Plant Methods最新文献

{"title":"Benefiting from the past: establishing in vitro culture of European beech (Fagus sylvatica L.) from provenance trial trees and seedlings.","authors":"Virginia Zahn, Alexander Fendel, Alice-Jeannine Sievers, Matthias Fladung, Tobias Bruegmann","doi":"10.1186/s13007-025-01350-3","DOIUrl":"10.1186/s13007-025-01350-3","url":null,"abstract":"<p><strong>Background: </strong>European beech (Fagus sylvatica L.) is distributed across diverse climate conditions throughout Europe. Local adaptations, such as drought tolerance, could become crucial for maintaining beech populations facing climate change. In vitro culture offers a promising tool for preserving and propagating valuable genotypes and provides a basis for biotechnological research, although establishing and propagating recalcitrant beech in vitro is difficult. To the best of our knowledge, this study is the first to use beeches from a provenance trial to establish in vitro cultures, aiming to capture a wide genetic spectrum and investigate provenance-specific suitability for in vitro cultivation. In addition, a high-throughput method using seedlings has been developed to increase the success of establishing in vitro cultures of a provenance.</p><p><strong>Results: </strong>Actively growing shoots from 22 field-grown provenances were obtained for in vitro establishment. After 12 weeks, shoot formation on shoot tips and nodal segments was induced in 13 provenances (57%), with success rates ranging from 3 to 80%, significantly influenced by the provenance and sampling date of the branches. Combining one harvest each in February and May resulted in the highest shoot formation rate (18%). However, after two years, stable micropropagation was achieved for a single genotype. In the second approach, whole shoots or shoot tips from seedlings were used for in vitro establishment, achieving shoot formation rates between 38 and 94%. Bacterial contamination during establishment was controlled through antibiotic application. Using culture medium without phytohormones improved initial leaf flush on shoot tips within the first 8 weeks of in vitro culture. Phytohormone-supplemented media were needed for shoot multiplication and prolonged in vitro culture. Cultures of 25 genotypes were maintained for up to two years. The viability of in vitro shoots was maintained by supplementing the medium with FeNaEDTA, MgSO₄, and glucose. Some genotypes showed enhanced performance on sugar-free media with increased light intensity, which reduced bacterial outgrowth.</p><p><strong>Conclusion: </strong>With the technical approaches presented here, we provide starting points for the establishment of beech cultures from various types of starting material, as well as for further method improvement for establishment and long-term cultivation.</p>","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":"21 1","pages":"31"},"PeriodicalIF":4.7,"publicationDate":"2025-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11887157/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143586674","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Swin-Unet++: a study on phenotypic parameter analysis of cabbage seedling roots.","authors":"Hongda Li, Yue Zhao, Zeyang Bi, Peng Hao, Huarui Wu, Chunjiang Zhao","doi":"10.1186/s13007-025-01340-5","DOIUrl":"10.1186/s13007-025-01340-5","url":null,"abstract":"<p><strong>Background: </strong>As an important economic crop, the growth status of the root system of cabbage directly affects its overall health and yield. To monitor the root growth status of cabbage seedlings during their growth period, this study proposes a new network architecture called Swin-Unet++. This architecture integrates the Swin-Transformer module and residual networks and uses attention mechanisms to replace traditional convolution operations for feature extraction. It also adopts the residual concept to fuse contextual information from different levels, addressing the issue of insufficient feature extraction for the thin and mesh-like roots of cabbage seedlings.</p><p><strong>Results: </strong>Compared with other backbone high-precision semantic segmentation networks, SwinUnet + + achieves superior segmentation results. The results show that the accuracy of Swin-Unet + + in root system segmentation tasks reached as high as 98.19%, with a model parameter of 60 M and an average response time of 29.5 ms. Compared with the classic Unet network, the mIoU increased by 1.08%, verifying that the Swin-Transformer and residual networks can accurately extract the fine-grained features of roots. Furthermore, when images after different semantic segmentations are compared to locate the root position through contours, Swin-Unet + + has the best positioning effect. On the basis of the root pixels obtained from semantic segmentation, the calculated maximum root length, extension width, and root thickness are compared with actual measurements. The resulting goodness of fit R² values are 94.82%, 94.43%, and 86.45%, respectively. Verifying the effectiveness of this network in extracting the phenotypic traits of cabbage seedling roots.