Fruit Disease Research Articles

An Improved Multi-Scale Region of Interest Deep Learning Model for Fruit Disease Classification

One of the main sources of nutrients is fruits, yet a variety of diseases appear that harmfully impact the fruit's quality and productivity. To avoid this issue, Deep Learning (DL) models have been developed, which identify and classify fruit diseases earlier. Amongst, a new Attribute registration and Shadow removal Adversarial Network with Multi-scale Region-Of-Interest (ROI)-based Deep Learning (ArSAN-MRDL) model creates more shadow-less fruit images to classify multiple diseases in a single fruit image and localizes the diseased regions precisely. In contrast, the standard convolution filters in the MRDL may lose the discrimination information for similar fruit diseases, which degrades the classification accuracy. Hence, this article designs the ArSAN with an improved MRDL (ArSAN-iMRDL) model to improve the accuracy of classifying similar diseases in the single shadow-less fruit image. Important advances made in this paper include (i) isolating the channel and spatial interdependency prediction of downsampling to prevent information loss, (ii) replacing the convolution in MRDL's Residual Blocks (ResBlocks) with a pyramid convolution with dilated convolution at many dilation rates to enrich the finite-size representation, and (iii) replacing the convolution in MRDL's Residual Blocks (ResBlocks. This iMRDL increases the robustness of classifying and localizing multiple fruit diseases. At last, extensive experiments show that the ArSAN-iMRDL model on apple, citrus, and tomato fruit images reaches 95.15%, 95.6%, and 95.43% accuracy, correspondingly, compared to the existing CNN models.

Antifungal Efficacy of the crude Alkaloid, Flavonoid, and Terpenoid of Saussurea costus (Falc.) Lipschitz Roots against Aspergillus species isolated from Rice Seeds

Background: Rice is an essential component of the diets of people all over the world, and it accounts for a sizeable amount of the calories that they consume. The world's food supply suffers huge economic losses due to fungal deterioration on rice seeds. The medicinal plant Saussurea costus contains bioactive chemicals and is well-known for its many therapeutic uses. There are a number of species of Aspergillus that are considered to be diseases in vegetables and fruits. One of these species is Aspergillus niger. The purpose of this current investigation was to investigate the impact of the crude Alkaloid, Flavonoid, and Terpenoid chemicals derived from Saussurea costus' roots on Aspergillus species Purified from Rice seeds obtained from various markets in Hillah, Iraq.Methods: In vitro, antifungal activity against Aspergillus species was achieved using the food poisoning method. Three concentrations 5, 10, and 15mg/ml of each crude compound were prepared and compared to a positive control represented by Carbendazim500g/l and a negative control represented by 10% dimethyl sulfoxide.Results: An objective of the current investigation was to manage the Aspergillus species growth identified in Rice seeds by utilizing secondary compounds derived from the roots of Saussurea costus. The study's data indicated that the extracts represented by active compounds such as Alkaloids, Flavonoids, and Terpenoids obtained from Saussurea costus roots exhibited a significant decrease in the of Aspergillus species growth, particularly at a concentration of 100mg/ml, in contrast to the negative control. This effect was equivalent to that of the positive control, Carbendazim 500g/l.Conclusion: Finally, Saussurea costus roots have shown the most efficacy in controlling Aspergillus species, particularly through the presence of Alkaloid, Flavonoid, and Terpenoid chemicals at a concentration of 100mg/ml.Keywords: Antifungal activity; Saussurea costus; Alkaloids; Flavonoids; Terpenoids

Genetic loci associated with tissue-specific resistance to powdery mildew in octoploid strawberry (Fragaria × ananassa).

