The impact of fine-tuning paradigms on unknown plant diseases recognition.

Plant diseases pose significant threats to agriculture, impacting both food safety and public health. Traditional plant disease detection systems are typically limited to recognizing disease categories included in the training dataset, rendering them ineffective against new disease types. Although out-of-distribution (OOD) detection methods have been proposed to address this issue, the impact of fine-tuning paradigms on these methods has been overlooked. This paper focuses on studying the impact of fine-tuning paradigms on the performance of detecting unknown plant diseases. Currently, fine-tuning on visual tasks is mainly divided into visual-based models and visual-language-based models. We first discuss the limitations of large-scale visual language models in this task: textual prompts are difficult to design. To avoid the side effects of textual prompts, we futher explore the effectiveness of purely visual pre-trained models for OOD detection in plant disease tasks. Specifically, we employed five publicly accessible datasets to establish benchmarks for open-set recognition, OOD detection, and few-shot learning in plant disease recognition. Additionally, we comprehensively compared various OOD detection methods, fine-tuning paradigms, and factors affecting OOD detection performance, such as sample quantity. The results show that visual prompt tuning outperforms fully fine-tuning and linear probe tuning in out-of-distribution detection performance, especially in the few-shot scenarios. Notably, the max-logit-based on visual prompt tuning achieves an AUROC score of 94.8 % in the 8-shot setting, which is nearly comparable to the method of fully fine-tuning on the full dataset (95.2 % ), which implies that an appropriate fine-tuning paradigm can directly improve OOD detection performance. Finally, we visualized the prediction distributions of different OOD detection methods and discussed the selection of thresholds. Overall, this work lays the foundation for unknown plant disease recognition, providing strong support for the security and reliability of plant disease recognition systems. We will release our code at https://github.com/JiuqingDong/PDOOD to further advance this field.

Optimizing Corn Tar Spot Measurement: A Deep Learning Approach Using Red-Green-Blue Imaging and Stromata Contour Detection Algorithm for Leaf-Level Disease Severity Analysis.

Visual detection of stromata (brown-black, elevated fungal fruiting bodies) is a primary method for quantifying tar spot early in the season, as these structures are definitive signs of the disease and essential for effective disease monitoring and management. Here, we present Stromata Contour Detection Algorithm version 2 (SCDA v2), which addresses the limitations of the previously developed SCDA version 1 (SCDA v1) without the need for empirical search of the optimal Decision Making Input Parameters (DMIPs), while achieving higher and consistent accuracy in tar spot stromata detection. SCDA v2 operates in two components: (i) SCDA v1 producing tar-spot-like region proposals for a given input corn leaf Red-Green-Blue (RGB) image, and (ii) a pre-trained Convolutional Neural Network (CNN) classifier identifying true tar spot stromata from the region proposals. To demonstrate the enhanced performance of the SCDA v2, we utilized datasets of RGB images of corn leaves from field (low, middle, and upper canopies) and glasshouse conditions under variable environments, exhibiting different tar spot severities at various corn developmental stages. Various accuracy analyses (F1-score, linear regression, and Lin's concordance correlation), showed that SCDA v2 had a greater agreement with the reference data (human visual annotation) than SCDA v1. SCDA v2 achievd 73.7% mean Dice values (overall accuracy), compared to 30.8% for SCDA v1. The enhanced F1-score primarily resulted from eliminating overestimation cases using the CNN classifier. Our findings indicate the promising potential of SCDA v2 for glasshouse and field-scale applications, including tar spot phenotyping and surveillance projects.

Diversity of Trichoderma species associated with the black rot disease of Gastrodia elata, including four new species.

