Search Results (52)

Citrus Huanglongbing (HLB) is one of the most devastating diseases in the global citrus industry, but its early detection under complex field conditions remains a major challenge. Existing methods often suffer from insufficient dataset diversity and poor generalization, and struggle to accurately detect subtle early-stage lesions and multiple HLB symptoms in natural backgrounds. To address these issues, we propose an enhanced YOLO11-based framework, DCH-YOLO11. We constructed a multi-symptom HLB leaf dataset (MS-HLBD) containing 9219 annotated images across five classes: Healthy (1862), HLB blotchy mottling (2040), HLB Zinc deficiency (1988), HLB yellowing (1768), and Canker (1561), collected under diverse field conditions. To improve detection performance, the DCH-YOLO11 framework incorporates three novel modules: the C3k2 Dynamic Feature Fusion (C3k2_DFF) module, which enhances early and subtle lesion detection through dynamic feature fusion; the C2PSA Context Anchor Attention (C2PSA_CAA) module, which leverages context anchor attention to strengthen feature extraction in complex vein regions; and the High-efficiency Dynamic Feature Pyramid Network (HDFPN) module, which optimizes multi-scale feature interaction to boost detection accuracy across different object sizes. On the MS-HLBD dataset, DCH-YOLO11 achieved a precision of 91.6%, recall of 87.1%, F1-score of 89.3, and mAP50 of 93.1%, surpassing Faster R-CNN, SSD, RT-DETR, YOLOv7-tiny, YOLOv8n, YOLOv9-tiny, YOLOv10n, YOLO11n, and YOLOv12n by 13.6%, 8.8%, 5.3%, 3.2%, 2.0%, 1.6%, 2.6%, 1.8%, and 1.6% in mAP50, respectively. On a publicly available citrus HLB dataset, DCH-YOLO11 achieved a precision of 82.7%, recall of 81.8%, F1-score of 82.2, and mAP50 of 89.4%, with mAP50 improvements of 8.9%, 4.0%, 3.8%, 3.2%, 4.7%, 3.2%, and 3.4% over RT-DETR, YOLOv7-tiny, YOLOv8n, YOLOv9-tiny, YOLOv10n, YOLO11n, and YOLOv12n, respectively. These results demonstrate that DCH-YOLO11 achieves both state-of-the-art accuracy and excellent generalization, highlighting its strong potential for robust and practical citrus HLB detection in real-world applications. Full article

Citrus diseases can lead to surface defects on citrus fruits, adversely affecting their quality. This study aims to accurately identify citrus defects against varying backgrounds by focusing on four types of diseases: citrus black spot, citrus canker, citrus greening, and citrus melanose. We propose an improved YOLOv10-based disease detection method that replaces the traditional convolutional layers in the Backbone network with LDConv to enhance feature extraction capabilities. Additionally, we introduce the GFPN module to strengthen multi-scale information interaction through cross-scale feature fusion, thereby improving detection accuracy for small-target diseases. The incorporation of the DAT mechanism is designed to achieve higher efficiency and accuracy in handling complex visual tasks. Furthermore, we integrate the AFPN module to enhance the model’s detection capability for targets of varying scales. Lastly, we employ the Slide Loss function to adaptively adjust sample weights, focusing on hard-to-detect samples such as blurred features and subtle lesions in citrus disease images, effectively alleviating issues related to sample imbalance. The experimental results indicate that the enhanced model YOLOv10-LGDA achieves impressive performance metrics in citrus disease detection, with accuracy, recall, mAP@50, and mAP@50:95 rates of 98.7%, 95.9%, 97.7%, and 94%, respectively. These results represent improvements of 4.2%, 3.8%, 4.5%, and 2.4% compared to the original YOLOv10 model. Furthermore, when compared to various other object detection algorithms, YOLOv10-LGDA demonstrates superior recognition accuracy, facilitating precise identification of citrus diseases. This advancement provides substantial technical support for enhancing the quality of citrus fruit and ensuring the sustainable development of the industry. Full article

