Biology subjects

Seethepalli, A.

Publications and source records attributed to Seethepalli, A..

10 recordsLinked to original sources

bioRxiv2026

Vision Transformers Enable Advanced Plant Phenotyping in Controlled Environments

Reliable plant segmentation in high-throughput phenotyping must transfer across species and imaging conditions without repeated model tuning or extensive reannotation. We compare three segmentation strategies using images from Oak Ridge National Laboratory's Advanced Plant Phenotyping Laboratory: (i) fixed color-based thresholding, (ii) supervised U-Nets trained from scratch, and (iii) pretrained vision transformers fine-tuned for binary segmentation. Models were evaluated on a held-out test set and a generalization set that comprised unseen species. On the held-out test set, thresholding, the best U-Net, and the best vision transformer achieved mean Dice scores of 58.3, 96.6, and 97.3, respectively. On the generalization set, the corresponding Dice scores were 56.5, 86.2, and 95.7. Thresholding remained effective on some datasets but failed when plant appearance changed. Supervised U-Net training resolved within-distribution errors but failed to generalize to novel species and backgrounds. Pretrained vision transformers consistently produced high-accuracy segmentations across the evaluated species, views, soil backgrounds, and tray types. These results benchmark the practical progression from fixed rules to task-specific supervision and pretrained visual representations for controlled-environment plant phenotyping.

plant biology↗

bioRxiv2026

Transformers Outperform ConvNets for Root Segmentation: A Systematic Comparison Across Nine Datasets

Root segmentation is a fundamental yet challenging task in image-based plant phenotyping. We present the first systematic comparison of Transformer and Convolutional Neural Network (ConvNet) architectures for root segmentation, evaluating 21 architectures across nine diverse datasets and comparing pre-trained models to training from scratch. Transformer-based models significantly outperform ConvNets for segmentation accuracy and root-diameter agreement. Pre-training significantly improves mean Dice from 0.623 to 0.666 (p = 3.3 x 10-10). We also find that Transformers benefit more from pre-training than ConvNets, with Dice improvements of +0.072 versus +0.022 (p = 3.7 x 10-4), supporting the hypothesis that fine-tuned Transformers transfer more effectively across large domain gaps. Among evaluated models, MobileSAM achieved the highest Dice score while maintaining computational efficiency. Dataset choice explained far more performance variance (70.9%) than model architecture (6.7%), suggesting that data curation matters more than model selection.

plant biology↗

bioRxiv2024

Divide and conquer: Using RhizoVision Explorer to aggregate data from multiple root scans using image concatenation and statistical methods

Roots are important in agricultural and natural systems for determining plant productivity and soil carbon inputs. The collection of root samples from the field and their subsequent cleaning and scanning in a water-filled tray ranging in size from 5 to 20 cm, followed by digital image analysis has been commonly used since the 1990s for measuring root length, volume, area, and diameter. However, one common issue has been neglected. Sometimes, the amount of roots for a sample is too much to fit into a single scanned image, so the sample is divided among several scans. There is no standard method to aggregate the root measurements across the scans of the same sample. Here, we describe and validate two methods for standardizing measurements across multiple scans: image concatenation and statistical aggregation. Both methods rely on standardizing file naming conventions to identify scans that belong to the same sample. Image concatenation refers to combining digital images into a single larger image while maintaining the original resolution. We developed a Python script that identifies which images belong to the same sample and returns a single, larger concatenated image for every set of images in a directory. These concatenated images (combining up to 10 scans) and the original images were processed with RhizoVision Explorer, a free and open-source software developed for estimating root traits from images, with the same settings. An R script was developed that can identify the rows of data belonging to the same sample in RhizoVision Explorer data files and apply correct statistical methods such as summation, weighted average by length, and average to the appropriate measurement types to return a single data row for each sample. These two methods were compared using example images from switchgrass, poplar, and various tree and ericaceous shrub species from a northern peatland and the Arctic. Overall, the new methods accomplished the goal of standardizing measurement aggregation. Most root measurements were nearly identical except median diameter, which can not be accurately computed by statistical aggregation. We believe the availability of these methods will be useful to the root biology community.

plant biology↗

bioRxiv2021

RhizoVision Explorer: Open-source software for root image analysis and measurement standardization