Introduction: Trichoderma species establish symbiotic relationships with plants through both parasitic and mutualistic mechanisms. While some Trichoderma species act as plant pathogenic fungi, others utilize various strategies to protect and enhance plant growth. Methods: Phylogenetic positions of new species of Trichoderma were determined through multi-gene analysis relying on the internal transcribed spacer (ITS) regions of the ribosomal DNA, the translation elongation factor 1-α (tef1-α) gene, and the RNA polymerase II (rpb2) gene. Additionally, pathogenicity experiments were conducted, and the aggressiveness of each isolate was evaluated based on the area of the cross-section of the infected site. Results: In this study, 13 Trichoderma species, including 9 known species and 4 new species, namely, T. delicatum, T. robustum, T. perfasciculatum, and T. subulatum were isolated from the diseased tubers of Gastrodia elata in Yunnan, China. Among the known species, T. hamatum had the highest frequency. T. delicatum belonged to the Koningii clade. T. robustum and T. perfasciculatum were assigned to the Virens clade. T. subulatum emerged as a new member of the Spirale clade. Pathogenicity experiments were conducted on the new species T. robustum, T. delicatum, and T. perfasciculatum, as well as the known species T. hamatum, T. atroviride, and T. harzianum. The infective abilities of different Trichoderma species on G. elata varied, indicating that Trichoderma was a pathogenic fungus causing black rot disease in G. elata. Discussion: This study provided the morphological characteristics of new species and discussed the morphological differences with phylogenetically proximate species, laying the foundation for research aimed at preventing and managing diseases that affect G. elata.

First Report of Phyllosticta capitalensis Causing Postharvest Brown Spot Disease on Guava Fruit in Thailand.

Guava (Psidium guajava L.) is a popular fruit crop that is widely cultivated in Thailand. In November 2023, brown spot disease on guava was observed during postharvest storage at 22 to 31°C and 70 to 75% relative humidity over a period of 3 to 7 days in Fang District, Chiang Mai Province, Thailand. The disease incidence was ~20% of 100 fruits per pallet box. The disease severity on each fruit ranged from 40 to 70% of the surface area affected by lesions. The symptoms appeared as circular to irregular brown to dark brown spots, ranging from 5 to 30 mm in diameter. Fungi were isolated from lesions using a single conidial isolation method (Choi et al. 1999). Two fungal isolates (SDBR-CMU497 and SDBR-CMU498) with similar morphology were obtained. Colonies on potato dextrose agar (PDA) and malt extract agar (MEA) were 65 to 67 and 29 to 38 mm in diameter, respectively after incubation for 1 week at 25°C. Colonies on PDA and MEA were flat, slightly undulate, greenish gray in the center, greyish green at the margin; reverse black. Both isolates produced asexual structures. Pycnidia were black, granular, and grouped. Conidiogenous cells were hyaline, subcylindrical to cylindrical, 8.5 to 17.5 × 3 to 5.5 µm. Conidia were single-celled, hyaline, obovoid to ellipsoid, 5.2 to 9.4 × 3.6 to 7.5 µm (n = 50), smooth-walled, with a single apical appendage. Morphologically, both isolates resembled Phyllosticta capitalensis (Wikee et al. 2013). The internal transcribed spacer (ITS) region, large subunit (nrLSU), translation elongation factor 1-alpha (tef1-α), actin (act), and glyceraldehyde-3-phosphate dehydrogenase (GAPDH) genes were amplified using primer pairs ITS5/ITS4, LROR/LRO5, EF1-728F/EF2, ACT-512F/ACT-783R, and GPD1-LM/GPD2-LM, respectively (White et al. 1990; Zhang et al. 2022). Sequences were deposited in GenBank (ITS: PP946770, PP946771; nrLSU: PP948677, PP948678; tef1-α: PP948012, PP948013; act: PP948014, PP948015; GAPDH: PP948016, PP948017). Maximum likelihood phylogenetic analyses of the concatenated five genes identified both isolates as P. capitalensis. Thus, both morphology and molecular data confirmed the fungus as P. capitalensis. To confirm pathogenicity, healthy commercial guava fruits cultivar Kim Ju were surface disinfected by 0.1% NaClO for 3 min, rinsed three times with sterile distilled water, and wounded (Cruz-Lagunas et al. 2023). Conidia were collected from 2-week-old cultures on PDA and suspended in sterile distilled water. Fifteen microliters of a 1 × 106 conidia/ml suspension were dropped onto the wounded fruits. Mock inoculations were used as a control with sterile distilled water. Ten replications were conducted for each treatment and repeated twice. The inoculated fruits were stored in individual sterile plastic boxes at 25°C with 80 to 90% relative humidity. After 7 days, all inoculated fruits exhibited brown to dark brown lesions, while control fruits were asymptomatic. Phyllosticta capitalensis was consistently reisolated from the inoculated tissues on PDA to complete Koch's postulates. Prior to this study, P. capitalensis was known to cause brown or black spot disease on guava fruits cultivated in fields in China (Liao et al. 2020), Egypt (Arafat 2018), and Mexico (Cruz-Lagunas et al. 2023). To our knowledge, this is the first report of P. capitalensis causing postharvest brown spot disease on guava fruit in Thailand. The results will inform epidemiological investigations and future approaches to managing this disease.