Phytopythium vexans is a plant pathogen responsible for a variety of destructive diseases in crops worldwide. This includes patch canker, damping-off, root, and crown rots in economically important crops, such as apple, pear, grapevine, citrus, avocado, and kiwi. The pathogen has a global distribution, and a recent report confirmed its presence in southern Ontario, Canada. This study presents the first genome sequencing, assembly, and annotation of the Canadian P. vexans strain SS21. To explore how variation in secreted protein repertoires may relate to infection strategies and host adaptation, we compared the predicted secretome of SS21 with reference strains from Iran (CBS 119.80) and China (HF1). The analysis revealed that HF1 harbors a larger set of CAZymes, sterol-binding proteins, and predicted effectors, which may suggest broader adaptive potential. In contrast, strain SS21 appears to have adapted to a niche-specific strategy, with fewer necrosis-inducing proteins, glucanase inhibitors, and effectors, possibly indicating adaptation to specific hosts or ecological conditions. Comparative genome data highlight distinct evolutionary trajectories that may have shaped each strain’s infection strategy, with SS21 potentially serving as a robust additional reference for future studies on P. vexans biology and host interactions. While this analysis identifies key candidate effectors, gene expression studies are required to validate their functional roles in infection and host manipulation. Full article

Citrus pests and diseases severely impact fruit yield and quality. However, existing object detection models face limitations in complex backgrounds, target occlusion, and small target recognition, and they struggle to be efficiently deployed on resource-constrained devices. To address these issues, this study proposes a lightweight pest and disease detection model, YOLOv11-RDTNet, based on the improved YOLOv11n. This model integrates multi-scale features and attention mechanisms to enhance recognition performance in complex scenarios, while adopting a lightweight design to reduce computational costs and improve deployment adaptability. The model introduces three key enhancement features: First, shallow RFD (SRFD) and deep RFD (DRFD) downsampling modules replace traditional convolution modules, improving image feature extraction accuracy and robustness. Second, the Dynamic Group Shuffle Transformer (DGST) module replaces the original C3k2 module, reducing the model’s parameter count and computational demand, further enhancing efficiency and performance. Lastly, the lightweight Task Align Dynamic Detection Head (TADDH) replaces the original detection head, significantly reducing the parameter count and improving accuracy in small-object detection. After processing the collected images, we obtained 1382 images and constructed a dataset containing five types of citrus pests and diseases: anthracnose, canker, yellow vein disease, coal pollution disease, and leaf miner moth. We applied data augmentation on the dataset and conducted experimental validation. Experimental results showed that the YOLOv11-RDTNet model had a parameter count of 1.54 MB, an mAP50 of 87.0%, and a model size of 3.4 MB. Compared to the original YOLOv11 model, the YOLOv11-RDTNet model reduced the parameter count by 40.3%, improved mAP50 by 4.8%, and reduced the model size from 5.5 MB to 3.4 MB. This model not only improved detection accuracy and reduced computational load but also achieved a balance in performance, size, and speed, making it more suitable for deployment on mobile devices. Additionally, the research findings provided an effective tool for citrus pest and disease detection with small sample sizes, offering valuable insights for citrus pest and disease detection in agricultural practices. Full article

Citrus canker, caused by Xanthomonas citri subsp. citri, is a devastating disease that affects citrus production and trade worldwide. Traditional control methods, based on copper compounds, are effective but pose environmental and health risks due to their toxicity and potential for bioaccumulation. This study evaluates the synergistic potential of essential oils (EOs) and rhamnolipids as sustainable alternatives for disease management. Four EOS (citronella, palmarosa, geranium, and clove) were tested for their antibacterial activity. Citronella EO showed a 90% inhibitory concentration (IC 90) of 0.15% (v/v) and a minimum bactericidal concentration of 0.25% (v/v), while the other EOs showed IC 90 and bactericidal activity at 0.06% (v/v). Rhamnolipids (RHLs), biosurfactants produced by Pseudomonas aeruginosa, inhibited X. citri at a concentration of 0.3% (v/v). The combination of citronella EO and RHLs showed a synergistic effect, reducing the inhibitory concentration of citronella by 50% and that of RHLs by more than 90%. In addition, the combined formulation permeabilized more than 80% of bacterial membranes and reduced biofilm formation. In contrast, other oils tested in combination with rhamnolipid showed independent effects. These results indicate that EOs and rhamnolipids represent an environmentally safe strategy for the control of X. citri subsp. citri that overcomes the limitations of conventional methods while reducing environmental and health impacts. Full article

