{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T19:18:08Z","timestamp":1788895088139,"version":"build-2803163510"},"reference-count":46,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,12,15]],"date-time":"2025-12-15T00:00:00Z","timestamp":1765756800000},"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>\n                    Pine wilt disease (PWD), characterized by rapid transmission and high pathogenicity, causes severe ecological and economic damage worldwide. Early detection is critical for curbing its spread, yet the concealed symptoms and minute lesions make it difficult for existing models to balance high accuracy with lightweight efficiency in complex forest environments. To address these challenges, this study proposes a lightweight detection model named LE-PWDNet. A total of 41,568 high-resolution UAV images were collected from diverse field scenarios to construct a standardized dataset covering four infection stages, providing comprehensive support for model training and evaluation. The model is built upon the DEIM training paradigm to enhance the utilization of positive samples for small-target detection. To strengthen multi-scale texture modeling of early lesions, a Wavelet Detail Attention Convolution (WDAConv) is designed. A ConvFFN module is introduced to mitigate the attenuation of high-frequency details, thereby improving robustness under complex backgrounds. A CGAFusion module is developed to reduce false positives caused by background noise. Furthermore, an Edge-Dilated Sampling-Point Generator (DySample-E) is incorporated to dynamically adjust the upsampling process, enhancing the ability to capture early micro-lesions. Experimental results demonstrate that, with only 5.64M parameters and approximately 7 GFLOPs, LE-PWDNet achieves an AP\n                    <jats:sub>50<\/jats:sub>\n                    of 83.8% for early-stage lesion detection and an overall AP\n                    <jats:sub>50<\/jats:sub>\n                    of 90.2%, outperforming existing mainstream models. This study provides a feasible solution for building intelligent and low-cost early-warning systems for forest diseases and highlights the broad application potential of the proposed framework in forestry and other ecological monitoring scenarios.\n                  <\/jats:p>","DOI":"10.3389\/fpls.2025.1701009","type":"journal-article","created":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T14:25:48Z","timestamp":1765895148000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["LE-PWDNet: a lightweight and enhanced detection framework based on DEIM for early-stage pine wilt disease"],"prefix":"10.3389","volume":"16","author":[{"given":"Yujia","family":"Shen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingjing","family":"Qian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haifeng","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,12,15]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.13140\/RG.2.2.18933.65768","article-title":"Pine Wilt Disease a global threat to forestry","volume":"4","author":"Back","year":"2020","journal-title":"Plant Pandemic Study"},{"key":"B2","first-page":"213","article-title":"End-to-end object detection with transformers","volume-title":"Lecture Notes in Computer Science (ECCV 2020)","author":"Carion","year":"2020"},{"key":"B3","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1007\/s11554-025-01710-1","article-title":"An object detection model for Ochotona curzoniae based on the dual-attention mechanism","volume":"22","author":"Chen","year":"2025","journal-title":"J. Real-Time Image Process."},{"key":"B4","doi-asserted-by":"publisher","first-page":"1002","DOI":"10.1109\/TIP.2024.3354108","article-title":"DEA-Net: Single image dehazing based on detail-enhanced convolution and content-guided attention","volume":"33","author":"Chen","year":"2024","journal-title":"IEEE Trans. image Process."},{"key":"B5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11554-025-01729-4","article-title":"PL-YOLO: a lightweight method for real-time detection of pomegranates","volume":"22","author":"Chen","year":"2025","journal-title":"J. Real-Time Image Process."},{"key":"B6","doi-asserted-by":"publisher","first-page":"103177","DOI":"10.1016\/j.cja.2024.08.008","article-title":"Air target intent recognition method combining graphing time series and diffusion models","volume":"38","author":"Chenghai","year":"2025","journal-title":"Chin. J. Aeronautics"},{"key":"B7","doi-asserted-by":"publisher","first-page":"294","DOI":"10.3390\/agriengineering2020019","article-title":"Detection and location of dead trees with pine wilt disease based on deep learning and UAV remote sensing","volume":"2","author":"Deng","year":"2020","journal-title":"AgriEngineering"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2024.1302361","article-title":"Pine wilt disease detection algorithm based on improved YOLOv5","volume":"15","author":"Du","year":"2024","journal-title":"Front. Plant Sci."