{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T02:46:17Z","timestamp":1769913977917,"version":"3.49.0"},"reference-count":44,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T00:00:00Z","timestamp":1763337600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computers"],"abstract":"<jats:p>Early detection of plant diseases is key to ensuring food production, reducing economic losses, minimizing the use of agrochemicals, and maintaining the sustainability of the agricultural sector. Citrus plants, an important source of vitamin C, fiber, and antioxidants, are among the world\u2019s most significant fruit crops but face threats such as canker and Huanglongbing (HLB), incurable diseases that require management strategies to mitigate their impact. Manual diagnosis, although common, I s imprecise, slow, and costly; therefore, efficient alternatives are emerging to identify diseases from early stages using Artificial Intelligence techniques. This study evaluated four deep learning models, specifically convolutional neural networks. In this study, we evaluated four convolutional neural network models (DenseNet121, ResNet50, EfficientNetB0, and MobileNetV2) to detect canker and HLB in citrus leaf images. We applied preprocessing and data-augmentation techniques; transfer learning via selective fine-tuning; stratified k-fold cross-validation; regularization methods such as dropout and weight decay; and hyperparameter-optimization techniques. The models were evaluated by the loss value and by metrics derived from the confusion matrix, including accuracy, recall, and F1-score. The best-performing model was EfficientNetB0, which achieved an average accuracy of 99.88% and the lowest loss value of 0.0058 using cross-entropy as the loss function. Since EfficientNetB0 is a lightweight model, the results show that lightweight models can achieve favorable performance compared to robust models, models that can be useful for disease detection in the agricultural sector using portable devices or drones for field monitoring. The high accuracy obtained is mainly because only two diseases were considered; consequently, it is possible that these results do not hold in a database that includes a larger number of diseases.<\/jats:p>","DOI":"10.3390\/computers14110500","type":"journal-article","created":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T08:50:07Z","timestamp":1763542207000},"page":"500","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Deep Learning-Based Citrus Canker and Huanglongbing Disease Detection Using Leaf Images"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-7738-7130","authenticated-orcid":false,"given":"Maryjose","family":"Devora-Guadarrama","sequence":"first","affiliation":[{"name":"Escuela Superior de C\u00f3mputo, Instituto Polit\u00e9cnico Nacional, M\u00e9xico City 07738, Mexico"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3519-6328","authenticated-orcid":false,"given":"Benjam\u00edn","family":"Luna-Benoso","sequence":"additional","affiliation":[{"name":"Escuela Superior de C\u00f3mputo, Instituto Polit\u00e9cnico Nacional, M\u00e9xico City 07738, Mexico"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9785-1252","authenticated-orcid":false,"given":"Antonio","family":"Alarc\u00f3n-Paredes","sequence":"additional","affiliation":[{"name":"Centro de Investigaci\u00f3n en Computaci\u00f3n, Instituto Polit\u00e9cnico Nacional, M\u00e9xico City 07738, Mexico"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9421-5923","authenticated-orcid":false,"given":"Jose Cruz","family":"Mart\u00ednez-Perales","sequence":"additional","affiliation":[{"name":"Escuela Superior de C\u00f3mputo, Instituto Polit\u00e9cnico Nacional, M\u00e9xico City 07738, Mexico"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9265-4228","authenticated-orcid":false,"given":"\u00darsula Samantha","family":"Morales-Rodr\u00edguez","sequence":"additional","affiliation":[{"name":"Escuela Superior de C\u00f3mputo, Instituto Polit\u00e9cnico Nacional, M\u00e9xico City 07738, Mexico"}]}],"member":"1968","published-online":{"date-parts":[[2025,11,17]]},"reference":[{"key":"ref_1","first-page":"100258","article-title":"Enhancing agricultural sustainability: Optimizing crop planting structures and spatial layouts within the water-land-energy-economy-environment-food nexus","volume":"6","author":"Wu","year":"2025","journal-title":"Geogr. Sustain."},{"key":"ref_2","first-page":"102139","article-title":"The biological activities of Citrus species in crop protection","volume":"22","author":"Iobbi","year":"2025","journal-title":"J. Agric. Food Res."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Kato-Noguchi, H., and Kato, M. (2025). Pesticidal Activity of Citrus Fruits for the Development of Sustainable Fruit-Processing Waste Management and Agricultural Production. Plants, 14.","DOI":"10.3390\/plants14050754"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"2036","DOI":"10.1016\/j.patrec.2011.08.003","article-title":"Automatic citrus canker detection from leaf images captured in field","volume":"32","author":"Zhang","year":"2011","journal-title":"Pattern Recognit. Lett."},{"key":"ref_5","first-page":"49","article-title":"Identification of Citrus Canker on Citrus Leaves and Fruit Surfaces in the Grove Using Deep Learning Neural Networks","volume":"10","author":"Matshwene","year":"2020","journal-title":"J. Agric. Sci. Technol."