-title":"Yolov12: Attention-centric real-time object detectors","author":"Tian","year":"2025","journal-title":"arXiv Preprint arXiv:2502.12524"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2021.e08387","article-title":"Identification of citrus greening based on visual symptoms: A grower's diagnostic toolkit","volume":"7","author":"Tipu","year":"2021","journal-title":"Heliyon"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.34133\/2019\/9237136","article-title":"How convolutional neural networks diagnose plant disease","volume":"2019","author":"Toda","year":"2019","journal-title":"Plant Phenomics"},{"key":"B32","doi-asserted-by":"publisher","first-page":"607","DOI":"10.1016\/j.molp.2019.03.008","article-title":"The citrus huanglongbing crisis and potential solutions","volume":"12","author":"Wang","year":"2019","journal-title":"Mol. Plant"},{"key":"B33","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1094\/php-2010-1003-01-rv","article-title":"A review of huanglongbing (citrus greening) management in citrus using nutritional approaches in China","volume":"12","author":"Xia","year":"2011","journal-title":"Plant Health Prog."}],"container-title":["Frontiers in Plant Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1853541\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T05:31:06Z","timestamp":1789536666000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1853541\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,16]]},"references-count":33,"alternative-id":["10.3389\/fpls.2026.1853541"],"URL":"https:\/\/doi.org\/10.3389\/fpls.2026.1853541","relation":{},"ISSN":["1664-462X"],"issn-type":[{"value":"1664-462X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,16]]},"article-number":"1853541"}}