Plant Methods最新文献

{"title":"Accelerating eucalypt clone selection pipeline via cloned progeny trials and molecular data.","authors":"Thiago Romanos Benatti, Filipe Manoel Ferreira, Rodolfo Manoel Lemes da Costa, Mario Luiz Teixeira de Moraes, Aurélio Mendes Aguiar, Donizete da Costa Dias, José Wilacildo de Matos, Aline Cristina Miranda Fernandes, Mateus Chagas Andrade, Leandro de Siqueira, Itaraju Junior Baracuhy Brum, André Vieira do Nascimento, Yuri Tani Utsunomiya, José Fernando Garcia, Evandro Vagner Tambarussi","doi":"10.1186/s13007-025-01342-3","DOIUrl":"10.1186/s13007-025-01342-3","url":null,"abstract":"<p><p>The high productivity of Eucalyptus spp. forest plantations is mainly due to advances in silvicultural techniques and genetic improvement associated with the potential that many species of the genus have for vegetative propagation. However, long reproduction cycles for forest species pose significant challenges for genetic progress via traditional breeding programs. Furthermore, there is often poor correlation between individual (seedling) performance in initial (progeny trials) and final (clonal trials) stages of the breeding program. In this scenario, cloned progeny trials (CPT) offer an alternative to accelerate the eucalypt clone selection pipeline, combining progeny and clonal trials in a single experiment. CPT has the potential to speed up the evaluation process and increase its efficiency by developing new commercial genotypes that were tested as clones from the initial stage of the breeding program. Thus, this study aims to assess the potential of CPT to accelerate eucalypt clone selection programs by estimating the genetic parameters, analyzing responses to selection, and predicting the adequate number of ramets to be used in CPT of Eucalyptus urophylla x Eucalyptus grandis. The results show that when the number of ramets per progeny was decreased from five to one there was a reduction in the estimates of broad-sense heritability and accuracy. However, three ramets/progeny can be used without significant reductions in these estimates. CPT accelerates clonal selection by combining progeny and clonal trial methodologies, enabling an evaluation of performance as both progeny and clone. This capacity is very important for vegetatively propagated crop species such as Eucalyptus. Integrating CPT with SNP markers can offer an alternative to shorten the tree clone selection pipeline, better estimate and decompose the genetic variance components, and improve the correlation between initial and final performance for selected genotypes. This study confirms the potential of CPT to improve selection processes and accelerate genetic gains in the eucalypt clone selection pipeline.</p>","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":"21 1","pages":"19"},"PeriodicalIF":4.7,"publicationDate":"2025-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11827336/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143426040","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":"Robust CRW crops leaf disease detection and classification in agriculture using hybrid deep learning models.","authors":"B V Baiju, Nancy Kirupanithi, Saravanan Srinivasan, Anjali Kapoor, Sandeep Kumar Mathivanan, Mohd Asif Shah","doi":"10.1186/s13007-025-01332-5","DOIUrl":"10.1186/s13007-025-01332-5","url":null,"abstract":"<p><p>The problem of plant diseases is huge as it affects the crop quality and leads to reduced crop production. Crop-Convolutional neural network (CNN) depiction is that several scholars have used the approaches of machine learning (ML) and deep learning (DL) techniques and have configured their models to specific crops to diagnose plant diseases. In this logic, it is unjustifiable to apply crop-specific models as farmers are resource-poor and possess a low digital literacy level. This study presents a Slender-CNN model of plant disease detection in corn (C), rice (R) and wheat (W) crops. The designed architecture incorporates parallel convolution layers of different dimensions in order to localize the lesions with multiple scales accurately. The experimentation results show that the designed network achieves the accuracy of 88.54% as well as overcomes several benchmark CNN models: VGG19, EfficientNetb6, ResNeXt, DenseNet201, AlexNet, YOLOv5 and MobileNetV3. In addition, the validated model demonstrates its effectiveness as a multi-purpose device by correctly categorizing the healthy and the infected class of individual types of crops, providing 99.81%, 87.11%, and 98.45% accuracy for CRW crops, respectively. Furthermore, considering the best performance values achieved and compactness of the proposed model, it can be employed for on-farm agricultural diseased crops identification finding applications even in resource-limited settings.