Citrus canker, caused by Xanthomonas citri subsp. citri, and bacterial blight, caused by Xanthomonas citri subsp. malvacearum, results in substantial economic losses worldwide, and searching for new antibacterial agents is a critical challenge. In this study, regional isolates AE28 and RQ3 were obtained from characteristic lesions on Citrus limon and Gossypium hirsutum, respectively. Essential oils extracted by steam distillation from the fresh aerial parts of Pelargonium graveolens and Schinus molle exhibited complete (100%) inhibition of bacterial growth in vitro at a concentration of 1000 ppm, as determined by diffusion tests. To evaluate the potential of these essential oils for controlling Xanthomonas-induced diseases, in vivo assays were conducted on lemon leaves and cotton cotyledons inoculated with the regional AE28 and RQ3 strains. Two treatment approaches were tested: preventive application (24 h before inoculation) and curative application (24 h after inoculation). Preventive and curative treatments with P. graveolens essential oil significantly reduced citrus canker severity, whereas S. molle essential oil did not show a significant reduction compared to the control. In contrast, regardless of the treatment’s timing, both essential oils effectively reduced bacterial blight severity in cotton cotyledons by approximately 1.5-fold. Gas chromatography–mass spectrometry (GC-MS) analysis identified geraniol and citronellol as the major components of P. graveolens essential oil, while limonene and t-cadinol were predominant in S. molle. These findings highlight the promising potential of botanical products as bactericidal agents, warranting further research to optimize their application and efficacy. Full article

Citrus greening disease (HLB) and citrus canker cause financial losses in Florida citrus groves via smaller fruits, blemishes, premature fruit drop, and/or eventual tree death. Management of these two diseases requires early detection and distinction from other leaf defects and infections. Automated leaf inspection with hyperspectral imagery (HSI) is tested in this study. Citrus leaves bearing visible symptoms of HLB, canker, scab, melanose, greasy spot, zinc deficiency, and a control class were collected, and images were taken with a line-scan HSI camera. YOLOv8 was trained to classify multispectral images from this image dataset, created by selecting bands with a novel variance-based method. The ‘small’ network using an intensity-based band combination yielded an overall weighted F1 score of 0.8959, classifying HLB and canker with F1 scores of 0.788 and 0.941, respectively. The network size appeared to exert greater influence on performance than the HSI bands selected. These findings suggest that YOLOv8 relies more heavily on intensity differences than on the texture properties of citrus leaves and is less sensitive to the choice of wavelengths than traditional machine vision classifiers. Full article

Xanthomonas citri subsp. citri (Xcc) is a Gram-negative bacterium responsible for citrus canker, a significant threat to citrus crops. ClpV is a critical protein in the type VI secretion system (T6SS) as an ATPase involved in bacterial motility, adhesion, and pathogenesis to the host for some pathogenic bacteria. In order to investigate the function of clpV gene in Xcc, the clpV-deletion strain ΔclpV was constructed, its biological properties were evaluated, and the differences in gene expression levels between the wild-type strain and ΔclpV were analyzed by transcriptomics. The results exhibited significantly reduced biofilm formation, extracellular polysaccharide synthesis, and swarming motility in ΔclpV compared to the wild-type strain. Although the clpV-deletion did not significantly affect bacterial growth or pathogenicity in terms of disease symptoms on citrus leaves, the mutant showed increased sensitivity to environmental stresses (NaCl, SDS, and H₂O₂) and antibiotics (β-lactams and aminoglycosides). Transcriptome analysis revealed that clpV-deletion altered the expression of motility-related genes and the efflux pump gene mexH. Our findings underscore the importance of ClpV in maintaining biofilm integrity and suggest a multifaceted role in adaptive strategies of Xcc, positioning ClpV as a potential target for mitigating citrus canker disease. Full article