Roots are central to the function of natural and agricultural ecosystems by driving plant acquisition of soil resources and influencing the carbon cycle. Root characteristics like length, diameter, and volume are critical to measure to understand plant and soil functions. RhizoVision Explorer is an open-source software designed to enable researchers interested in roots by providing an easy-to-use interface, fast image processing, and reliable measurements. The default broken roots mode is intended for roots sampled from pots or soil cores, washed, and typically scanned on a flatbed scanner, and provides measurements like length, diameter, and volume. The optional whole root mode for complete root systems or root crowns provides additional measurements such as angles, root depth, and convex hull. Both modes support providing measurements grouped by defined diameter ranges, the inclusion of multiple regions of interest, and batch analysis. RhizoVision Explorer was successfully validated against ground truth data using a novel copper wire image set. In comparison, the current reference software, the commercial WinRhizo, drastically underestimated volume when wires of different diameters were in the same image. Additionally, measurements were compared with WinRhizo and IJ_Rhizo using a simulated root image set, showing general agreement in software measurements, except for root volume. Finally, scanned root image sets acquired in different labs for the crop, herbaceous, and tree species were used to compare results from RhizoVision Explorer with WinRhizo. The two software showed general agreement, except that WinRhizo substantially underestimated root volume relative to RhizoVision Explorer. In the current context of rapidly growing interest in root science, RhizoVision Explorer intends to become a reference software, improve the overall accuracy and replicability of root trait measurements, and provide a foundation for collaborative improvement and reliable access to all. O_FIG_DISPLAY_L [Figure 1] M_FIG_DISPLAY C_FIG_DISPLAY

plant biology↗

bioRxiv2021

Interactions among rooting traits for deep water and nitrogen uptake in upland and lowland ecotypes of switchgrass (Panicum virgatum L.)

Plant phenotypic plasticity in response to nutrient and water availability is an important adaptation for abiotic stress tolerance. Roots intercept water and nutrients while foraging through soil searching for further resources. Substantial amounts of nitrate can leach into groundwater; yet, little is known about how deep rooting affects this process. Here, we phenotyped root system traits and deep 15N nitrate capture across 1.5 m profiles of solid-media using tall mesocosms in switchgrass (Panicum virgatum L.), a cellulosic bioenergy feedstock. Root and shoot biomass, photosynthesis and respiration, and nutrient uptake traits were quantified in response to a water and nitrate stress factorial experiment in the greenhouse for switchgrass upland (VS16) and lowland (AP13) ecotypes. The two switchgrass ecotypes shared common plastic abiotic responses to nitrogen (N) and water availability and yet showed genotypic differences for root and shoot traits. A significant interaction between nitrogen and water stress for axial and lateral root traits represents a complex and shared root development strategy for stress mitigation. Deep root growth and 15N capture were found to be closely linked to aboveground growth. Together, these results represent the wide genetic pool of switchgrass and that deep rooting promotes nitrate capture, plant productivity, and sustainability. HighlightTwo main ecotypes of switchgrass have both shared and different root responses to varying water and nitrogen conditions, with deep rooting shown to be closely linked to aboveground growth.

plant biology↗

bioRxiv2020

Functional phenomics and genetics of the root economics space in winter wheat using high-throughput phenotyping of respiration and architecture

O_LIThe root economics space is a useful framework for plant ecology, but rarely considered for crop ecophysiology. In order to understand root trait integration in winter wheat, we combined functional phenomics with trait economic theory utilizing genetic variation, high-throughput phenotyping, and multivariate analyses. C_LIO_LIWe phenotyped a diversity panel of 276 genotypes for root respiration and architectural traits using a novel high-throughput method for CO2 flux and the open-source software RhizoVision Explorer for analyzing scanned images. C_LIO_LIWe uncovered substantial variation for specific root respiration (SRR) and specific root length (SRL), which were primary indicators of root metabolic and construction costs. Multiple linear regression estimated that lateral root tips had the greatest SRR, and the residuals of this model were used as a new trait. SRR was negatively correlated with plant mass. Network analysis using a Gaussian graphical model identified root weight, SRL, diameter, and SRR as hub traits. Univariate and multivariate genetic analyses identified genetic regions associated with aspects of the root economics space, with underlying gene candidates. C_LIO_LICombining functional phenomics and root economics is a promising approach to understand crop ecophysiology. We identified root traits and genomic regions that could be harnessed to breed more efficient crops for sustainable agroecosystems. C_LI

plant biology↗

bioRxiv2020

A multiple ion-uptake phenotyping platform reveals shared mechanisms that affect nutrient uptake by maize roots