Powdery mildew is one of the most problematic diseases in strawberry production. To date, few commercial strawberry cultivars are deemed to have complete resistance and as such, an extensive spray programme must be implemented to control the pathogen. Here, a large-scale field experiment was used to determine the powdery mildew resistance status of leaf and fruit tissues across a diverse panel of strawberry genotypes. This phenotypic data was used to identify Quantitative Trait Nucleotides (QTN) associated with tissue-specific powdery mildew resistance. In total, six stable QTN were found to be associated with foliar resistance, with one QTN on chromosome 7D associated with a 61% increase in resistance. In contrast to the foliage results, there were no QTN associated with fruit disease resistance and there was a high level of resistance observed on strawberry fruit, with no genetic correlation observed between fruit and foliar symptoms, indicating a tissue-specific response. Beyond the identification of genetic loci, we also demonstrate that genomic selection can lead to rapid gains in foliar resistance across genotypes, with the potential to capture >50% of the genetic foliage resistance present in the population. To date, breeding of robust powdery mildew resistance in strawberry has been impeded by the quantitative nature of natural resistance and a lack of knowledge relating to the genetic control of the trait. These results address this shortfall, through providing the community with a wealth of information that could be utilized for genomic informed breeding, implementation of which could deliver a natural resistance strategy for combatting powdery mildew.

Multisite Field Evaluation of Bacteriophages for Fire Blight Management: Incorporation of Ultraviolet Radiation Protectants and Impact on the Apple Flower Microbiome.

Fire blight, a disease of pome fruits caused by the bacterium Erwinia amylovora, has become increasingly difficult to manage after the emergence of streptomycin-resistant strains. Alternative antibiotics and copper are available; however, these chemicals have use restrictions in some countries and also can carry risks of phytotoxicity. Therefore, there is growing interest in biological-based management options, with bacteriophage (phages) showing promise, as these naturally occurring pathogens of bacteria are easy to isolate and grow. However, there are several technical challenges regarding the implementation of phage biocontrol in the field, as the viral molecules suffer from ultraviolet radiation (UVR) degradation and can die off rapidly in the absence of the host bacterium. In this work, we assessed the efficacy of Erwinia phages and a commercial phage product for blossom blight control in the field across multiple locations in the eastern United States. In these tests, disease control ranged from 0.0 to 82.7%, and addition of a UVR protectant only resulted in significantly increased disease control in 2 of 12 tests. We also analyzed microbial community population changes in response to phage application. Changes in bacterial community diversity metrics over time were not detected; however, relative abundances of target taxa were temporarily reduced after phage applications, indicating that these phage applications did not have deleterious effects on the flower microbiome. We have demonstrated that biological control of fire blight with phages is achievable, but a better understanding of phage-pathogen dynamics is required to optimize disease control efficacy.

Riboflavin alleviates the occurrence of anthracnose caused by Colletotrichum gloeosporioides in postharvest mango and the possible mechanisms involved

Colletotrichum gloeosporioides is a major pathogenic fungus that causes anthracnose in stored mangoes, and it exhibits higher pathogenicity compared to Colletotrichum acutatum. This study primarily investigates the mechanism by which riboflavin prevents mango anthracnose caused by Colletotrichum gloeosporioides. In vitro experiments demonstrated that a concentration of 1.0 mmol L−1 riboflavin exhibited a strong inhibitory effect on spore germination of Colletotrichum gloeosporioides strains isolated from different major mango-producing regions in China, surpassing the efficacy of the chemical agent pyrimethanil. Furthermore, mango fruits infected with Colletotrichum gloeosporioides and treated with 1.0 mmol L−1 riboflavin exhibited a significant reduction in disease index. The mechanism behind this is that riboflavin not only generated reactive oxygen species (ROS) but also induced the production of ROS in the fruit during the early stages of storage, directly killing Colletotrichum gloeosporioides. Additionally, riboflavin activated phenylalanine ammonia lyase (PAL) and peroxidase (POD), leading to the production of total phenols and lignin, enhancing the fruit's disease resistance. Riboflavin also increased the activity of β-1,3-glucanase (GLU) and chitinase (CHI), which can disrupt the cell wall of Colletotrichum gloeosporioides. Moreover, riboflavin enhanced the activity of superoxide dismutase (SOD) and catalase (CAT) in the fruit, reducing weight loss percentage and minimizing the degradation of total soluble solids (TSS). These findings highlight the efficacy of riboflavin in preventing and controlling mango anthracnose.