</p>","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":"21 1","pages":"18"},"PeriodicalIF":4.7,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11827293/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143414857","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":"SHP Buddy: a QGIS plugin for generating shapefiles to support remote sensing in plant breeding and agronomic experiments.","authors":"Nathaniel Burner, Donna K Harris, Zenglu Li","doi":"10.1186/s13007-025-01336-1","DOIUrl":"10.1186/s13007-025-01336-1","url":null,"abstract":"<p><strong>Background: </strong>Shapefiles are a geospatial vector data format used to indicate geographic features in geographic information systems (GIS) software. Shapefiles are used in high-throughput phenotyping plant breeding and agronomic studies to identify plots from aerial imagery and extract remote sensing data. However, the process of manually creating shapefiles is tedious and error prone. Current options that assist in shapefile generation suffer from issues such as installation processes that require a degree of programming knowledge or inefficient methods for incorporating plot-level information from field books. In this study, we have developed a program called 'SHP Buddy', a QGIS plugin that provides accessible and intuitive functions that quickly generate shapefiles for common experimental layouts used in agricultural research.</p><p><strong>Results: </strong>SHP Buddy is a free and open source QGIS plugin that is easily downloaded directly from the QGIS plugin repository. It provides options for generating serpentine replicated and unreplicated experimental layouts. Further, SHP Buddy is the first of its type to provide an intuitive method for removing non-experimental plots, such as non-experimental \"fill\" plots at the end of experiments or plots in irrigation wheel tracks. Plot information is easily incorporated by uploading a field book CSV file that contains a column of matching plot numbers. Lastly, plot dimensions can be modified to produce more precise regions of interest.</p><p><strong>Conclusions: </strong>SHP Buddy substantially reduces the time and increases the accuracy of shapefile generation. This results in reliable shapefiles that improve record keeping and the quality of high-throughput phenotyping data extracted. By working natively in QGIS, SHP Buddy provides an efficient solution to shapefile generation while maintaining a low learning curve.</p>","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":"21 1","pages":"17"},"PeriodicalIF":4.7,"publicationDate":"2025-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11823009/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143409802","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":"Deep-learning-ready RGB-depth images of seedling development.","authors":"Félix Mercier, Geoffroy Couasnet, Angelina El Ghaziri, Nizar Bouhlel, Alain Sarniguet, Muriel Marchi, Matthieu Barret, David Rousseau","doi":"10.1186/s13007-025-01334-3","DOIUrl":"10.1186/s13007-025-01334-3","url":null,"abstract":"<p><p>In the era of machine learning-driven plant imaging, the production of annotated datasets is a very important contribution. In this data paper, a unique annotated dataset of seedling emergence kinetics is proposed. It is composed of almost 70,000 RGB-depth frames and more than 700,000 plant annotations. The dataset is shown valuable for training deep learning models and performing high-throughput phenotyping by imaging. The ability of such models to generalize to several species and outperform the state-of-the-art owing to the delivered dataset is demonstrated. We also discuss how this dataset raises new questions in plant phenotyping.</p>","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":"21 1","pages":"16"},"PeriodicalIF":4.7,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11817399/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143399635","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":"3D-CNN detection of systemic symptoms induced by different Potexvirus infections in four Nicotiana benthamiana genotypes using leaf hyperspectral imaging.","authors":"Rizos-Theodoros Chadoulis, Ioannis Livieratos, Ioannis Manakos, Theodore Spanos, Zeinab Marouni, Christos Kalogeropoulos, Constantine Kotropoulos","doi":"10.1186/s13007-025-01337-0","DOIUrl":"10.1186/s13007-025-01337-0","url":null,"abstract":"<p><strong>Purpose: </strong>Hyperspectral imaging combined with machine learning offers a promising, cost-effective alternative to invasive chemical analysis for early plant disease detection. In this study, the use of 3D Convolutional Neural Networks (3D-CNNs) was explored to detect presymptomatic viral infections in the model plant Nicotiana benthamiana L. and assess the generalization of these models across different plant genotypes.