{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T18:05:46Z","timestamp":1779473146076,"version":"3.53.1"},"reference-count":62,"publisher":"Public Library of Science (PLoS)","issue":"5","license":[{"start":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T00:00:00Z","timestamp":1779408000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Ensuring global food security depends on timely and reliable plant disease identification. Traditional disease detection methods often prove inefficient because of the lack of necessary precision. Furthermore, public datasets typically suffer from the class imbalance issue, which can obstruct reliable model testing and lead to biased performance evaluations. This paper introduces LeafDet, an object detection model based on the YOLOv8 architecture, specifically designed for the effective detection of tomato leaf diseases. Moreover, a revised, balanced dataset, named PlantTom, is developed by combining images from various public sources to reduce the existing dataset limitations. PlantTom has 7836 images with 8 distinct classes, each representing a tomato leaf disease. The proposed LeafDet model includes CBM, C2f, SPPF, and ECA attention modules in the backbone section; BiFPN, GSConv, VoVGSCSP, and Shuffle Attention in the neck section. Efficient attention methods like ECA and Shuffle Attention are used to improve both accuracy and speed. LeafDet model achieves 91.6% mAP@0.5 on the PlantTom dataset, which is a 2.2% improvement over the original YOLOv8n with 2.69M parameters and an inference time of 2.4ms. The proposed model also outperforms several other state-of-the-art object detection models, including the latest YOLOv11n and YOLOv12n. Ablation studies show that each part of the model helps to improve its performance, and the PIoUv2 loss function is found to be the optimal choice for this use. The model predictions are then validated using Eigen-CAM, which provides a visualization of the decision-making process. These results demonstrate that LeafDet provides a deployable and interpretable framework for plant disease detection in smart agriculture.<\/jats:p>","DOI":"10.1371\/journal.pone.0349501","type":"journal-article","created":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T17:27:20Z","timestamp":1779470840000},"page":"e0349501","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["LeafDet: A lightweight and interpretable deep learning framework for tomato leaf disease detection"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-8987-3447","authenticated-orcid":true,"given":"Vaskor","family":"Mostafa","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3962-8182","authenticated-orcid":true,"given":"Md. Shafak Shahriar","family":"Sozol","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8582-9197","authenticated-orcid":true,"given":"M. Rubaiyat Hossain","family":"Mondal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,5,22]]},"reference":[{"issue":"8","key":"pone.0349501.ref001","doi-asserted-by":"crossref","first-page":"635","DOI":"10.1038\/s41558-021-01124-4","article-title":"Pathogens, precipitation and produce prices","volume":"11","year":"2021","journal-title":"Nat Clim Change"},{"key":"pone.0349501.ref002","unstructured":"FAO. AI can be a game-changing solution for farmers \u2013 FAO innovation chief. Accessed 2025 July 29. https:\/\/www.fao.org\/newsroom\/detail\/ai-can-be-a-game-changing-solution-for-farmers--fao-innovation-chief\/en"},{"issue":"1","key":"pone.0349501.ref003","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1186\/s12870-025-06247-w","article-title":"Efficient deep learning-based tomato leaf disease detection through global and local feature fusion","volume":"25","author":"H Sun","year":"2025","journal-title":"BMC Plant Biol"},{"key":"pone.0349501.ref004","doi-asserted-by":"crossref","first-page":"123595","DOI":"10.1109\/ACCESS.2024.3453379","article-title":"YOLOv8-ACCW: lightweight grape leaf disease detection method based on improved YOLOv8","volume":"12","author":"Z Chen","year":"2024","journal-title":"IEEE Access"},{"issue":"6","key":"pone.0349501.ref005","doi-asserted-by":"crossref","DOI":"10.3390\/sym16060723","article-title":"Multifactorial tomato leaf disease detection based on improved YOLOV5","volume":"16","author":"G Wang","year":"2024","journal-title":"Symmetry"},{"key":"pone.0349501.ref006","article-title":"Mish: a self regularized non-monotonic activation function","author":"D Misra","year":"2019","journal-title":"arXiv preprint"},{"key":"pone.0349501.ref007","unstructured":"Jocher G, Chaurasia A, Qiu J. Ultralytics YOLOv8. 