</p><p><strong>Conclusions: </strong>The Swin-Unet + + framework developed in this study provides a new technique for the monitoring and analysis of cabbage root systems, ultimately leading to the development of an automated analysis platform that offers technical support for intelligent agriculture and efficient planting practices.</p>","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":"21 1","pages":"30"},"PeriodicalIF":4.7,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11874442/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143542783","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Rootrainertrons: a novel root phenotyping method used to identify genotypic variation in lettuce rooting.","authors":"Cara Wharton, Andrew Beacham, Miriam L Gifford, James Monaghan","doi":"10.1186/s13007-025-01348-x","DOIUrl":"10.1186/s13007-025-01348-x","url":null,"abstract":"<p><strong>Background: </strong>There is much interest in how roots can be manipulated to improve crop performance in a changing climate, yet root research is made difficult by the challenges of visualising the root system accurately, particularly when grown in natural environments such as soil. Scientists often resort to use of agar- or paper-based assays, which provide unnatural growing media, with the roots often exposed to light. Alternatives include rhizotrons or x-ray computed tomography, which require specialist and expensive pieces of equipment, not accessible to those in developing countries most affected by climate change. Another option is excavation of roots, however, this is time-consuming and near impossible to achieve without some degree of root damage. Therefore, new, affordable but reliable alternatives for root phenotyping are necessary.</p><p><strong>Results: </strong>This study reports a novel, low cost, Rootrainer-based system for root phenotyping. Rootrainers were tilted at an angle, in a rhizotron-like set-up. This encouraged root growth on the bottom plane of the Rootrainers, and since Rootrainers open (in a book-like fashion), root growth can be easily observed. This new technique was successfully used to uncover significant genotypic variance in rooting traits for a selection of lettuce (L. sativa) varieties across multiple timepoints.</p><p><strong>Conclusion: </strong>This novel Rootrainertron method has many advantages over existing methods of phenotyping seedling roots. Rootrainers are cheap, and readily available from garden centres, unlike rhizotrons which are expensive and only available from specialist suppliers. Rootrainers allow the roots to grow in substrate medium, providing a significant advantage over agar and paper assays.This approach offers an affordable and relevant root phenotyping option and makes root phenotyping more accessible and applicable for researchers.</p>","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":"21 1","pages":"29"},"PeriodicalIF":4.7,"publicationDate":"2025-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11872326/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143537552","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Vapor pressure deficit control and mechanical vibration techniques to induce self-pollination in strawberry flowers.","authors":"Hyein Lee, Meiyan Cui, Byungkwan Lee, Jeesang Myung, Jaewook Shin, Changhoo Chun","doi":"10.1186/s13007-025-01343-2","DOIUrl":"10.1186/s13007-025-01343-2","url":null,"abstract":"<p><strong>Background: </strong>Pollination strategies to supplement or replace insect pollinators are needed to produce marketable strawberry fruits in indoor vertical farms. To ensure the self-pollination of strawberry flowers, anther dehiscence, and pollen attachment were investigated under different vapor pressure deficit (VPD) conditions and external mechanical wave vibrations.</p><p><strong>Results: </strong>The proportion of dehisced anthers was examined under VPDs of 2.06, 1.58, and 0.33 kPa, and the projected area of pollen clumps was assessed under VPDs of 2.06 and 0.33 kPa. After exposing flowers to a VPD of 2.06 kPa, vibrations with various frequency (Hz) and root mean square acceleration (m s^-2) combinations were used to evaluate pollination effectiveness. The anthers underwent complete dehiscence at VPDs of 2.06, 1.58, and 0.33 kPa. The pollen clump ejection index was highest at a VPD of 2.06 kPa. Pollen clump detachment was effective at 800 Hz with 40 m s^-2, while pollen attachment to the stigma was most effective at 100 Hz with 30 and 40 m s^-2.</p><p><strong>Conclusions: </strong>These findings demonstrate that high VPD promotes anther dehiscence timing and facilitates pollen clump formation, while specific vibration frequencies with high acceleration optimize pollen detachment and stigma attachment, offering an effective strategy for controlled strawberry pollination in vertical farming.