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Deng, X., Zhu, Z., Yang, J., Zheng, Z., Xianbo, H., Shujin Wei, Y., and Lan, Y. (2020). Detection of Citrus Huanglongbing Based on Multi-Input Neural Network Model of UAV Hyperspectral Remote Sensing. Remote Sens., 12.","DOI":"10.3390\/rs12172678"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"825","DOI":"10.1016\/j.compag.2019.05.032","article-title":"Detection of Huanglongbing disease based on intensity-invariant texture analysis of images in the visible spectrum","volume":"162","year":"2019","journal-title":"Comput. Electron. Agric."},{"key":"ref_8","first-page":"127","article-title":"Cross-comparative review of Machine learning for plant disease detection: Apple, cassava, cotton and potato plants","volume":"12","author":"Omaye","year":"2024","journal-title":"Artif. Intell. Agric."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1016\/j.gltp.2022.03.016","article-title":"Plant leaf disease detection using computer vision and machine learning algorithms","volume":"3","author":"Harakannanavar","year":"2022","journal-title":"Glob. Transit. Proc."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1435","DOI":"10.1016\/j.procs.2025.04.376","article-title":"A Deep Learning Framework for Early Detection and Diagnosis of Plant Diseases","volume":"258","author":"Vinay","year":"2025","journal-title":"Procedia Comput. Sci."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Andrew, J., Eunice, J., Elena Popescu, D., Kalpana Chowdary, M., and Hemanth, J. (2022). Deep Learning-Based Leaf Disease Detection in Crops Using Images for Agricultural Applications. Agronomy, 12.","DOI":"10.3390\/agronomy12102395"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Konstantinos, D., Dimitrios, T., Dimitrios, T., Lykourgos, M., Lazaros, I., and Panayotis, K. (2021). Pandemic Analytics by Advanced Machine Learning for Improved Decision Making of COVID-19 Crisis. Processes, 9.","DOI":"10.3390\/pr9081267"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Ching-Nam, H., Yi-Zhen, T., Pei-Duo, Y., Jiasi, C., and Chee-Wei, T. (2023). Privacy-Enhancing Digital Contact Tracing with Machine Learning for Pandemic Response: A Comprehensive Review. Big Data Cogn. Comput., 7.","DOI":"10.3390\/bdcc7020108"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"220","DOI":"10.1016\/j.compag.2018.04.023","article-title":"Detection and classification of citrus diseases in agriculture based on optimized weighted segmentation and feature selection","volume":"150","author":"Sharif","year":"2018","journal-title":"Comput. Electron. Agric."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"400","DOI":"10.1364\/AO.55.000400","article-title":"Detection of citrus canker and Huanglongbing using fluorescence imaging spectroscopy and support vector machine technique","volume":"55","author":"Wetterich","year":"2016","journal-title":"Appl. Opt."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Abdulridha, J., Batuman, O., and Ampatzidis, Y. (2019). UAV-Based Remote Sensing Technique to Detect Citrus Canker Disease Utilizing Hyperspectral Imaging and Machine Learning. Remote Sens., 11.","DOI":"10.3390\/rs11111373"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1016\/j.jfoodeng.2009.01.014","article-title":"Detection of citrus canker using hyperspectral reflectance imaging with spectral information divergence","volume":"93","author":"Qin","year":"2009","journal-title":"J. Food Eng."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Narayanan, K.B., Krishna Sai, D., Akhil Chowdary, K., and Reddy, S. (2024). Applied Deep Learning approaches on canker effected leaves to enhance the detection of the disease using Image Embedding and Machine Learning Techniques. EAI Endorsed Trans. Internet Things, 10.","DOI":"10.4108\/eetiot.5346"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"110549","DOI":"10.1016\/j.compag.2025.110549","article-title":"Multiple light sources excited fluorescence image-based non-destructive method for citrus Huanglongbing disease detection","volume":"237","author":"Yan","year":"2025","journal-title":"Comput. Electron. Agric."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"107008","DOI":"10.1016\/j.cropro.2024.107008","article-title":"Citrus huanglongbing detection: A hyperspectral data-driven model integrating feature band selection with machine learning algorithms","volume":"188","author":"Yan","year":"2025","journal-title":"Crop Prot."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"015701","DOI":"10.1088\/1612-202X\/ad1097","article-title":"Early diagnosis of citrus Huanglongbing by Raman spectroscopy and machine learning","volume":"21","author":"Kong","year":"2024","journal-title":"Laser Phys. Lett."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"190","DOI":"10.1080\/15502724.2022.2077753","article-title":"Predicting Window View Preferences Using the Environmental Information Criteria","volume":"19","author":"Kent","year":"2022","journal-title":"LEUKOS"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Goyal, A., and Lakhwani, K. (2025). Integrating advanced deep learning techniques for enhanced detection and classification of citrus leaf and fruit diseases. Sci. Rep., 15.","DOI":"10.1038\/s41598-025-97159-0"},{"key":"ref_24","first-page":"895","article-title":"Deep Transfer Learning Based Detection and Classification of Citrus Plant Diseases","volume":"76","author":"Faisal","year":"2023","journal-title":"Comput. Mater. Contin."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"107181","DOI":"10.1016\/j.cropro.2025.107181","article-title":"Multi-component image analysis for citrus disease detection using convolutional neural networks","volume":"193","author":"Sharma","year":"2025","journal-title":"Crop Prot."