</p><p><strong>Methods: </strong>Four genotypes of Nicotiana benthamiana L. (wild-type, DCL2/4, AGO2, and NahG) were inoculated with different potexviruses (PepMV mild or severe strain, PVX, BaMV). Viral infection was verified via northern blot analysis at 5 and 10 days post inoculation (DPI). Hyperspectral images were captured over 10 days following inoculation, focusing on the top 3 leaves where symptoms typically appear. The dataset was carefully processed to remove errors, and raster masks were generated to isolate only the leaf pixels. The Extremely Randomized Trees algorithm was used for Effective Wavelength selection, and a novel 3D-CNN architecture was developed to classify <math><mrow><mn>16</mn> <mo>×</mo> <mn>16</mn> <mo>×</mo> <mn>16</mn></mrow> </math> nonoverlapping cubes extracted from the unmasked leaf surfaces. The aim was to classify each cube into healthy or diseased for each of the four viruses at different time points.</p><p><strong>Results: </strong>Accuracies of <math><mrow><mn>0.78</mn></mrow> </math> - <math><mrow><mn>0.87</mn></mrow> </math> were achieved for AGO2 mutants at the cube level, and overall plant-level accuracies of <math><mrow><mn>0.68</mn></mrow> </math> - <math><mrow><mn>0.89</mn></mrow> </math> . The model's generalization capabilities were tested across other genotypes, yielding accuracies of up to <math><mrow><mn>0.75</mn></mrow> </math> for DCL2/4, <math><mrow><mn>0.83</mn></mrow> </math> for NahG, and <math><mrow><mn>0.78</mn></mrow> </math> for the wild-type. The timing of disease detection was also assessed, finding that accuracies approached 0.8 as early as <math><mrow><mn>6</mn></mrow> </math> - <math><mrow><mn>8</mn></mrow> </math>  DPI depending on the virus. The results were validated against northern blot analyses and benchmarked against another state-of-the-art methodology for Nicotiana benthamiana viral infections, achieving superior overall classification accuracies.</p><p><strong>Conclusion: </strong>The proposed patch-based method demonstrated key advantages: (a) exploiting both spectral and textural information, (b) deriving a large training dataset from few hyperspectral images, (c) providing localized classification explainability within leaf regions, and (d) achieving high accuracy for early detection of viral infections.</p>","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":"21 1","pages":"15"},"PeriodicalIF":4.7,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11809018/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143391580","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":"MtCro: multi-task deep learning framework improves multi-trait genomic prediction of crops.","authors":"Dian Chao, Hao Wang, Fengqiang Wan, Shen Yan, Wei Fang, Yang Yang","doi":"10.1186/s13007-024-01321-0","DOIUrl":"10.1186/s13007-024-01321-0","url":null,"abstract":"<p><p>Genomic Selection (GS) predicts traits using genome-wide markers, speeding up genetic progress and enhancing breeding efficiency. Recent emphasis has been placed on deep learning models to enhance prediction accuracy. However, current deep learning models focus on learning specific phenotypes for the given task, overlooking the inter-correlations among different phenotypes. In response, we introduce MtCro, a multi-task learning approach that simultaneously captures diverse plant phenotypes within a shared parameter space. Extensive experiments reveal that MtCro outperforms mainstream models, including DNNGP and SoyDNGP, with performance gains of 1-9% on the Wheat2000 dataset, 1-8% on Wheat599, and 1-3% on Maize8652. Furthermore, comparative analysis shows a consistent 2-3% improvement in multi-phenotype predictions, emphasizing the impact of inter-phenotype correlations on accuracy. By leveraging multi-task learning, MtCro efficiently captures diverse plant phenotypes, enhancing both model training efficiency and prediction accuracy, ultimately accelerating the progress of plant genetic breeding. Our code is available on https://github.com/chaodian12/mtcro .</p>","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":"21 1","pages":"12"},"PeriodicalIF":4.7,"publicationDate":"2025-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11796200/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143256347","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":"In vitro micropropagation protocols for two endangered Dianthus species - via in vitro culture for conservation and recultivation purposes.","authors":"Dóra Farkas, Judit Csabai, Angéla Kolesnyk, Pál Szarvas, Judit Dobránszki","doi":"10.1186/s13007-025-01335-2","DOIUrl":"10.1186/s13007-025-01335-2","url":null,"abstract":"<p><strong>Background: </strong>D. giganteiformis subsp. pontederae and D. superbus subsp. superbus are protected or critically endangered species in several European regions; therefore, developing an efficient in vitro micropropagation protocol is essential for germplasm conservation and recultivation purposes.