Existing deep learning models for detecting citrus diseases and nutritional deficiencies grapple with issues related to recognition accuracy, complex backgrounds, occlusions, and the need for lightweight architecture. In response, we developed an improved YOLOv8-GABNet model designed specifically for citrus disease and nutritional deficiency detection, which effectively addresses these challenges. This model incorporates several key enhancements: A lightweight ADown subsampled convolutional block is utilized to reduce both the model’s parameter count and its computational demands, replacing the traditional convolutional module. Additionally, a weighted Bidirectional Feature Pyramid Network (BiFPN) supersedes the original feature fusion network, enhancing the model’s ability to manage complex backgrounds and achieve multiscale feature extraction and integration. Furthermore, we introduced important features through the Global to Local Spatial Aggregation module (GLSA), focusing on crucial image details to enhance both the accuracy and robustness of the model. This study processed the collected images, resulting in a dataset of 1102 images. Using LabelImg, bounding boxes were applied to annotate leaves affected by diseases. The dataset was constructed to include three types of citrus diseases—anthracnose, canker, and yellow vein disease—as well as two types of nutritional deficiencies, namely magnesium deficiency and manganese deficiency. This dataset was expanded to 9918 images through data augmentation and was used for experimental validation. The results show that, compared to the original YOLOv8, our YOLOv8-GABNet model reduces the parameter count by 43.6% and increases the mean Average Precision (mAP50) by 4.3%. Moreover, the model size was reduced from 50.1 MB to 30.2 MB, facilitating deployment on mobile devices. When compared with mainstream models like YOLOv5s, Faster R-CNN, SSD, YOLOv9t, and YOLOv10n, the YOLOv8-GABNet model demonstrates superior performance in terms of size and accuracy, offering an optimal balance between performance, size, and speed. This study confirms that the model effectively identifies the common diseases and nutritional deficiencies of citrus from Conghua’s “Citrus Planet”. Future deployment to mobile devices will provide farmers with instant and precise support. Full article

Citrus canker, a highly transmissible bacterial disease, has three major types, with Asiatic canker (Canker A), caused by Xanthomonas citri pv. citri (Xcc A), being the most widespread and severe, affecting most citrus varieties. Xcc A has two mild variants, Xcc A* and A^w with a limited host range, reported in Southwest Asia and Florida, respectively. Since 2015, the canker caused by Xcc A^w has been being reported in the Rio Grande Valley of South Texas where the Texas commercial citrus industry is located. In 2016, a more severe Canker A was reported in the upper Texas gulf coast region, north of the Rio Grande Valley, posing a potential threat to the Texas citrus industry. Given that existing diagnostic methods cannot reliably distinguish Xcc A^w from Xcc A, we developed a loop-mediated isothermal amplification (LAMP) assay specific to Xcc A^w (LAMP-A^w) for rapid, field-based identification of this bacterial variant. The detection limit of LAMP-A^w was ~4.52 Log₁₀ copies of the target molecule. This study also evaluated the field applicability of the LAMP-A^w assay by coupling the LAMP-A^w assay with a lateral flow immunoassay system. Full article