Predicting plant disease epidemics using boosted regression trees.

Plant epidemics are often associated with weather-related variables. It is difficult to identify weather-related predictors for models predicting plant epidemics. In the article by Shah et al., to predict Fusarium head blight (FHB) epidemics of wheat, they explored a functional approach using scalar-on-function regression to model a binary outcome (FHB epidemic or non-epidemic) with respect to weather time series spanning 140 days relative to anthesis. The scalar-on-function models fit the data better than previously described logistic regression models. In this work, given the same dataset and models, we attempt to reproduce the article by Shah et al. using a different approach, boosted regression trees. After fitting, the classification accuracy and model statistics are surprisingly good.

Exploitation of functionalized green nanomaterials for plant disease management.

A crucial determining factor in agricultural productivity is biotic stress. In addition, supply of quality food to the ever-increasing world's population has raised the food demand tremendously. Therefore, enhanced agricultural crop productivity is the only option to mitigate these concerns. It ultimately demanded the often and indiscriminate use of synthetic agrochemicals such as chemical fertilizers, pesticides, insecticides, herbicides, etc. for the management of various biotic stresses including a variety of plant pathogens. However, the food chain and biosphere are severely impacted due to the use of such harmful agrochemicals and their byproducts. Hence, it is need of hour to search for novel, effective and ecofriendly approaches for the management of biotic stresses in crop plants. Particularly, in plant disease management, efforts are being made to take advantage of newly emerged science i.e. nanotechnology for the creation of inorganic nanoparticles (NPs) such as metallic, oxide, sulphide, etc. through different routes and their application in plant disease management. Among these, green nanomaterials which are synthesized using environmentally friendly methods and materials reported to possess unique properties (such as high surface area, adjustable size and shape, and specific functionalities) making them ideal candidates for targeted disease control. Nanotechnology can stop crop losses by managing specific diseases from soil, plants, and hydroponic systems. This review mainly focuses on the application of biologically produced green NPs in the treatment of plant diseases caused due to bacteria, viruses, and fungi. The utilization of green synthesis of NPs in the creation of intelligent targeted pesticide and biomolecule control delivery systems, for disease management is considered environmentally friendly due to its pursuit of less hazardous, sustainable, and environmentally friendly methods.

MLNAS: Meta-learning based neural architecture search for automated generation of deep neural networks for plant disease detection tasks.

Plant diseases pose a significant threat to agricultural productivity worldwide. Convolutional neural networks (CNNs) have achieved state-of-the-art performances on several plant disease detection tasks. However, the manual development of CNN models using an exhaustive approach is a resource-intensive task. Neural Architecture Search (NAS) has emerged as an innovative paradigm that seeks to automate model generation procedures without human intervention. However, the application of NAS in plant disease detection has received limited attention. In this work, we propose a two-stage meta-learning-based neural architecture search system (ML NAS) to automate the generation of CNN models for unseen plant disease detection tasks. The first stage recommends the most suitable benchmark models for unseen plant disease detection tasks based on the prior evaluations of benchmark models on existing plant disease datasets. In the second stage, the proposed NAS operators are employed to optimize the recommended model for the target task. The experimental results showed that the MLNAS system's model outperformed state-of-the-art models on the fruit disease dataset, achieving an accuracy of 99.61%. Furthermore, the MLNAS-generated model outperformed the Progressive NAS model on the 8-class plant disease dataset, achieving an accuracy of 99.8%. Hence, the proposed MLNAS system facilitates faster model development with reduced computational costs.