</p><p><strong>Results: </strong>After germination, one-nodal segments of both species were transferred onto several MS media supplemented with 3% sucrose and different types of cytokinins (at a concentration of 4.5 µM) alongside 0.54 µM 1-naphthaleneacetic acid (NAA) for the multiplication phase for 3 weeks. The shoot clusters were subsequently transferred onto elongation medium (plant growth regulator-free MS medium) for 3 weeks. Individual shoots separated from the shoot clusters were cultured on MS medium supplemented with 0.54 µM NAA and 2% sucrose for 3 weeks for rooting. Taking into account the effects and after-effects of cytokinins, we found that the most suitable cytokinin for D. giganteiformis subsp. pontederae was N-(2-isopentenyl)-adenine (2-iP), while for D. superbus subsp. superbus it was meta-topolin (mT).</p><p><strong>Conclusions: </strong>In vitro micropropagation methods were developed for two endangered Dianthus species (D. giganteiformis subsp. pontederae and D. superbus subsp. superbus) by determining the optimal type of cytokinin to be used during the multiplication phase. The protocols are designed to produce large quantities of propagation material for recultivation, educational, and research purposes within three months.</p>","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":"21 1","pages":"13"},"PeriodicalIF":4.7,"publicationDate":"2025-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11796268/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143256344","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":"Rapid detection of Tulipalin A with SESI-Orbitrap MS: an exploration across spring flowers.","authors":"An N T Phan, Roy Eerlings, Hendrik G Mengers, Lars M Blank","doi":"10.1186/s13007-025-01331-6","DOIUrl":"10.1186/s13007-025-01331-6","url":null,"abstract":"<p><strong>Background: </strong>Allergic contact dermatitis and chronic actinic dermatitis are frequently observed among florists and gardeners due to exposure to potentially allergenic plants and plant products. Tulipalin A, an alpha-methylene-gamma-butyrolactone, is a common allergen synthesized by Tulipa genera, but its natural occurrence across Plantae remains unexplored.</p><p><strong>Results: </strong>Here, we demonstrated the secondary electrospray ionization coupled Orbitrap mass spectrometry (SESI-Orbitrap MS) methodology for quantifying tulipalin A release from plants upon injury. By outlining temperature treatment, homogenization strategies and plant organ distribution, we show that processing flower samples stored at room temperature using a garlic press yielded the highest tulipalin A release upon injury. Via real-time monitoring, tulipalin A release was demonstrated to occur immediately upon homogenization. Next, the biosynthesis of tulipalin A across spring flowers was landscaped. Highlighting Rosa, Gerbera, Neapolitanum, Ranunculus, Othocalis, Muscari, Galanthus, Tulipa and Alstroemeria to release detectable amounts of tulipalin A upon injury. Tulipalin A was predominantly released from the Tulipa and Alstroemeria species, both belonging to the Liliales order, as stated in previous clinical and research studies.</p><p><strong>Conclusions: </strong>In conclusion, a rapid method using the SESI-Orbitrap MS is reported to detect and track tulipalin A synthesis across plant organs and outline its cross-species distribution. Our methodology can be easily adapted for mapping other volatile plant defense metabolites and identify potentially allergenic plants. By addressing these aspects, we can ensure a safer work environment for florists and gardeners.</p>","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":"21 1","pages":"14"},"PeriodicalIF":4.7,"publicationDate":"2025-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11795999/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143256350","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":"Optimizing fully-efficient two-stage models for genomic selection using open-source software.","authors":"Javier Fernández-González, Julio Isidro Y Sánchez","doi":"10.1186/s13007-024-01318-9","DOIUrl":"10.1186/s13007-024-01318-9","url":null,"abstract":"<p><p>Genomic-assisted breeding has transitioned from theoretical concepts to practical applications in breeding. Genomic selection (GS) predicts genomic breeding values (GEBV) using dense genetic markers. Single-stage models predict GEBVs from phenotypic observations in one step, fully accounting for the entire variance-covariance structure among genotypes, but face computational challenges. Two-stage models, preferred for their simplicity and efficiency, first calculate adjusted genotypic means accounting for spatial variation within each environment, then use these means to predict