Citrus diseases are significant threats to citrus groves, causing financial losses through reduced fruit size, blemishes, premature fruit drop, and tree death. The detection of citrus diseases via leaf inspection can improve grove management and mitigation efforts. This study explores the potential of a portable reflectance and fluorescence hyperspectral imaging (HSI) system for detecting and classifying a control group and citrus leaf diseases, including canker, Huanglongbing (HLB), greasy spot, melanose, scab, and zinc deficiency. The HSI system was used to simultaneously collect reflectance and fluorescence images from the front and back sides of the leaves. Nine machine learning classifiers were trained using full spectra and spectral bands selected through principal component analysis (PCA) from the HSI with pixel-based and leaf-based spectra. A support vector machine (SVM) classifier achieved the highest overall classification accuracy of 90.7% when employing the full spectra of combined reflectance and fluorescence data and pixel-based analysis from the back side of the leaves, whereas a discriminant analysis classifier yielded the best accuracy of 94.5% with the full spectra of combined reflectance and fluorescence data and leaf-based analysis. Among the diseases, control, scab, and melanose were classified most accurately, each with over 90% accuracy. Therefore, the integration of the reflectance and fluorescence HSI with advanced machine learning techniques demonstrated the capability to accurately detect and classify these citrus leaf diseases with high precision. Full article

Accurate categorization and timely control of leaf diseases are crucial for citrus growth. We proposed the Multi-Models Fusion Network (MMFN) for citrus leaf diseases detection based on model fusion and transfer learning. Compared to traditional methods, the algorithm (integrating transfer learning Alexnet, VGG, and Resnet) we proposed can address the issues of limited categories, slow processing speed, and low recognition accuracy. By constructing efficient deep learning models and training and optimizing them with a large dataset of citrus leaf images, we ensured the broad applicability and accuracy of citrus leaf disease detection, achieving high-precision classification. Herein, various deep learning algorithms, including original Alexnet, VGG, Resnet, and transfer learning versions Resnet34 (Pre_Resnet34) and Resnet50 (Pre_Resnet50) were also discussed and compared. The results demonstrated that the MMFN model achieved an average accuracy of 99.72% in distinguishing between diseased and healthy leaves. Additionally, the model attained an average accuracy of 98.68% in the classification of multiple diseases (citrus huanglongbing (HLB), greasy spot disease and citrus canker), insect pests (citrus leaf miner), and deficiency disease (zinc deficiency). These findings conclusively illustrate that deep learning model fusion networks combining transfer learning and integration algorithms can automatically extract image features, enhance the automation and accuracy of disease recognition, demonstrate the significant potential and application value in citrus leaf disease classification, and potentially drive the development of smart agriculture. Full article

Mexico ranks second in the world for Persian lime (Citrus latifolia) exports, making it the principal citrus exporter within the national citrus industry, exporting over 600,000 tons per year. However, diseases are the main factor reducing production, resulting in significant economic losses. Among these diseases, fungal diseases like dieback, caused by species of Lasiodiplodia, are an emerging issue in Persian lime. Symptoms include gummosis, twig and branch dieback, cankers, the necrosis of bark and wood, fruit mummification, and tree decline. The aim of this study was to investigate the occurrence and pathogenicity of the fungal species associated with twig and branch dieback, cankers, and decline of Persian lime trees in southern Mexico, and to elucidate the current status of the Lasiodiplodia species causing the disease in Mexico. During June, July, and August of 2023, a total of the 9229 Persian lime trees were inspected across 230 hectares of Persian lime orchards in southern Mexico, and symptoms of the disease were detected in 48.78% of the trees. Branches from 30 of these Persian lime trees were collected. Fungal isolates were obtained, resulting in a collection of 40 strains. The isolates were characterized molecularly and phylogenetically through the partial regions of four loci: the internal transcribed spacer region (ITS), the β-tubulin gene (tub2), the translation elongation factor 1-alpha gene (tef1-α), and the DNA-directed RNA polymerase II second largest subunit (rpb2). Additionally, pathogenicity was assessed, successfully completing Koch’s postulates on both detached Persian lime branches and certified 18-month-old Persian lime plants. Through multilocus molecular phylogenetic identification, pathogenicity, and virulence tests, five species were identified as causal agents: L. iraniensis, L. lignicola, L. mexicanensis, L. pseudotheobromae, and L. theobromae. This study demonstrates that in southern Mexico, at least five species of the genus Lasiodiplodia are responsible for dieback in Persian lime. Additionally, this is the first report of L. lignicola and L. mexicanensis as causal agents of the disease in citrus, indicating novel host interactions between species of Lasiodiplodia and C. latifolia. Full article