From glycans to green biotechnology: exploring cell wall dynamics and phytobiota impact in plant glycopathology.

Filamentous plant pathogens, including fungi and oomycetes, pose significant threats to cultivated crops, impacting agricultural productivity, quality and sustainability. Traditionally, disease control heavily relied on fungicides, but concerns about their negative impacts motivated stakeholders and government agencies to seek alternative solutions. Biocontrol agents (BCAs) have been developed as promising alternatives to minimize fungicide use. However, BCAs often exhibit inconsistent performances, undermining their efficacy as plant protection alternatives. The eukaryotic cell wall of plants and filamentous pathogens contributes significantly to their interaction with the environment and competitors. This highly adaptable and modular carbohydrate armor serves as the primary interface for communication, and the intricate interplay within this compartment is often mediated by carbohydrate-active enzymes (CAZymes) responsible for cell wall degradation and remodeling. These processes play a crucial role in the pathogenesis of plant diseases and contribute significantly to establishing both beneficial and detrimental microbiota. This review explores the interplay between cell wall dynamics and glycan interactions in the phytobiome scenario, providing holistic insights for efficiently exploiting microbial traits potentially involved in plant disease mitigation. Within this framework, the incorporation of glycobiology-related functional traits into the resident phytobiome can significantly enhance the plant's resilience to biotic stresses. Therefore, in the rational engineering of future beneficial consortia, it is imperative to recognize and leverage the understanding of cell wall interactions and the role of the glycome as an essential tool for the effective management of plant diseases.

Phytoplasma-Associated Diseases in South America: Thirty Years of Research.

Phytoplasma-associated diseases are mainly insect-transmitted and are present worldwide. Considering that disease detection is a relevant environmental factor that may elucidate the presence of these diseases, a review reporting the geographic distribution of phytoplasma taxa in geographically consistent areas helps manage diseases appropriately and reduce their spreading. This work summarizes the data available about the identification of the phytoplasma associated with several diverse diseases in South America in the last decades. The insect vectors and putative vectors together with the plant host range of these phytoplasmas are also summarized. Overall, 16 'Candidatus Phytoplasma' species were detected, and those most frequently detected in agricultural-relevant crops such as corn, alfalfa, grapevine, and other horticultural species are 'Ca. P. pruni', 'Ca. P. asteris', and 'Ca. P. fraxini'.

Engineered Resistance to Tobamoviruses.

Tobacco mosaic virus (TMV) was the first virus to be studied in detail and, for many years, TMV and other tobamoviruses, particularly tomato mosaic virus (ToMV) and tobamoviruses infecting pepper (Capsicum spp.), were serious crop pathogens. By the end of the twentieth and for the first decade of the twenty-first century, tobamoviruses were under some degree of control due to introgression of resistance genes into commercial tomato and pepper lines. However, tobamoviruses remained important models for molecular biology, biotechnology and bio-nanotechnology. Recently, tobamoviruses have again become serious crop pathogens due to the advent of tomato brown rugose fruit virus, which overcomes tomato resistance against TMV and ToMV, and the slow but apparently inexorable worldwide spread of cucumber green mottle mosaic virus, which threatens all cucurbit crops. This review discusses a range of mainly molecular biology-based approaches for protecting crops against tobamoviruses. These include cross-protection (using mild tobamovirus strains to 'immunize' plants against severe strains), expressing viral gene products in transgenic plants to inhibit the viral infection cycle, inducing RNA silencing against tobamoviruses by expressing virus-derived RNA sequences in planta or by direct application of double-stranded RNA molecules to non-engineered plants, gene editing of host susceptibility factors, and the transfer and optimization of natural resistance genes.

Discovery of Novel Antioomycete Metabolites from the Marine-Derived Fungus Paraconiothyrium sporulosum.

