{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,3]],"date-time":"2026-11-03T20:26:36Z","timestamp":1793737596838,"version":"4.6.1"},"reference-count":25,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T00:00:00Z","timestamp":1777334400000},"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:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Early detection of plant diseases is essential for maintaining crop health and ensuring sustainable agricultural productivity. Guava fruit and leaf diseases, if not identified at an early stage, can lead to significant yield losses. Recent advances in deep learning offer promising solutions; however, challenges remain in achieving both high accuracy and model interpretability for practical agricultural deployment.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This study proposes an explainable deep learning\u2013based framework for the classification of guava fruit and leaf diseases. A real-world dataset consisting of 527 annotated images across five classes\u2014Disease Free, Phytophthora, Red Rust, Scab, and Styler and Root Rot\u2014was utilized. Six hybrid model architectures were developed by integrating transfer learning backbones (VGG16, MobileNetV2, InceptionV3, and ResNet50) with custom convolutional neural network (CNN) classifiers. Model performance was evaluated using accuracy, precision, recall, F1-score, and class-wise metrics. To enhance transparency, Gradient-weighted Class Activation Mapping (Grad-CAM) was employed to visualize disease-relevant regions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Among all evaluated models, the proposed VGG16 + MobileNetV2 hybrid architecture achieved the best performance, attaining an accuracy of 96%, an F1-score of 0.96, and strong generalization across all disease classes. Comparative analyses using confusion matrices, ROC-AUC curves, precision\u2013recall curves, and radar plots confirmed the superior and consistent performance of the proposed model over other hybrid configurations.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>The results demonstrate that combining deep feature extractors with lightweight architectures enhances both classification accuracy and computational efficiency. The integration of Grad-CAM provides meaningful visual explanations, increasing trust and interpretability in AI-assisted disease diagnosis. This framework shows strong potential for deployment in real-time smart farming systems and mobile-based diagnostic applications, particularly in resource-constrained agricultural environments.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fpls.2026.1738585","type":"journal-article","created":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T05:35:39Z","timestamp":1777354539000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Explainable deep learning-based comparative study for guava fruit and leaf disease classification: advancing agricultural diagnostics through AI"],"prefix":"10.3389","volume":"17","author":[{"given":"Zeyu","family":"Zhou","sequence":"first","affiliation":[{"name":"School of Economics, Shandong Normal University","place":["Jinan, Shandong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,4,28]]},"reference":[{"key":"B1","volume-title":"Guava Dataset [Data set]","author":"Abdulazeem","year":"2023"},{"key":"B2","doi-asserted-by":"publisher","first-page":"31103","DOI":"10.1109\/access.2022.3159678","article-title":"End-to-end deep learning model for corn leaf disease classification","volume":"10","author":"Amin","year":"2022","journal-title":"IEEE Access"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-024-06134-x","article-title":"Prediction of bank credit worthiness through credit risk analysis: an explainable machine learning study","author":"Chang","year":"2024","journal-title":"Ann. Operations Res"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.3390\/agronomy15040944","article-title":"YOLOv8-RBean: runner bean leaf disease detection model based on YOLOv8","volume":"15","author":"Chen","year":"2025","journal-title":"Agronomy"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1016\/j.atech.2023.100350","article-title":"Integrating explainable artificial intelligence and blockchain to smart agriculture: Research prospects for decision making and improved security","volume":"6","author":"Chen","year":"2023","journal-title":"Smart Agric. Technol."},{"key":"B6","volume-title":"Explainable AI meets healthcare: A study on heart disease dataset","author":"Dave","year":"2020"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1111\/ppa.14006","article-title":"Image-based crop disease detection using machine learning","author":"Dolatabadian","year":"2024","journal-title":"Plant Pathology."},{"key":"B8","doi-asserted-by":"publisher","first-page":"356","DOI":"10.37394\/23209.2023.20.38","article-title":"Classification of guava leaf disease using deep learning","volume":"20","author":"Doutoum","year":"2023","journal-title":"WSEAS Trans. Inf. Sci. Appl."