</p>","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":"21 1","pages":"28"},"PeriodicalIF":4.7,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11863501/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143503398","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A method for phenotyping lettuce volume and structure from 3D images.","authors":"Victor Bloch, Alexey Shapiguzov, Titta Kotilainen, Matti Pastell","doi":"10.1186/s13007-025-01347-y","DOIUrl":"10.1186/s13007-025-01347-y","url":null,"abstract":"<p><p>Monitoring plant growth is crucial for effective crop management, and using color and depth (RGBD) cameras to model lettuce has emerged as one of the most convenient and non-invasive methods. In recent years, deep learning techniques, particularly neural networks, have become popular for estimating lettuce fresh weight. However, these models are typically specific to particular datasets, lack domain adaptation, and are often limited by the availability of open-access datasets. In this study, we propose a method based on plant geometric features for estimating the rosette structure and volume of lettuce. This new approach was compared to existing methods that reconstruct surfaces from point clouds, such as Ball Pivoting and Alpha Shapes. The proposed method creates a tight hull around the plant's point cloud, preserving high detail of the rosette structure while filling in surface holes in areas not visible to 3D cameras. Using a linear regression model, we estimated fresh weight for this dataset, achieving a root mean square error (RMSE) of 18.2 g when using only the estimated plant volume, and 17.3 g when both volume and geometric features were included. Additionally, we introduced new geometric features that characterize leaf density, which could be useful for breeding applications. A dataset of 402 point clouds of lettuce plants, captured before harvest, was compiled using one top-down and three side-view 3D cameras.</p>","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":"21 1","pages":"27"},"PeriodicalIF":4.7,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11852549/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143493192","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Estimation of chlorophyll content in rice canopy leaves using 3D radiative transfer modeling and unmanned aerial hyperspectral images.","authors":"Honggang Zhang, Dan Zhao, Zhonghui Guo, Sien Guo, Quchi Bai, Huini Cao, Shuai Feng, Fenghua Yu, Tongyu Xu","doi":"10.1186/s13007-025-01346-z","DOIUrl":"10.1186/s13007-025-01346-z","url":null,"abstract":"<p><strong>Background: </strong>The chlorophyll content has a strong influence on plant photosynthesis and crop growth and is a key factor for understanding the functioning of farming systems. Therefore, the accurate estimation of chlorophyll content (Cab) is important in precision agriculture. In this study, the three-dimensional radiative transfer model (3DRTM) was used to calculate the radiative transfer and simulate the canopy hyperspectral image of a rice field. Then, a physically based joint inversion model was developed using an iterative optimization approach with penalty function and a priori information constraints to estimate chlorophyll content efficiently and accurately from the hyperspectral curve of a rice canopy.</p><p><strong>Results: </strong>The inversion model demonstrates that the sparrow search algorithm (SSA) can estimate rice Cab, providing relatively satisfactory Cab estimation outcomes. In addition, the inversion of the SSA method with or without carotenoids content (Car) constraints was compared, and compared to the inversion of Cab without Car constraints [coefficient of determination (R²) = 0.690, root mean square error (RMSE) = 7.677 µg/cm²)], the SSA with constraints was more accurate (R² = 0.812, RMSE = 5.413 µg/cm²).</p><p><strong>Conclusions: </strong>The Large-Scale remote sensing data and image simulation framework over heterogeneous 3D scenes (LESS) exhibited higher accuracy in estimating the rice Cab compared to the 1DRTM PROSAIL model, which is constituted by coupling the Leaf Optical Properties Spectra (PROSPECT) model and the Scattering by Arbitrarily Inclined Leaves (SAIL) model. The 3DRTM is conducive to precisely estimating Cab from the hyperspectral data of the rice canopy, thereby holding great potential for precise nutrient management in rice cultivation.