},{"key":"B9","doi-asserted-by":"publisher","first-page":"8725","DOI":"10.1109\/TMM.2023.3240881","article-title":"Strongsort: Make deepsort great again","volume":"25","author":"Du","year":"2023","journal-title":"IEEE Trans. Multimedia"},{"key":"B10","first-page":"363","article-title":"Wavelet convolutions for large receptive fields","volume-title":"Lecture Notes in Computer Science (ECCV 2024)","author":"Finder","year":"2024"},{"key":"B11","first-page":"1440","article-title":"Fast r-cnn","author":"Girshick","year":"2015"},{"key":"B12","first-page":"15162","article-title":"Deim: Detr with improved matching for fast convergence","author":"Huang","year":"2025"},{"key":"B13","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1007\/978-1-4842-6168-2","author":"Koonce","year":"2021","journal-title":"Convolutional Neural Networks with Swift for TensorFlow: Image Recognition and Dataset Categorization."},{"key":"B14","doi-asserted-by":"publisher","first-page":"109160","DOI":"10.1016\/j.compag.2024.109160","article-title":"An efficient transformer network for detecting multi-scale chicken in complex free-range farming environments via improved RT-DETR","volume":"224","author":"Li","year":"2024","journal-title":"Comput. Electron. Agric."},{"key":"B15","doi-asserted-by":"publisher","first-page":"10797","DOI":"10.3390\/ijms231810797","article-title":"The detection of pine wilt disease: A literature review","volume":"23","author":"Li","year":"2022","journal-title":"Int. J. Mol. Sci."},{"key":"B16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11554-025-01724-9","article-title":"SMC-YOLO: efficient object detector for underwater small sonar target","volume":"22","author":"Li","year":"2025","journal-title":"J. Real-Time Image Process."},{"key":"B17","first-page":"21","article-title":"Ssd: Single shot multibox detector","volume-title":"Lecture Notes in Computer Science (ECCV 2016)","author":"Liu","year":"2016"},{"key":"B18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2024.3362877","article-title":"Clusterformer for pine tree disease identification based on UAV remote sensing image segmentation","volume":"62","author":"Liu","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"B19","doi-asserted-by":"publisher","first-page":"8989","DOI":"10.1109\/TNNLS.2022.3155114","article-title":"\"Central attention network for hyperspectral imagery classification","volume":"34","author":"Liu","year":"2022","journal-title":"IEEE Transactions on Geoscience and Remote Sensing."},{"key":"B20","doi-asserted-by":"publisher","first-page":"6469","DOI":"10.1109\/TIP.2024.3492724","article-title":"Seghsi: Semantic segmentation of hyperspectral images with limited labeled pixels","volume":"33","author":"Liu","year":"2024","journal-title":"IEEE Trans. Image Process"},{"key":"B21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2023.3318071","article-title":"\"Multiarea target attention for hyperspectral image classification","volume":"61","author":"Liu","year":"2023","journal-title":"in IEEE Transactions on Geoscience and Remote Sensing"},{"key":"B22","doi-asserted-by":"publisher","first-page":"438","DOI":"10.3390\/s25020438","article-title":"MSCD-YOLO: A lightweight dense pedestrian detection model with finer-grained feature information interaction","volume":"25","author":"Liu","year":"2025","journal-title":"Sensors"},{"key":"B23","first-page":"17902","article-title":"CATANet: efficient content-aware token aggregation for lightweight image super-resolution","author":"Liu","year":"2025"},{"key":"B24","first-page":"6027","article-title":"Learning to upsample by learning to sample","author":"Liu","year":"2023"},{"key":"B25","doi-asserted-by":"publisher","first-page":"139","DOI":"10.3390\/f14010139","article-title":"Refined assessment of economic loss from pine wilt disease at the subcompartment scale","volume":"14","author":"Liu","year":"2023","journal-title":"Forests"},{"key":"B26","first-page":"5018","article-title":"Star-convolution for image-based 3d object detection","author":"Liu","year":"2022"},{"key":"B27","first-page":"116","article-title":"Shufflenet v2: Practical guidelines for efficient cnn architecture design","author":"Ma","year":"2018"},{"key":"B28","first-page":"1","article-title":"Eigen-cam: Class activation map using principal components","author":"Muhammad","year":"2020"},{"key":"B29","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1007\/s11554-025-01644-8","article-title":"Egc-yolo: strip steel surface defect detection method based on edge detail enhancement and multiscale feature fusion","volume":"22","author":"Ni","year":"2025","journal-title":"J. Real-Time Image Process."