2023. https:\/\/github.com\/ultralytics\/ultralytics"},{"key":"pone.0349501.ref008","article-title":"ECA-Net: efficient channel attention for deep convolutional neural networks.","author":"Q Wang","year":"2020","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"pone.0349501.ref009","doi-asserted-by":"crossref","first-page":"10778","DOI":"10.1109\/CVPR42600.2020.01079","article-title":"EfficientDet: Scalable and Efficient Object Detection","author":"M Tan","year":"2020","journal-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"},{"issue":"3","key":"pone.0349501.ref010","article-title":"Slim-neck by GSConv: a lightweight-design for real-time detector architectures","volume":"21","author":"H Li","year":"2024","journal-title":"J Real-Time Image Proc"},{"key":"pone.0349501.ref011","article-title":"SA-Net: shuffle attention for deep convolutional neural networks.","author":"Y Zhang","year":"2021","journal-title":"Proc. ICASSP"},{"key":"pone.0349501.ref012","first-page":"1","article-title":"Eigen-CAM: class activation map using principal components","author":"MB Muhammad","year":"2020","journal-title":"2020 International Joint Conference on Neural Networks (IJCNN)"},{"issue":"8","key":"pone.0349501.ref013","doi-asserted-by":"crossref","first-page":"833","DOI":"10.3390\/agriculture15080833","article-title":"CEFW-YOLO: a high-precision model for plant leaf disease detection in natural environments","volume":"15","author":"J Tao","year":"2025","journal-title":"Agriculture"},{"key":"pone.0349501.ref014","doi-asserted-by":"crossref","first-page":"1473928","DOI":"10.3389\/fpls.2024.1473928","article-title":"DM-YOLO: improved YOLOv9 model for tomato leaf disease detection","volume":"15","author":"A Abulizi","year":"2025","journal-title":"Front Plant Sci"},{"key":"pone.0349501.ref015","doi-asserted-by":"crossref","DOI":"10.3389\/fpls.2024.1514832","article-title":"SerpensGate-YOLOv8: an enhanced YOLOv8 model for accurate plant disease detection","volume":"15","author":"Y Miao","year":"2025","journal-title":"Front Plant Sci"},{"issue":"2","key":"pone.0349501.ref016","doi-asserted-by":"crossref","first-page":"563","DOI":"10.1109\/TAFE.2024.3445119","article-title":"Lightweight tomato leaf intelligent disease detection model based on adaptive kernel convolution and feature fusion","volume":"2","author":"B Ji","year":"2024","journal-title":"IEEE Transac Agri Food Electron"},{"key":"pone.0349501.ref017","author":"DP Hughes","year":"2015"},{"key":"pone.0349501.ref018","doi-asserted-by":"crossref","first-page":"1452502","DOI":"10.3389\/fpls.2024.1452502","article-title":"Precision agriculture with YOLO-Leaf: advanced methods for detecting apple leaf diseases","volume":"15","author":"T Li","year":"2024","journal-title":"Front Plant Sci"},{"issue":"9","key":"pone.0349501.ref019","doi-asserted-by":"crossref","DOI":"10.1002\/aps3.11390","article-title":"The plant pathology challenge 2020 data set to classify foliar disease of apples","volume":"8","author":"R Thapa","year":"2020","journal-title":"Appl Plant Sci"},{"issue":"5","key":"pone.0349501.ref020","doi-asserted-by":"crossref","first-page":"116","DOI":"10.3390\/computers13050116","article-title":"A hybrid deep learning architecture for apple foliar disease detection","volume":"13","author":"A Ait Nasser","year":"2024","journal-title":"Computers"},{"key":"pone.0349501.ref021","article-title":"Tomato leaf disease detection based on attention mechanism and multi-scale feature fusion","volume":"15","author":"Y Wang","year":"2024","journal-title":"Front Plant Sci"},{"key":"pone.0349501.ref022","doi-asserted-by":"crossref","first-page":"49167","DOI":"10.1109\/ACCESS.2024.3383154","article-title":"Precision agriculture through deep learning: tomato plant multiple diseases recognition with CNN and improved YOLOv7","volume":"12","author":"M Umar","year":"2024","journal-title":"IEEE Access"},{"issue":"2","key":"pone.0349501.ref023","doi-asserted-by":"crossref","first-page":"265","DOI":"10.62051\/ijcsit.v3n2.30","article-title":"Tomato leaf disease identification based on Yolov8","volume":"3","author":"Y Zhong","year":"2024","journal-title":"IJCSIT"},{"key":"pone.0349501.ref024","doi-asserted-by":"crossref","first-page":"1323301","DOI":"10.3389\/fpls.2023.1323301","article-title":"YOLOV5-CBAM-C3TR: an optimized model based