</p>","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":"21 1","pages":"26"},"PeriodicalIF":4.7,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11849381/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143493194","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Exploring the potential of microscopic hyperspectral, Raman, and LIBS for nondestructive quality assessment of diverse rice samples.","authors":"Jing Guo, Sijia Jiang, Bingjie Lu, Wei Zhang, Yinyin Zhang, Xiao Hu, Wanneng Yang, Hui Feng, Liang Xu","doi":"10.1186/s13007-025-01345-0","DOIUrl":"10.1186/s13007-025-01345-0","url":null,"abstract":"<p><p>The enhancement of rice quality stands as a pivotal focus in crop breeding research, with spectral analysis-based non-destructive quality assessment emerging as a widely adopted tool in agriculture. A prevalent trend in this field prioritizes the assessment of effectiveness of individual spectral technologies while overlooking the influence of sample type on spectral quality testing outcomes. Thus, the present study employed Microscopic Hyperspectral Imaging, Raman, and Laser-Induced Breakdown Spectroscopy (LIBS) to acquire spectral data from paddy rice, brown rice, polished rice, and rice flour. The data were then modeled and analyzed with respect to the amylopectin and protein contents of the rice samples via regression methods. Correlation analysis revealed varying degrees of correlation, both positive and negative, among the three spectral techniques and the analytes of interest. LIBS and Raman spectroscopy demonstrated stronger correlations with the analytes compared to microscopic hyperspectral imaging. Based on the selected correlation variables, feature screening and regression modeling were conducted. The modeling results indicated that microscopic hyperspectral data modeling yielded the lowest coefficient of determination of R² = 0.2, followed by Raman data modeling result was higher than it, which was about 0.5. The modeling effect of polished rice is the best. LIBS data modeling performed best, with a coefficient of determination of 0.6. The influence of different sample types on the modeling results was less than that of Raman spectroscopy, and modeling results of grains were better. The feature matching analysis of Raman and libs spectroscopy techniques showed that there were spectral variables that could match amylopectin and protein in the features obtained by multiple modeling statistics, but some modeling variables failed to match. LIBS matched more variables than Raman. These findings provide valuable insights into the application effectiveness of different spectral techniques in detecting rice contents across diverse sample types.</p>","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":"21 1","pages":"25"},"PeriodicalIF":4.7,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11844132/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143468833","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Production of HSVd- and PPV-free apricot cultivars by in vitro thermotherapy followed by meristem culture.","authors":"C Pérez-Caselles, L Burgos, E Yelo, L Faize, N Alburquerque","doi":"10.1186/s13007-025-01344-1","DOIUrl":"10.1186/s13007-025-01344-1","url":null,"abstract":"<p><strong>Background: </strong>The production of virus-free apricots (Prunus armeniaca L.) is essential for controlling viral diseases, exchanging breeding materials without the risk of spreading new diseases, and preserving plant germplasm. Plum pox virus (PPV) is the most devastating disease of the Prunus genus and Hop stunt viroid (HSVd) is prevalent in most apricot-growing regions. It was evaluated whether thermotherapy, etiolation, or a combination of both followed by meristem culture could effectively eliminate PPV and HSVd from 'Canino' and 'Mirlo Rojo' apricot cultivars in vitro.</p><p><strong>Results: </strong>In the thermotherapy treatments, shoots were exposed to 38ºC and 32ºC, alternating every four hours, for 30, 35, 40, and 45 days. Before this, shoots were acclimated to heat for one day at 28ºC and two days at 30ºC. Etiolation experiments consisted of eight weeks of culture in dark conditions. A combination of 45 days of thermotherapy, as described previously, and etiolation was also performed. At the end of each treatment, 1.5 mm meristems were cultured, and developed as potential independent pathogen-free lines. The presence or absence of pathogens was analysed by RT-PCR. The 45 days of thermotherapy and the combined thermotherapy and etiolation treatments resulted in the highest percentages of PPV-free plants (66.7 and 75.0%, respectively). At least 40 days of thermotherapy were required to obtain HSVd-free plants, although the best efficiency was achieved at 45 days (22.7%).</p><p><strong>Conclusions: </strong>In this study, we have developed an effective in vitro thermotherapy protocol that eliminates PPV and HSVd from apricot cultivars. This is the first report where a thermotherapy protocol eliminates HSVd in Prunus species.