Citrus bacterial canker disease, caused by Xanthomonas citri subsp. citri (Xcc), poses a significant global threat to the citrus industry. Lateral organ boundaries 1 (Lob1) is confirmed as a citrus susceptibility gene that induces pathogenesis by interaction with the PthA4 effector of Xcc. Citron C-05 (Citrus medica) is a Citrus genotype resistant to Xcc. However, there is little information available on the regulation of Lob1 in resistant genotypes, which is important for the breeding of citrus cultivars resistant to canker disease. This study aimed to identify upstream regulatory factors of Lob1 in Citron C-05 and to investigate its function in disease resistance. ‘Bingtang’ sweet orange (C. sinensis), a susceptible genotype, was utilized as the control. cDNA yeast libraries of Xcc-induced Citron C-05 and ‘Bingtang’ sweet orange were constructed. The capacities of ‘Bingtang’ and Citron C-05 were 1.896 × 10⁷ and 2.154 × 10⁷ CFU, respectively. The inserted fragments ranged from 500 to 2000 bp with a 100% recombination rate. The promoter of Lob1 was segmented into two pieces and the P1 fragment from both genotypes was used to construct a bait yeast (PAbAi-CsLob1-P1; PAbAi-CmLob1-P1). Through library screening with the bait yeast, upstream regulators interacting with the Lob1-P1 promoter were identified and then validated using Y1H and dual-luciferase tests. The expression analysis of the three transcript factors indicated that RMA3 was upregulated by inoculation with Xcc in the resistant Citron C-05, but not in the susceptible sweet orange. The overexpression of CsRMA3 in ‘Bingtang’ sweet orange led to reduced canker symptoms, with a significantly lower pathogen density in the leaves following Xcc inoculation. When CmRMA3 was silenced by virus-induced gene silencing (VIGS) in Citron C-05, typical canker symptoms appeared on the CmRMA3-silenced leaves at 15 days post-inoculation with Xcc. Further expression analyses revealed that the CmRMA3 transcription factor suppressed the expression of Lob1. These results suggest that RMA3 participates in the resistant reaction of Citron C-05 to Xcc infection, and such a response might be in relation to its suppression of the expression of the pathogenic gene Lob1. Full article

Citrus canker caused by Xanthomonas citri subsp. citri is a devastating bacterial disease with severe implications for the citrus industry. Microorganisms possessing biocontrol capabilities against X. citri subsp. citri offer a highly promising strategy for healthy citrus management. In the present study, a broad-spectrum antagonist strain ZJLMBA1908 with potent antibacterial activity against X. citri subsp. citri was isolated from symptomatic lemon leaves, and identified as Bacillus amyloliquefaciens. Cell-free supernatant (CFS) of strain ZJLMBA1908 also exhibited remarkable antimicrobial activity, especially suppressing the growth of X. citri subsp. citri and Nigrospora oryzae, with inhibition rates of 27.71% and 63.75%, respectively. The antibacterial crude extract (CE) derived from the CFS displayed effective activity against X. citri subsp. citri. A preventive treatment using the CE significantly reduced the severity and incidence of citrus canker in a highly susceptible citrus host. Additionally, the CE maintained activity in the presence of protease and under a wide range of temperature and pH treatments. Applying high-performance liquid chromatography (HPLC) to separate and purify the CE resulted in the discovery of one highly potent anti-X. citri subsp. citri subfraction, namely CE3, which could completely inhibit the growth of X. citri subsp. citri. Liquid chromatography–electrospray ionization–mass spectrometry (LC–ESI–MS) analysis revealed that CE3 mainly consisted of palmitic acid, surfactin C15, phytosphingosine and dihydrosphingosine. Taken together, the results contribute to the possible biocontrol mechanisms of B. amyloliquefaciens ZJLMBA1908, as well as providing a promising new candidate strain as a biological control agent for controlling citrus canker. Full article