on transformer module and attention mechanism for apple leaf disease detection","volume":"14","author":"M Lv","year":"2024","journal-title":"Front Plant Sci"},{"key":"pone.0349501.ref025","unstructured":"Plant disease dataset. Baidu AI Studio. Accessed 2025 July 19. https:\/\/aistudio.baidu.com\/datasetdetail\/11591"},{"issue":"1","key":"pone.0349501.ref026","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1186\/s13007-024-01188-1","article-title":"An efficient deep learning model for tomato disease detection","volume":"20","author":"X Wang","year":"2024","journal-title":"Plant Methods"},{"key":"pone.0349501.ref027","article-title":"Bangladeshi crops leaf disease detection using YOLOv8","volume":"10","author":"MSZ Abid","year":"2024","journal-title":"Heliyon"},{"key":"pone.0349501.ref028","doi-asserted-by":"crossref","first-page":"139872","DOI":"10.1109\/ACCESS.2023.3340148","article-title":"Citrus diseases and pests detection model based on self-attention YOLOV8","volume":"11","author":"D Luo","year":"2023","journal-title":"IEEE Access"},{"issue":"7","key":"pone.0349501.ref029","doi-asserted-by":"crossref","DOI":"10.3390\/agronomy13071824","article-title":"A lightweight YOLOv8 tomato detection algorithm combining feature enhancement and attention","volume":"13","author":"G Yang","year":"2023","journal-title":"Agronomy"},{"key":"pone.0349501.ref030","doi-asserted-by":"crossref","first-page":"1289464","DOI":"10.3389\/fpls.2023.1289464","article-title":"Tomato brown rot disease detection using improved YOLOv5 with attention mechanism","volume":"14","author":"J Liu","year":"2023","journal-title":"Front Plant Sci"},{"key":"pone.0349501.ref031","doi-asserted-by":"crossref","first-page":"107605","DOI":"10.1016\/j.compag.2022.107605","article-title":"Identification of tomato leaf diseases based on multi-channel automatic orientation recurrent attention network","volume":"205","author":"Y Zhang","year":"2023","journal-title":"Comp Electron Agricul"},{"key":"pone.0349501.ref032","doi-asserted-by":"crossref","first-page":"54080","DOI":"10.1109\/ACCESS.2023.3282309","article-title":"An improved lightweight YOLOv5 algorithm for detecting strawberry diseases","volume":"11","author":"S Chen","year":"2023","journal-title":"IEEE Access"},{"key":"pone.0349501.ref033","doi-asserted-by":"crossref","first-page":"1120724","DOI":"10.3389\/fpls.2023.1120724","article-title":"EADD-YOLO: an efficient and accurate disease detector for apple leaf using improved lightweight YOLOv5","volume":"14","author":"S Zhu","year":"2023","journal-title":"Front Plant Sci"},{"key":"pone.0349501.ref034","article-title":"PlantDoc: a dataset for visual plant disease detection","author":"D Singh","year":"2019","journal-title":"arXiv"},{"key":"pone.0349501.ref035","unstructured":"Pratikkayal P. GitHub - pratikkayal\/PlantDoc-Dataset: Dataset used in \u201cPlantDoc: A Dataset for Visual Plant Disease Detection\u201d accepted in CODS-COMAD 2020. Accessed 2023 October 1. https:\/\/github.com\/pratikkayal\/PlantDoc-Dataset"},{"key":"pone.0349501.ref036","article-title":"An open access repository of images on plant health to enable the development of mobile disease diagnostics","author":"DP Hughes","year":"2015","journal-title":"arXiv preprint"},{"key":"pone.0349501.ref037","unstructured":"spMohanty. GitHub - spMohanty\/PlantVillage-Dataset: Dataset of diseased plant leaf images and corresponding labels. Accessed 2023 October 1. https:\/\/github.com\/spMohanty\/PlantVillage-Dataset"},{"key":"pone.0349501.ref038","unstructured":"Bryan. Tomato leaf disease dataset. Roboflow universe. 2023. https:\/\/universe.roboflow.com\/bryan-b56jm\/tomato-leaf-disease-ssoha"},{"key":"pone.0349501.ref039","doi-asserted-by":"crossref","first-page":"35398","DOI":"10.1109\/ACCESS.2023.3263042","article-title":"FieldPlant: a dataset of field plant images for plant disease detection and classification with deep learning","volume":"11","author":"E Moupojou","year":"2023","journal-title":"IEEE Access"},{"key":"pone.0349501.ref040","unstructured":"Detection PD. FieldPlant Dataset. Roboflow Universe. 