In our screening program for natural products that are effective in controlling plant diseases, we found that the culture filtrate of Paraconiothyrium sporulosum SFC20160907-M11 effectively suppressed the development of tomato late blight disease caused by Phytophthora infestans. Using a bioassay-guided fractionation of antioomycete activity, 12 active compounds (1-12) were obtained from an ethyl acetate extract of the culture filtrate. Chemical structures of five new compounds 1-5 were determined by the extensive analyses of nuclear magnetic resonance (NMR), high resolution mass spectrometry (HRMS), and circular dichroism (CD) data. Interestingly, mycosporulonol (1) and botrallin (8) completely inhibited the growth of P. infestans at concentrations of 8 and 16 µg/mL, respectively. Furthermore, the spray treatment of 1 and 8 (500 µg/mL) successfully protected tomato seedlings against P. infestans with disease control values of 92%. Taken together, these results suggest that the culture filtrates of P. sporulosum SFC20160907-M11 and their bioactive metabolites can be used as new antioomycete agents for Phytophthora late blight control.

Biocontrol potential of plant growth-promoting rhizobacteria against plant disease and insect pest.

Biological control is a promising approach to enhance pathogen and pest control to ensure high productivity in cash crop production. Therefore, PGPR biofertilizers are very suitable for application in the cultivation of tea plants (Camellia sinensis) and tobacco, but it is rarely reported so far. In this study, production of a consortium of three strains of PGPR were applied to tobacco and tea plants. The results demonstrated that plants treated with PGPR exhibited enhanced resistance against the bacterial pathogen Pseudomonas syringae (PstDC3000). The significant effect in improving the plant's ability to resist pathogen invasion was verified through measurements of oxygen activity, bacterial colony counts, and expression levels of resistance-related genes (NPR1, PR1, JAZ1, POD etc.). Moreover, the application of PGPR in the tea plantation showed significantly reduced population occurrences of tea green leafhoppers (Empoasca onukii Matsuda), tea thrips (Thysanoptera:Thripidae), Aleurocanthus spiniferus (Quaintanca) and alleviated anthracnose disease in tea seedlings. Therefore, PGPR biofertilizers may serve as a viable biological control method to improve tobacco and tea plant yield and quality. Our findings revealed part of the mechanism by which PGPR helped improve plant biostresses resistance, enabling better application in agricultural production.

PND-Net: plant nutrition deficiency and disease classification using graph convolutional network.

Crop yield production could be enhanced for agricultural growth if various plant nutrition deficiencies, and diseases are identified and detected at early stages. Hence, continuous health monitoring of plant is very crucial for handling plant stress. The deep learning methods have proven its superior performances in the automated detection of plant diseases and nutrition deficiencies from visual symptoms in leaves. This article proposes a new deep learning method for plant nutrition deficiencies and disease classification using a graph convolutional network (GNN), added upon a base convolutional neural network (CNN). Sometimes, a global feature descriptor might fail to capture the vital region of a diseased leaf, which causes inaccurate classification of disease. To address this issue, regional feature learning is crucial for a holistic feature aggregation. In this work, region-based feature summarization at multi-scales is explored using spatial pyramidal pooling for discriminative feature representation. Furthermore, a GCN is developed to capacitate learning of finer details for classifying plant diseases and insufficiency of nutrients. The proposed method, called Plant Nutrition Deficiency and Disease Network (PND-Net), has been evaluated on two public datasets for nutrition deficiency, and two for disease classification using four backbone CNNs. The best classification performances of the proposed PND-Net are as follows: (a) 90.00% Banana and 90.54% Coffee nutrition deficiency; and (b) 96.18% Potato diseases and 84.30% on PlantDoc datasets using Xception backbone. Furthermore, additional experiments have been carried out for generalization, and the proposed method has achieved state-of-the-art performances on two public datasets, namely the Breast Cancer Histopathology Image Classification (BreakHis 40 × : 95.50%, and BreakHis 100 × : 96.79% accuracy) and Single cells in Pap smear images for cervical cancer classification (SIPaKMeD: 99.18% accuracy). Also, the proposed method has been evaluated using five-fold cross validation and achieved improved performances on these datasets. Clearly, the proposed PND-Net effectively boosts the performances of automated health analysis of various plants in real and intricate field environments, implying PND-Net's aptness for agricultural growth as well as human cancer classification.

Colletotrichum caladii sp. nov. causing anthracnose leaf spot of Caladium × hortulanum (Araceae) in Florida, USA.