},{"key":"B30","doi-asserted-by":"publisher","first-page":"7113","DOI":"10.1007\/s00521-021-06846-2","article-title":"PConv: simple yet effective convolutional layer for generative adversarial network","volume":"34","author":"Park","year":"2022","journal-title":"Neural Computing Appl."},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2410.13842","article-title":"D-FINE: Redefine regression task in DETRs as fine-grained distribution refinement","author":"Peng","year":"2024","journal-title":"arXiv preprint arXiv:2410.13842"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.3390\/s25196025","article-title":"Object detection with transformers: A review","volume":"25","author":"Shehzadi","year":"2023","journal-title":"Sensors"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2502.12524","article-title":"Yolov12: Attention-centric real-time object detectors","author":"Tian","year":"2025","journal-title":"arXiv preprint arXiv:2502.12524"},{"key":"B34","doi-asserted-by":"publisher","first-page":"6609","DOI":"10.3390\/s24206609","article-title":"LFIR-YOLO: Lightweight model for infrared vehicle and pedestrian detection","volume":"24","author":"Wang","year":"2024","journal-title":"Sensors"},{"key":"B35","doi-asserted-by":"publisher","first-page":"4503","DOI":"10.3390\/electronics13224503","article-title":"A novel multi-scale feature enhancement U-shaped network for pixel-level road crack segmentation","volume":"13","author":"Wang","year":"2024","journal-title":"Electronics"},{"key":"B36","first-page":"17872","article-title":"Adaptive rectangular convolution for remote sensing pansharpening","author":"Wang","year":"2025"},{"key":"B37","first-page":"3","article-title":"Cbam: Convolutional block attention module","author":"Woo","year":"2018"},{"key":"B38","doi-asserted-by":"publisher","first-page":"4586","DOI":"10.3390\/app15084586","article-title":"Wavelet-enhanced YOLO for intelligent detection of welding defects in X-ray films","volume":"15","author":"Wu","year":"2025","journal-title":"Appl. Sci."},{"key":"B39","doi-asserted-by":"publisher","first-page":"1672","DOI":"10.3390\/f14081672","article-title":"Extraction of pine wilt disease regions using UAV RGB imagery and improved mask R-CNN models fused with ConvNeXt","volume":"14","author":"Wu","year":"2023","journal-title":"Forests"},{"key":"B40","article-title":"What is YOLOv8: An in-depth exploration of the internal features of the next-generation object detector","author":"Yaseen","year":"2024"},{"key":"B41","doi-asserted-by":"publisher","first-page":"108671","DOI":"10.1016\/j.compag.2024.108671","article-title":"Exploring the potential of visual tracking and counting for trees infected with pine wilt disease based on improved YOLOv5 and StrongSORT algorithm","volume":"218","author":"Ye","year":"2024","journal-title":"Comput. Electron. Agric."},{"key":"B42","doi-asserted-by":"publisher","first-page":"4065","DOI":"10.3390\/rs13204065","article-title":"Three-dimensional convolutional neural network model for early detection of pine wilt disease using UAV-based hyperspectral images","volume":"13","author":"Yu","year":"2021","journal-title":"Remote Sens."},{"key":"B43","first-page":"16965","article-title":"Detrs beat yolos on real-time object detection","author":"Zhao","year":"2024"},{"key":"B44","doi-asserted-by":"publisher","first-page":"296","DOI":"10.1007\/s42417-025-01874-x","article-title":"Few-shot bearing fault diagnosis using adaptive detail convolution and global KAN-transformer with Mahalanobis distance","volume":"13","author":"Zhao","year":"2025","journal-title":"J. Vibration Eng. Technol."},{"key":"B45","first-page":"12780","article-title":"Srformer: Permuted self-attention for single image super-resolution","author":"Zhou","year":"2023"},{"key":"B46","doi-asserted-by":"publisher","first-page":"12780","DOI":"10.1109\/ICCV51070.2023.01174","article-title":"\"SRFormerV2: Taking a closer look at permuted self-attention for image super-resolution","author":"Zhou","year":"2023","journal-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV 2023)"}],"container-title":["Frontiers in Plant Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2025.1701009\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T14:25:49Z","timestamp":1765895149000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2025.1701009\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,15]]},"references-count":46,"alternative-id":["10.3389\/fpls.2025.1701009"],"URL":"https:\/\/doi.org\/10.3389\/fpls.2025.1701009","relation":{},"ISSN":["1664-462X"],"issn-type":[{"value":"1664-462X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,15]]},"article-number":"1701009"}}