GEBVs. However, unweighted (UNW) two-stage models assume independent errors among adjusted means, neglecting correlations among estimation errors. Here, we show that fully-efficient two-stage models perform similarly to UNW models for randomized complete block designs but substantially better for augmented designs. Our simulation studies demonstrate the impact of the fully-efficient methodology on prediction accuracy across different implementations and scenarios. Incorporating non-additive effects and augmented designs significantly improved accuracy, emphasizing the synergy between design and model strategy. Consistent performance requires the estimation error covariance to be incorporated into a random effect (Full_R model) rather than into the residuals. Our results suggest that the fully-efficient methodology, particularly the Full_R model, should be more prevalent, especially as GS increases the appeal of sparse designs. We also provide a comprehensive theoretical background and open-source R code, enhancing understanding and facilitating broader adoption of fully-efficient two-stage models in GS. Here, we offer insights into the practical applications of fully-efficient models and their potential to increase genetic gain, demonstrating a <math><mrow><mn>13.80</mn> <mo>%</mo></mrow> </math> improvement after five selection cycles when moving from UNW to Full_R models.</p>","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":"21 1","pages":"9"},"PeriodicalIF":4.7,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11796230/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143190229","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":"Enabling high-throughput quantitative wood anatomy through a dedicated pipeline.","authors":"Jan Van den Bulcke, Louis Verschuren, Ruben De Blaere, Simon Vansuyt, Maxime Dekegeleer, Pierre Kibleur, Olivier Pieters, Tom De Mil, Wannes Hubau, Hans Beeckman, Joris Van Acker, Francis Wyffels","doi":"10.1186/s13007-025-01330-7","DOIUrl":"10.1186/s13007-025-01330-7","url":null,"abstract":"<p><p>Throughout their lifetime, trees store valuable environmental information within their wood. Unlocking this information requires quantitative analysis, in most cases of the surface of wood. The conventional pathway for high-resolution digitization of wood surfaces and segmentation of wood features requires several manual and time consuming steps. We present a semi-automated high-throughput pipeline for sample preparation, gigapixel imaging, and analysis of the anatomy of the end-grain surfaces of discs and increment cores. The pipeline consists of a collaborative robot (Cobot) with sander for surface preparation, a custom-built open-source robot for gigapixel imaging (Gigapixel Woodbot), and a Python routine for deep-learning analysis of gigapixel images. The robotic sander allows to obtain high-quality surfaces with minimal sanding or polishing artefacts. It is designed for precise and consistent sanding and polishing of wood surfaces, revealing detailed wood anatomical structures by applying consecutively finer grits of sandpaper. Multiple samples can be processed autonomously at once. The custom-built open-source Gigapixel Woodbot is a modular imaging system that enables automated scanning of large wood surfaces. The frame of the robot is a CNC (Computer Numerical Control) machine to position a camera above the objects. Images are taken at different focus points, with a small overlap between consecutive images in the X-Y plane, and merged by mosaic stitching, into a gigapixel image. Multiple scans can be initiated through the graphical application, allowing the system to autonomously image several objects and large surfaces. Finally, a Python routine using a trained YOLOv8 deep learning network allows for fully automated analysis of the gigapixel images, here shown as a proof-of-concept for the quantification of vessels and rays on full disc surfaces and increment cores. We present fully digitized beech discs of 30-35 cm diameter at a resolution of 2.25  <math><mi>μ</mi></math> m, for which we automatically quantified the number of vessels (up to 13 million) and rays. We showcase the same process for five 30 cm length beech increment cores also digitized at a resolution of 2.25  <math><mi>μ</mi></math> m, and generated pith-to-bark profiles of vessel density. This pipeline allows researchers to perform high-detail analysis of anatomical features on large surfaces, test fundamental hypotheses in ecophysiology, ecology, dendroclimatology, and many more with sufficient sample replication.</p>","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":"21 1","pages":"11"},"PeriodicalIF":4.7,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11796111/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143190228","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}