Caladium (Caladium × hortulanum) is an ornamental plant popular for its variable and colorful foliage. In 2020, plants showing leaf spots and blight, typical of anthracnose, were found in a field trial at the University of Florida's Gulf Coast Research and Education Center (UF/GCREC) in Wimauma, FL, USA. Leaf samples consistently yielded a Colletotrichum-like species with curved conidia and abundant setae production in the acervuli. The internal transcribed spacer (ITS), partial sequences of the glyceraldehyde-3-phosphate dehydrogenase gene (gapdh), actin gene (act), chitin synthase 1 gene (chs-1), beta-tubulin gene (tub2), and histone3 gene (his3) were amplified and sequenced. Blastn searches in the NCBI GenBank database revealed similarities to species of the Colletotrichum truncatum species complex. Phylogenetic analyses using multi-locus sequence data supports a distinct species within this complex, with the closest related species being C. curcumae. Based on morphological and phylogenetic analyses, a new species of Colletotrichum, named C. caladii, is reported. Pathogenicity assays and subsequent isolation confirmed that this species was the causal agent of the disease.

Escuzarmycins A-D, Potent Biofungicides to Control Septoria tritici Blotch.

A study targeting novel antifungal metabolites identified potent in vitro antifungal activity against key plant pathogens in acetone extracts of Streptomyces sp. strain CA-296093. Feature-based molecular networking revealed the presence in this extract of antimycin-related compounds, leading to the isolation of four new compounds: escuzarmycins A-D (1-4). Extensive structural elucidation, employing 1D and 2D NMR, high-resolution mass spectrometry, Marfey's analysis, and NOESY correlations, confirmed their structures. The bioactivity of these compounds was tested against six fungal phytopathogens, and compounds 3 and 4 demonstrated strong efficacy, particularly against Zymoseptoria tritici, with compound 3 exhibiting the highest potency (EC50: 11 nM). Both compounds also displayed significant antifungal activity against Botrytis cinerea and Colletotrichum acutatum, with compound 4 proving to be the most potent. Despite moderate cytotoxicity against the human cancer cell line HepG2, compounds 3 and 4 emerge as promising fungicides for combating Septoria tritici blotch, anthracnose, and gray mold.

From leaf to harvest: achieving sustainable agriculture through advanced disease prediction with DBN-EKELM.

BACKGROUND: In the agricultural sector, the early identification of plant diseases presents a pressing challenge. Throughout the growing season, plants remain vulnerable to an array of diseases. Failure to detect these diseases at their early stages can significantly compromise the overall yield, thereby reducing profitability for farmers. To address this issue, several researchers have introduced standard methods that leverage machine learning and deep learning techniques. However, many of these methods offer limited classification accuracy and often necessitate extensive training parameter adjustments. METHOD: The objective of this study is to develop a new deep learning-based technique for detecting and classifying plant diseases at earlier stages. Thus, this paper introduces a novel technique known as the deep belief network-based enhanced kernel extreme learning machine (DBN-EKELM) that identifies a disease automatically and performs effective classification. The initial phase involves data preprocessing to enhance quality of plant leaf images, facilitating the extraction of critical information. With the goal of achieving superior classification accuracy, this paper proposes the use of the DBN-EKELM technique for optimal plant leaf disease detection. Given that KELM parameters are highly sensitive to minor variations, proper parameter tuning is essential and introduces a novel binary gaining sharing knowledge-based optimization algorithm (NBGSK). RESULT: The efficacy of the proposed DBN-EKELM method is evaluated by comparing its performance with other conventional methods, considering various measures like accuracy, precision, specificity, sensitivity and F-measure. CONCLUSION: Experimental analyses demonstrate that the DBN-EKELM technique achieves an impressive rate of approximately 98.2%, 97%, 98.1%, 97.4% as well as 97.8%, surpassing other standard methods. © 2024 Society of Chemical Industry.

Robust diagnosis and meta visualizations of plant diseases through deep neural architecture with explainable AI.