Enhancing Transfer Learning for Identifying Tomato Fruit Diseases: Investigating Parameters with Google Teachable Machine

Enhancing Transfer Learning for Identifying Tomato Fruit Diseases: Investigating Parameters with Google Teachable Machine

Pseudomonas protegens volatile organic compounds inhibited brown rot of postharvest peach fruit by repressing the pathogenesis-related genes in Monilinia fructicola

Brown rot, caused by Monilinia fructicola, is considered one of the devasting diseases of pre-harvest and post-harvest peach fruits, restricting the yield and quality of peach fruits and causing great economic losses to the peach industry every year. Presently, the management of the disease relies heavily on chemical control. In the study, we demonstrated that the volatile organic compounds (VOCs) of endophyte bacterial Pseudomonas protegens QNF1 inhibited the mycelial growth of M. fructicola by 95.35% compared to the control, thereby reducing the brown rot on postharvest fruits by 98.76%. Additionally, QNF1 VOCs severely damaged the mycelia of M. fructicola. RNA-seq analysis revealed that QNF1 VOCs significantly repressed the expressions of most of the genes related to pathogenesis (GO:0009405) and integral component of plasma membrane (GO:0005887), and further analysis revealed that QNF1 VOCs significantly altered the expressions of the genes involved in various metabolism pathways including Amino acid metabolism, Carbohydrate metabolism, and Lipid metabolism. The findings of the study indicated that QNF1 VOCs displayed substantial control efficacy by disrupting the mycelial morphology of M. fructicola, weakening its pathogenesis, and causing its metabolic disorders. The study provided a potential way and theoretical support for the management of the brown rot of peach fruits.

Application of Statistical Features in Vibro-acoustic Signals to Detect Early Browning Disorder in Pears Compared with Food Chemistry Method

- Browning in pears is one of the most serious diseases in pear fruit, which is caused by Alternaria alternata. The browning process is accompanied by changes in the chemical properties of the fruit, which affect its taste and nutritional composition. Additionally, as a typical postharvest disease, internal browning in pears can cause fruit tissue decay during storage that can reduce the shelf stability of fruit, and bring serious losses to sellers. Because it is difficult to identify the browning pears by appearance, a non-destructive detection technology is highly desirable to correctly discriminate a pear at the early stage of browning for increasing the market value. Firstly, 11 and 7 statistical features were calculated from the time-domain and frequency-domain, respectively. Then, sensitive features in time-domain set, frequency-domain set and combined feature set were selected by the distance evaluation technology, respectively. These selected features were used to train classifier based on K-nearest neighbor algorithm under different K-values. With the selected combined features adopted, the constructed KNN classifier performed the best classification performance. It allowed a high overall accuracy of 91.8 % to classify the healthy and browning pears. Also, the F1 value of 92.6 % indicated that the classifier can be successfully generalized. Therefore, the classification model established in this study is effective for identifying the early browning disorder in pear fruit.

Transcriptomic analysis – Transient expression of CYP714C2 improves resistance in pears

Postharvest pear fruit is highly susceptible to infection by pathogens, particularly by Penicillium expansum. The cytochrome P450 family plays a crucial role in the plant's defense response against pathogen invasion. However, the mechanism underlying CYP714C2 defense in pear fruit remains unclear. In this study, we investigated the molecular and physiological changes in pears after overexpressing CYP714C2 using transient expression technology and transcriptomics analysis. Our findings demonstrate that the up-regulation of CYP714C2 significantly enhances the expression of genes related to pear resistance, including CDPK, CNGC, FLS2, WRKY22, WRKY29, PYL1, ETR, ERS, EIL3, ERF1, NPR, GST, BGLU and others. Moreover, CYP714C2 overexpression altered starch and sucrose metabolism, pentose and glucuronate interconversions, glutathione metabolism, plant hormone signal transduction, MAPK signaling pathway - Plant, plant-pathogen interaction and other resistance-related pathways. Meanwhile, SOD, POD and GST activities of pear were increased. The transient expression of CYP714C2 also resulted in reduced incidence and severity of pathogen infection in pears. It was also found that CYP714C2 protein can interact with GA2ox1 which is a key protein in gibberellin metabolic pathway. As a result, the research showed that CYP714C2 played a role in enhancing resistance in pear fruit and detailed its molecular mechanism for enhancing fruit resistance. This provides a theoretical foundation for future exploration of fruit disease resistance.