</p>","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":"21 1","pages":"23"},"PeriodicalIF":4.7,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11843746/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143468836","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Two-fold red excess (TREx): a simple and novel digital color index that enables non-invasive real-time monitoring of green-leaved as well as anthocyanin-rich crops.","authors":"Avinash Agarwal, Filipe de Jesus Colwell, Viviana Andrea Correa Galvis, Tom R Hill, Neil Boonham, Ankush Prashar","doi":"10.1186/s13007-025-01339-y","DOIUrl":"10.1186/s13007-025-01339-y","url":null,"abstract":"<p><strong>Background: </strong>Digital color indices provide a reliable means for assessing plant status by enabling real-time estimation of chlorophyll (Chl) content, and are thus adopted widely for crop monitoring. However, as all prevalent leaf color indices used for this purpose have been developed using green-leaved plants, they do not perform reliably for anthocyanin (Anth)-rich red-leaved varieties. Hence, the present study investigates digital color indices for six types of leafy vegetables with different levels of Anth to identify congruent trends that could be implemented universally for non-invasive crop monitoring irrespective of species and leaf Anth content. For this, datasets from three digital color spaces, viz., RGB (Red, Green, Blue), HSV (Hue, Saturation, Value), and L*a*b* (Lightness, Redness-greenness, Yellowness-blueness), as well as various derived plant color indices were compared with Anth/Chl ratio and SPAD Chl meter readings of n = 320 leaf samples.</p><p><strong>Results: </strong>Logarithmic decline of G/R, G-minus-R, and Augmented Green-Red Index (AGRI) with increasing Anth/Chl ratio (R² > 0.8) revealed that relative Anth content affected digital color profile markedly by shifting the greenness-redness balance until the Anth/Chl ratio reached a certain threshold. Further, while most digital color features and indices presented abrupt shifts between Anth-rich and green-leaved samples, the proposed color index Two-fold Red Excess (TREx) did not exhibit any deviation due to leaf Anth content and showed better correlation with SPAD readings (R² = 0.855) than all other color features and vegetation indices.</p><p><strong>Conclusion: </strong>The present study provides the first in-depth assessment of variations in RGB-based digital color indices due to high leaf Anth contents, and uses the data for Anth-rich as well as green-leaved crops belonging to different species to formulate a universal digital color index TREx that can be used as a reliable alternative to handheld Chl meters for rapid high-throughput monitoring of green-leaved as well as red-leaved crops.</p>","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":"21 1","pages":"24"},"PeriodicalIF":4.7,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11843946/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143468140","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automated pipeline for leaf spot severity scoring in peanuts using segmentation neural networks.","authors":"Joshua Larsen, Jeffrey Dunne, Robert Austin, Cassondra Newman, Michael Kudenov","doi":"10.1186/s13007-024-01316-x","DOIUrl":"10.1186/s13007-024-01316-x","url":null,"abstract":"<p><strong>Background: </strong>Late and early leaf spot in peanuts is a foliar disease contributing to a significant amount of lost yield globally. Peanut breeding programs frequently focus on developing disease-resistant peanut genotypes. However, existing phenotyping protocols employ subjective rating scales, performed by human raters, who determine the severity of leaf spot infection. The objective of this study was to develop an objective end-to-end pipeline that can serve to replace an expert human scorer in the field. This was accomplished using image capture protocols and segmentation neural networks that extracted lesion areas from plot-level images to determine an appropriate rating for infection severity.</p><p><strong>Results: </strong>The pipeline incorporated a neural network that accurately determined the infected leaf surface area and identified dead leaves from plot-level cellphone imagery. Image processing algorithms then convert these labels into quality metrics that can efficiently score these images based on infected versus non-infected area. The pipeline was evaluated using field data from plots with varying leaf spot severity, creating a dataset of thousands of images that spanned conventional visual severity scores ranging from 1-9. These predictions were based on the amount of infected leaf area and the presence of defoliated leaves in the surrounding area. We were able to demonstrate automated scoring, as compared to expert visual scoring, with a root mean square error of 0.996 visual scores, on individual images (one image per plot), and 0.800 visual scores when three images were captured of each plot.</p><p><strong>Conclusion: </strong>Results indicated that the model and image processing pipeline can serve as an alternative to human scoring. Eliminating human subjectivity for the scoring protocols will allow non-experts to collect scores and may enable drone-based data collection. This could reduce the time needed to obtain new lines or identify new genes responsible for leaf spot resistance in peanut.</p>","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":"21 1","pages":"22"},"PeriodicalIF":4.7,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11841321/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143468831","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}