Deep learning has emerged as a highly effective and precise method for classifying images. The presence of plant diseases poses a significant threat to food security. However, accurately identifying these diseases in plants is challenging due to limited infrastructure and techniques. Fortunately, the recent advancements in deep learning within the field of computer vision have opened up new possibilities for diagnosing plant pathology. Detecting plant diseases at an early stage is crucial, and this research paper proposes a deep convolutional neural network model that can rapidly and accurately identify plant diseases. Given the minimal variation in image texture and color, deep learning techniques are essential for robust recognition. In this study, we introduce a deep, explainable neural architecture specifically designed for recognizing plant diseases. Fine-tuned deep convolutional neural network is designed by freezing the layers and adjusting the weights of learnable layers. By extracting deep features from a down sampled feature map of a fine-tuned neural network, we are able to classify these features using a customized K-Nearest Neighbors Algorithm. To train and validate our model, we utilize the largest standard plant village dataset, which consists of 38 classes. To evaluate the performance of our proposed system, we estimate specificity, sensitivity, accuracy, and AUC. The results demonstrate that our system achieves an impressive maximum validation accuracy of 99.95% and an AUC of 1, making it the most ideal and highest-performing approach compared to current state-of-the-art deep learning methods for automatically identifying plant diseases.

ScAnalyzer: an image processing tool to monitor plant disease symptoms and pathogen spread in Arabidopsis thaliana leaves.

BACKGROUND: Plants are known to be infected by a wide range of pathogenic microbes. To study plant diseases caused by microbes, it is imperative to be able to monitor disease symptoms and microbial colonization in a quantitative and objective manner. In contrast to more traditional measures that use manual assignments of disease categories, image processing provides a more accurate and objective quantification of plant disease symptoms. Besides monitoring disease symptoms, computational image processing provides additional information on the spatial localization of pathogenic microbes in different plant tissues. RESULTS: Here we report on an image analysis tool called ScAnalyzer to monitor disease symptoms and bacterial spread in Arabidopsis thaliana leaves. Thereto, detached leaves are assembled in a grid and scanned, which enables automated separation of individual samples. A pixel color threshold is used to segment healthy (green) from chlorotic (yellow) leaf areas. The spread of luminescence-tagged bacteria is monitored via light-sensitive films, which are processed in a similar manner as the leaf scans. We show that this tool is able to capture previously identified differences in susceptibility of the model plant A. thaliana to the bacterial pathogen Xanthomonas campestris pv. campestris. Moreover, we show that the ScAnalyzer pipeline provides a more detailed assessment of bacterial spread within plant leaves than previously used methods. Finally, by combining the disease symptom values with bacterial spread values from the same leaves, we show that bacterial spread precedes visual disease symptoms. CONCLUSION: Taken together, we present an automated script to monitor plant disease symptoms and microbial spread in A. thaliana leaves. The freely available software ( https://github.com/MolPlantPathology/ScAnalyzer ) has the potential to standardize the analysis of disease assays between different groups.

Portable hydrogel kit based on Michael addition reaction for (E)-2-hexenal gas detection.

Plants exhibit rapid responses to biotic and abiotic stresses by releasing a range of volatile organic compounds (VOCs). Monitoring changes in these VOCs holds the potential for the early detection of plant diseases. This study proposes a method for identifying late blight in potatoes based on the detection of (E)-2-hexenal, one of the major VOC markers released during plant infection by Phytophthora infestans. By combining the Michael addition reaction with cysteine-mediated etching of aggregation-induced emission gold nanoclusters (Au NCs), we have developed a portable hydrogel kit for on-site detection of (E)-2-hexenal. The Michael addition reaction between (E)-2-hexenal and cysteine effectively alleviates the etching of cysteine-mediated Au NCs, leading to a distinct fluorescence color change in the Au NCs, enabling a detection limit of 0.61 ppm. Utilizing the superior loading and diffusion characteristics of the three-dimensional structure of agarose hydrogel, our sensor demonstrated exceptional performance in terms of sensitivity, selectivity, reaction time, and ease of use. Moreover, quantitative measurement of (E)-2-hexenal was made easier by using ImageJ software to transform fluorescent images from the hydrogel kit into digital data. Such method was effectively used for the early detection of potato late blight. This study presents a low-cost, portable fluorescent analytical tool, offering a new avenue for on-site detection of plant diseases.