Pseudomonas protegens controlled brown rot (Monilinia fructicola) on peach fruit in postharvest by suppressing fungal development and inducing plant defense-related genes

Brown rot, caused by Monilinia fructicola (Wint.) Honey is one of the world's most economically important stone fruit diseases, incurring significant losses during pre-harvest and post-harvest phases. This study demonstrated the inhibitory effect of an endophyte bacterium Pseudomonas protegens (strain QNF1), isolated from Chinese leek (Allium tuberosum) roots. The in vitro experiment revealed that P. protegens significantly suppressed M. fructicola mycelial growth by 67.11 % and 95.53 % in the potato dextrose agar (PDA) and potato dextrose broth (PDB) media compared to the control. P. protegens cell-free supernatants (CFS) also restrained M. fructicola mycelial growth by 97.95 %. In addition, the in vivo experiment displayed P. protegens reduced brown rot of peach fruit inoculated with M. fructicola plug and dipped into M. fructicola fermentation broth by 81.57 % and 85.58 %, respectively. Moreover, P. protegens improved the peach fruit quality to a certain extent. In the early stage, P. protegens significantly induced defense-related genes, including superoxide dismutase (SOD), catalase (CAT), phenylalanine ammonia-lyase (PAL), polyphenol oxidase (PPO), chitinase (CHI), and beta-1,3-glucanases (GLU). Through gas chromatography-mass spectrometry and liquid chromatography-MS analysis, 21 and 19 principal metabolites were identified in P. protegens, respectively. Among them, pyroglutamic acid, lysine, valine, tryptophan, tyrosine, and methionine were discovered by both analysis methods. The study revealed that P. protegens reduced the brown rot of peach fruit by suppressing fungal development and inducing plant defense systems. The main findings of the study proved that P. protegens represents a promising alternative for controlling the brown rot of peach fruit and other stone fruits during storage.

Extraction of Heterogeneous Features from Various Fruits and Classification of diseases using Deep Learning Techniques

The success of the farming business and the economy as a whole is directly tied to each individual farmer's output. Micro-level illnesses that emerge during fruit development may have a significant influence on output. There is an overwhelming variety of viruses, necessitating improvements in image processing and other informational resources before effective treatments can be proposed. Unparalleled approaches to segmenting, extracting characteristics, and classifying in order to identify overt conditions constitute a substantial portion of the research in this domain. However, in the event of larger and more in-depth datasets, machine learning and artificial intelligence technologies like deep learning and the like are necessary to discover illnesses that would otherwise be invisible to the human eye. Machine designers are not always sure what kinds of illnesses can be identified by mixing algorithms since there are so many possible combinations. In this paper we proposed a fruit disease detection and classification using deep convolutional neural network. The VGG-16 and VGG-19 both deep learning frameworks are utilized for detection of heterogeneous fruits. The both deep learning frameworks are archives 96.10% and 98.10% average accuracy on heterogeneous fruit dataset. In overall analysis the VGG-19 obtains higher accuracy with 200 epoch size which is higher the VGG-16 and other conventional machine learning and deep learning frameworks.

Small size CNN (CAS-CNN), and modified MobileNetV2 (CAS-MODMOBNET) to identify cashew nut and fruit diseases

Small size CNN (CAS-CNN), and modified MobileNetV2 (CAS-MODMOBNET) to identify cashew nut and fruit diseases

Comparative transcriptome and metabolome reveal the role of acidic electrolyzed oxidizing water in improving postharvest disease resistance of longan fruit

Acidic electrolyzed oxidizing water (AEOW) was applied to suppress disease development and maintain good quality of fresh fruit. However, the involvement of AEOW in improving disease resistance of fresh longan remains unknown. Here, transcriptomic and metabolic analyses were performed to compare non-treated and AEOW-treated longan during storage. The transcriptome analysis showed AEOW-induced genes associated with phenylpropanoid and flavonoid biosynthesis. The metabolome analysis found the contents of coumarin, phenolic acid, and tannin maintained higher levels in AEOW-treated longan than non-treated longan. Moreover, the weighted correlation network analysis (WGCNA) was performed to identify hub genes, and a gene-metabolite correlation network associated with AEOW-improved disease resistance in longan was constructed by the co-analysis of transcriptomics and metabolomics. These findings identified a series of important genes and metabolites involving in AEOW-induced disease resistance of longan fruit, expanding our knowledges on fruit disease resistance and quality maintenance at the transcript and metabolic levels.