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Butt, N., Munwar Iqbal, M., Ramzan, S., Raza, A., Abualigah, L., Latif Fitriyani, M., Gu, Y., and Syafrudin, M. (2025). Citrus diseases detection using innovative deep learning approach and Hybrid Meta-Heuristic. PLoS ONE, 20.","DOI":"10.1371\/journal.pone.0316081"},{"key":"ref_27","doi-asserted-by":"crossref","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":"Prasad","year":"2022","journal-title":"Appl. Intell."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1016\/j.biosystemseng.2022.09.006","article-title":"Automated identification of citrus diseases in orchards using deep learning","volume":"223","author":"Zhang","year":"2022","journal-title":"Biosyst. Eng."},{"key":"ref_29","first-page":"103355","article-title":"Duck optimization with enhanced capsule network based citrus disease detection for sustainable crop management","volume":"58","author":"Arthi","year":"2023","journal-title":"Sustain. Energy Technol. Assess."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Dhiman, P., Kaur, A., Hamid, Y., Alabdulkreem, E., Elmannai, H., and Ababneh, N. (2023). Smart Disease Detection System for Citrus Fruits Using Deep Learning with Edge Computing. Sustainability, 15.","DOI":"10.3390\/su15054576"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"100247","DOI":"10.1016\/j.health.2023.100247","article-title":"The stratified K-folds cross-validation and class-balancing methods with high-performance ensemble classifiers for breast cancer classification","volume":"4","author":"Mahesh","year":"2023","journal-title":"Healthc. Anal."},{"key":"ref_32","unstructured":"Dtrilsbeek (2025, October 30). Citrus Leaves Prepared; [Dataset]. Kaggle. Available online: https:\/\/www.kaggle.com\/datasets\/dtrilsbeek\/citrus-leaves-prepared."},{"key":"ref_33","unstructured":"Kaku321 (2025, October 30). Citrus Plant Disease; [Dataset]. Kaggle. Available online: https:\/\/www.kaggle.com\/datasets\/kaku321\/citrus-plant-disease."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"110886","DOI":"10.1016\/j.compag.2025.110886","article-title":"Implementing transfer learning for citrus Huanglongbing disease detection across different datasets using neural network","volume":"238","author":"Huang","year":"2025","journal-title":"Comput. Electron. Agric."},{"key":"ref_35","first-page":"132722","article-title":"Surge phenomenon in optimal learning rate and batch size scaling","volume":"Volume 37","author":"Li","year":"2025","journal-title":"Proceedings of the 38th International Conference on Neural Information Processing Systems (NIPS \u201824)"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"111244","DOI":"10.1016\/j.dib.2024.111244","article-title":"A comprehensive image dataset for the identification of lemon leaf diseases and computer vision applications","volume":"58","author":"Bishshash","year":"2025","journal-title":"Data Brief"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"108907","DOI":"10.1016\/j.compag.2024.108907","article-title":"Hybrid attention network for citrus disease identification","volume":"220","author":"Zhang","year":"2024","journal-title":"Comput. Electron. Agric."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"200199","DOI":"10.1016\/j.sasc.2025.200199","article-title":"Citrus diseases detection and classification based on efficientnet-B5","volume":"7","author":"Zambuk","year":"2025","journal-title":"Syst. Soft Comput."},{"key":"ref_39","doi-asserted-by":"crossref","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":"ref_40","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1016\/j.jfoodeng.2011.07.022","article-title":"Development of a two-band spectral imaging system for real-time citrus canker detection","volume":"108","author":"Qin","year":"2012","journal-title":"J. Food Eng."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"111071","DOI":"10.1016\/j.engappai.2025.111071","article-title":"A novel method for predicting plant leaf disease based on machine learning and deep learning techniques","volume":"155","author":"Dinesh","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"105202","DOI":"10.1016\/j.chemolab.2024.105202","article-title":"A 1D-CNN model for the early detection of citrus Huanglongbing disease in the sieve plate of phloem tissue using micro-FTIR","volume":"252","author":"Yang","year":"2024","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Cao, L., Xiao, W., Hu, Z., Li, X., and Wu, Z. (2025). Detection of Citrus Huanglongbing in Natural Field Conditions Using an Enhanced YOLO11 Framework. Mathematics, 13.","DOI":"10.3390\/math13142223"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Qiu, R.-Z., Chen, S.-P., Chi, M.-X., Wang, R.-B., Huang, T., Fan, G.-C., Zhao, J., and Weng, Q.-Y. (2022). An automatic identification system for citrus greening disease (Huanglongbing) using a YOLO convolutional neural network. Front. Plant Sci., 13.","DOI":"10.3389\/fpls.2022.1002606"}],"container-title":["Computers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-431X\/14\/11\/500\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T09:08:00Z","timestamp":1763543280000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-431X\/14\/11\/500"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,17]]},"references-count":44,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["computers14110500"],"URL":"https:\/\/doi.org\/10.3390\/computers14110500","relation":{},"ISSN":["2073-431X"],"issn-type":[{"value":"2073-431X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,17]]}}}