},{"key":"B9","doi-asserted-by":"publisher","first-page":"92","DOI":"10.53430\/ijsru.2024.7.1.0030","article-title":"Theoretical frameworks in AI for credit risk assessment: Towards banking efficiency and accuracy","volume":"7","author":"Edunjobi","year":"2024","journal-title":"Int. J. Sci. Res. Updates"},{"key":"B10","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1186\/s40066-015-0031-7","article-title":"Food in a future of 10 billion","volume":"4","author":"Fedoroff","year":"2015","journal-title":"Agric. Food Secur."},{"key":"B11","doi-asserted-by":"publisher","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":"B12","doi-asserted-by":"publisher","DOI":"10.3390\/app12010239","article-title":"Guava disease detection using deep convolutional neural networks: A case study of guava plants","volume":"12","author":"Mostafa","year":"2022","journal-title":"Appl. Sci."},{"key":"B13","doi-asserted-by":"publisher","first-page":"542","DOI":"10.1016\/j.csbj.2024.08.005","article-title":"Unveiling the black box: A systematic review of Explainable Artificial Intelligence in medical image analysis [Review of Unveiling the black box: A systematic review of Explainable Artificial Intelligence in medical image analysis","volume":"24","author":"Muhammad","year":"2024","journal-title":"Comput. Struct. Biotechnol. J."},{"key":"B14","first-page":"1","article-title":"Device-friendly guava fruit and leaf disease detection using deep learning","author":"Nandi","year":"2022","journal-title":"Proc. MIET 2022."},{"key":"B15","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/j.inpa.2020.04.004","article-title":"Recent advances in image processing techniques for automated leaf pest and disease recognition \u2013 A review [Review of Recent advances in image processing techniques for automated leaf pest and disease recognition \u2013 A review","volume":"8","author":"Ngugi","year":"2020","journal-title":"Inf. Process. Agric."},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4637897","article-title":"Explainable Artificial Intelligence (XAI) in healthcare: Interpretab le Models for Clinical Decision Support","author":"Rane","year":"2023","journal-title":"SSRN Electronic J"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.3390\/plants9101319","article-title":"Plant disease classification: A comparative evaluation of convolutional neural networks and deep learning optimizers","volume":"9","author":"Saleem","year":"2020","journal-title":"Plants"},{"key":"B18","first-page":"5","article-title":"Towards explainable artificial intelligence","volume-title":"Lecture notes in computer science","author":"Samek","year":"2019"},{"key":"B19","volume-title":"Explainable artificial intelligence: understanding, visualizing and interpreting deep learning models","author":"Samek","year":"2017"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2025.1538163","article-title":"Leveraging deep learning for plant disease and pest detection: a comprehensive review and future directions [Review of Leveraging deep learning for plant disease and pest detection: a comprehensive review and future directions","volume":"16","author":"Shoaib","year":"2025","journal-title":"Front. Plant Sci."},{"key":"B21","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1186\/s12870-025-06679-4","article-title":"Potato plant disease detection: leveraging hybrid deep learning models","volume":"25","author":"Sinamenye","year":"2025","journal-title":"BMC Plant Biol."},{"key":"B22","doi-asserted-by":"crossref","DOI":"10.3390\/jimaging6060052","article-title":"Explainable deep learning models in medical image analysis","volume-title":"Explainable Deep Learning Models in Medical Image Analysis","author":"Singh","year":"2020"},{"key":"B23","doi-asserted-by":"publisher","first-page":"9973","DOI":"10.1007\/s11042-023-15386","article-title":"Automatic guava disease detection using different deep learning approaches","volume":"83","author":"Tewari","year":"2024","journal-title":"Multimedia Tools Appl."},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1155\/2017\/2917536","article-title":"Automatic image-based plant disease severity estimation using deep learning","volume":"2017","author":"Wang","year":"2017","journal-title":"Comput. Intell. Neurosci."},{"key":"B25","doi-asserted-by":"publisher","first-page":"2159","DOI":"10.1007\/s12525-022-00608-1","article-title":"Designing a feature selection method based on explainable artificial intelligence","volume":"32","author":"Zacharias","year":"2022","journal-title":"Electronic Markets"}],"container-title":["Frontiers in Plant Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1738585\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T05:35:40Z","timestamp":1777354540000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1738585\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,28]]},"references-count":25,"alternative-id":["10.3389\/fpls.2026.1738585"],"URL":"https:\/\/doi.org\/10.3389\/fpls.2026.1738585","relation":{},"ISSN":["1664-462X"],"issn-type":[{"value":"1664-462X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,28]]},"article-number":"1738585"}}