Evaluation of Trichoderma spp. as a plant growth promoter and antagonist of major pulse pathogens

Trichoderma spp. is mostly used for the management of soil-borne diseases and some foliage and fruit diseases in a variety of crop plants. It can help the environment by reducing agrochemical pollution, promoting plant growth, and enhancing plant resistance in addition to preventing plant diseases. Trichoderma spp. also functions as a secure, affordable, efficient, and environmentally friendly biocontrol agent for several crop species. In the present study, we obtained different Trichoderma isolates from rhizospheric soil samples of different locations and tested them for their antagonistic activity against major pulse pathogens. Among seven isolates, three isolates, viz., Pipal TH-2, ATH-Kashipur, and Mz/AP-2 were found to be highly effective by inhibiting the growth of Fusarium udum (64.04 to 78.65%), Fusarium ciceris (77.77 to 82.12%), Sclerotium rolfsii (59.09 to 69.30%), Macrophomina phaseolina (52.42 to 62.72%) and Alternaria alternata (80.12 to 83.22%). These isolates were also tested for growth-promoting traits (PGPR) in the present study and isolates having both plant growth-promoting ability and biocontrol potentiality were selected and preserved for further studies. These isolates of Trichoderma spp. would be a crucial partner for achieving the Green Earth goal due to their contribution to the sustainable growth of agriculture.

Guava fruit disease identification based on improved convolutional neural network

Guava fruit cultivation is crucial for Asian economic development, with Indonesia producing 449,970 metric tons between 2022 and 2023. However, technology-based approaches can detect disease symptoms, enhancing production and mitigating economic losses by enhancing quality. In this paper, we introduce an accurate guava fruit disease detection (GFDI) system. It contains the generation of appropriate diseased images and the development of a novel improved convolutional neural network (improved-CNN) that is built depending on the principles of AlexNet. Also, several preprocessing techniques have been used, including data augmentation, contrast enhancement, image resizing, and dataset splitting. The proposed improved-CNN model is trained to identify three common guava fruit diseases using a dataset of 612 images. The experimental findings indicate that the proposed improved-CNN model achieve accuracy 98% for trains and 93% for tests using 0.001 learning rate, the model parameters are decreased by 50,106,831 compared with traditional AlexNet model. The findings of the investigation indicate that the deep learning model improves the accuracy and convergence rate for guava fruit disease prevention.

Automatic detection and classification of disease in citrus fruit and leaves using a customized CNN based model

India's commercial advancement and development depend heavily on agriculture. A common fruit grown in tropical settings is citrus. A professional judgment is required while analyzing an illness because different diseases have slight variations in their symptoms. In order to recognize and classify diseases in citrus fruits and leaves, a customized CNN-based approach that links CNN with LSTM was developed in this research. By using a CNN-based method, it is possible to automatically differentiate from healthier fruits and leaves and those that have diseases such fruit blight, fruit greening, fruit scab, and melanoses. In terms of performance, the proposed approach achieves 96% accuracy, 98% sensitivity, 96% Recall, and an F1-score of 92% for citrus fruit and leave identification and classification and the proposed method was compared with KNN, SVM, and CNN and concluded that the proposed CNN-based model is more accurate and effective at identifying illnesses in citrus fruits and leaves

Acidic electrolyzed-oxidizing water treatment mitigated the disease progression in Phomopsis longanae Chi-infected longans by modulating ROS and membrane lipid metabolism