2024. https:\/\/universe.roboflow.com\/plant-disease-detection\/fieldplant"},{"key":"pone.0349501.ref041","author":"B Dwyer","year":"2026","journal-title":"Roboflow (Version 1.0)"},{"key":"pone.0349501.ref042","doi-asserted-by":"crossref","first-page":"3897","DOI":"10.1109\/TIP.2021.3065822","article-title":"Regularized densely-connected pyramid network for salient instance segmentation","volume":"30","author":"Y-H Wu","year":"2021","journal-title":"IEEE Trans Image Process"},{"issue":"1","key":"pone.0349501.ref043","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1016\/j.icte.2023.03.009","article-title":"SAR ship detection based on improved YOLOv5 and BiFPN","volume":"10","author":"C Yu","year":"2024","journal-title":"ICT Express"},{"issue":"1","key":"pone.0349501.ref044","doi-asserted-by":"crossref","first-page":"012013","DOI":"10.1088\/1742-6596\/2632\/1\/012013","article-title":"Insulator defect detection method upon fused attention mechanism and bidirectional feature fusion","volume":"2632","author":"Y Chen","year":"2023","journal-title":"J Physics Conf Series"},{"issue":"14","key":"pone.0349501.ref045","doi-asserted-by":"crossref","first-page":"2149","DOI":"10.3390\/ani15142149","article-title":"Enhanced YOLOv8 for robust pig detection and counting in complex agricultural environments","volume":"15","author":"J Li","year":"2025","journal-title":"Animals (Basel)"},{"key":"pone.0349501.ref046","article-title":"Focal loss for dense object detection","author":"TY Lin","year":"2017","journal-title":"arXiv.org"},{"key":"pone.0349501.ref047","article-title":"Faster R-CNN: towards real-time object detection with region proposal networks","author":"S Ren","year":"2015","journal-title":"arXiv.org"},{"key":"pone.0349501.ref048","author":"J Redmon","year":"2018"},{"key":"pone.0349501.ref049","first-page":"1","article-title":"Evolution of YOLO-V5 algorithm for object detection: automated detection of library books and performance validation of dataset","author":"M Karthi","year":"2021","journal-title":"2021 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES)"},{"key":"pone.0349501.ref050","article-title":"YOLOV6: a single-stage object detection framework for industrial applications","author":"C Li","year":"2022","journal-title":"arXiv.org"},{"key":"pone.0349501.ref051","first-page":"1","article-title":"YOLOv8: a novel object detection algorithm with enhanced performance and robustness.","author":"R Varghese","year":"2024","journal-title":"2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems (ADICS)"},{"key":"pone.0349501.ref052","article-title":"YOLOV9: learning what you want to learn using programmable gradient information","author":"C-Y Wang","year":"2024","journal-title":"arXiv.org"},{"key":"pone.0349501.ref053","article-title":"YOLOV10: real-time end-to-end object detection","author":"A Wang","year":"2024","journal-title":"arXiv.org"},{"key":"pone.0349501.ref054","article-title":"YOLOV11: An overview of the key architectural enhancements","author":"R Khanam","year":"2024","journal-title":"arXiv.org"},{"key":"pone.0349501.ref055","article-title":"YOLOV12: attention-centric real-time object detectors","author":"Y Tian","year":"2025","journal-title":"arXiv.org"},{"key":"pone.0349501.ref056","article-title":"Enhancing geometric factors in model learning and inference for object detection and instance segmentation","author":"Z Zheng","year":"2020","journal-title":"arXiv.org"},{"key":"pone.0349501.ref057","author":"Z Zheng","year":"2019"},{"key":"pone.0349501.ref058","article-title":"Focal and efficient IOU loss for accurate bounding box regression","author":"YF Zhang","year":"2021","journal-title":"arXiv.org"},{"key":"pone.0349501.ref059","article-title":"Generalized intersection over union: a metric and a loss for bounding box regression","author":"H Rezatofighi","year":"2019","journal-title":"arXiv.org"},{"key":"pone.0349501.ref060","article-title":"SIOU loss: More powerful learning for bounding box regression","author":"Z Gevorgyan","year":"2022","journal-title":"arXiv.org"},{"key":"pone.0349501.ref061","article-title":"MPDIOU: A loss for efficient and accurate bounding box regression","author":"S Ma","year":"2023","journal-title":"arXiv.org"},{"key":"pone.0349501.ref062","author":"Z Chen","year":"2020"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0349501","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T17:27:29Z","timestamp":1779470849000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0349501"}},"subtitle":[],"editor":[{"given":"Yaseen Ahmed","family":"Al-Mulla","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,5,22]]},"references-count":62,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5,22]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0349501","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,22]]}}}