Postharvest harmful pathogenic infestation leads to rapid decay in longan fruit. Compared with P. longanae-infected longans, AEOW alleviated fruit disease severity and diminished the O2-. production rate and MDA content. It also increased APX, CAT, and SOD activities, delayed the decrease in the levels of GSH and AsA, as well as the reducing power and DPPH radical scavenging ability, which resulted in a decline in membrane lipid peroxidation in P. longanae-infected longans. Additionally, AEOW reduced LOX, lipase, PI-PLC, PC-PLC, and PLD activities, maintained higher levels of PC, PI, IUFA, USFAs, and U/S, while reducing levels of PA, DAG, SFAs, and CMP. These effects alleviated membrane lipid degradation and peroxidation in P. longanae-infected longans. Consequently, AEOW effectively maintained membrane integrity via improving antioxidant capacity and suppressing membrane lipid peroxidation. This comprehensive coordination of ROS and membrane lipid metabolisms improved fruit resistance and delayed disease development in longans.

Biocontrol efficiency and potential mechanism of streptomyces distatochromogenes XT34 against postharvest anthracnose caused by colletotrichum musae on banana fruit

Banana anthracnose caused by Colletotrichum musae is a serious postharvest disease. Use of fungicides has potential adverse effects on the environment safety and human health. Application of biological control agents (BCA) is a promising strategy for managing postharvest fruit diseases. In this study, Streptomyces sp. XT34 was isolated from the banana rhizosphere soil and exhibited a strong antifungal activity against C. musae. Combining the phenotypic and whole-genomic alignment, strain XT34 was identified as Streptomyces diastatochromogenes. Strain XT34 extracts reduced the disease incidence of anthracnose and maintained the fruit quality of banana. Treatment of extracts reduced the colonization of C. musae on fruit surface. The activity inhibition of cell wall-degrading enzymes maintained the cell-wall strength of fruit. The activity increase of defense enzymes contributed to the low disease symptom. It was supported by the differentially expressed genes (DEGs) related to supramolecular fiber organization and flavonoid biosynthesis. In addition, spore germination of C. musae was effectively inhibited by extracts. The morphology of mycelia and spore become wrinkled and ruptured. The treatment of extracts increased the optical density of A260 and soluble sugar and protein contents of C. musae. The integrity of cell membrane was also destroyed, reflecting on an increase in electrical conductivity and malondialdehyde. Several metabolites were found in the genome of strain XT34 using antiSMASH. Eleven volatile compounds were identified by gas chromatography-mass spectrometer (GC-MS). Notably, strain XT34 and extracts exhibited a broad-spectrum antifungal activity against eight phytopathogenic fungi. Hence, S. diastatochromogenes XT34 provides a potential BCA to control banana anthracnose.

Effect of Chitosan-Riboflavin Bioconjugate on Green Mold Caused by Penicillium digitatum in Lemon Fruit.

Penicillium digitatum is the causal agent of green mold, a primary postharvest disease of citrus fruits. This study evaluated the efficacy of a novel photoactive chitosan-riboflavin bioconjugate (CH-RF) to control green mold in vitro and in lemon fruit. The results showed total inhibition of P. digitatum growth on APDA supplemented with CH-RF at 0.5% (w/v) and a significant reduction of 84.8% at 0.25% (w/v). Lemons treated with CH-RF and kept under controlled conditions (20 °C and 90-95% relative humidity) exhibited a noteworthy reduction in green mold incidence four days post-inoculation. Notably, these effects persisted, with all treatments remaining significantly distinct from the control group until day 14. Furthermore, CH-RF showed high control of green mold in lemons after 20 days of cold storage (5 ± 1 °C). The disease incidence five days after cold storage indicated significant differences from the values observed in the control. Most CH-RF treatments showed enhanced control of green mold when riboflavin was activated by white-light exposure. These findings suggest that this novel fungicide could be a viable alternative to conventional synthetic fungicides, allowing more sustainable management of lemon fruit diseases.

RETRACTED: Optimizing precision agriculture: Bayesian-enhanced papaya (Carica papaya L.) fruit disease classification via cubic SVM and ResNet-101 deep features

This article has been retracted. A retraction notice can be found at https://doi.org/10.3233/JIFS-219433.