Nutrient uptake is critical for crop growth and determined by root foraging in soil. Growth and branching of roots lead to effective root placement to acquire nutrients, but relatively less is known about absorption of nutrients at the root surface from the soil solution. This knowledge gap could be alleviated by understanding sources of genetic variation for short-term nutrient uptake on a root length basis. A new modular platform for high-throughput phenotyping of multiple ion uptake kinetics was designed to determine nutrient uptake rates in Zea mays. Using this system, uptake rates were characterized for the crop macronutrients nitrate, ammonium, potassium, phosphate and sulfate among the Nested Association Mapping (NAM) population founder lines. The data revealed that substantial genetic variation exists for multiple ion uptake rates in maize. Interestingly, specific nutrient uptake rates (nutrient uptake rate per length of root) were found to be both heritable and distinct from total uptake and plant size. The specific uptake rates of each nutrient were positively correlated with one another and with specific root respiration (root respiration rate per length of root), indicating that uptake is governed by shared mechanisms. We selected maize lines with high and low specific uptake rates and performed an RNA-seq analysis, which identified key regulatory components involved in nutrient uptake. The high-throughput multiple ion uptake kinetics pipeline will help further our understanding of nutrient uptake, parameterize holistic plant models, and identify breeding targets for crops with more efficient nutrient acquisition. Significance StatementNutrient uptake is among the most limiting factors for plant growth and yet has not been used as a selection criterion in breeding. This is partly due to the lack of high-throughput phenotyping methods for measuring nutrient uptake. Here we describe a novel high-throughput phenotyping pipeline for quantification of multiple ion uptake rates. Using this new phenotyping system, our results demonstrate that specific ion uptake performance by maize plants is positively correlated among the macronutrients nitrogen, phosphorus, potassium and sulfur, and that substantial variation exists within a genetically diverse population. The findings reveal components of regulatory pathways possibly related with enhanced uptake, and confirm that nutrient uptake itself is a potential target for breeding of nutrient-efficient crops.

plant biology↗

bioRxiv2019

RhizoVision Crown: An Integrated Hardware and Software Platform for Root Crown Phenotyping

Root crown phenotyping measures the top portion of crop root systems and can be used for marker-assisted breeding, genetic mapping, and understanding how roots influence soil resource acquisition. Several imaging protocols and image analysis programs exist, but they are not optimized for high-throughput, repeatable, and robust root crown phenotyping. The RhizoVision Crown platform integrates an imaging unit, image capture software, and image analysis software that are optimized for reliable extraction of measurements from large numbers of root crowns. The hardware platform utilizes a back light and a monochrome machine vision camera to capture root crown silhouettes. RhizoVision Imager and RhizoVision Analyzer are free, open-source software that streamline image capture and image analysis with intuitive graphical user interfaces. RhizoVision Analyzer was physically validated using copper wire and features were extensively validated using 10,464 ground-truth simulated images of dicot and monocot root systems. This platform was then used to phenotype soybean and wheat root crowns. A total of 2,799 soybean (Glycine max) root crowns of 187 lines and 1,753 wheat (Triticum aestivum) root crowns of 186 lines were phenotyped. Principal component analysis indicated similar correlations among features in both species. The maximum heritability was 0.74 in soybean and 0.22 in wheat, indicating differences in species and populations need to be considered. The integrated RhizoVision Crown platform facilitates high-throughput phenotyping of crop root crowns, and sets a standard by which open plant phenotyping platforms can be benchmarked.

plant biology↗

bioRxiv2018

Digital imaging to evaluate root system architectural changes associated with soil biotic factors

Root system architecture (RSA) is critical for plant growth, which is influenced by several edaphic, environmental, genetic and biotic factors including beneficial and pathogenic microbes. Studying root architecture and the dynamic changes that occur during a plants lifespan, especially for perennial crops growing over multiple growing seasons, is still a challenge because of the nature of their growing environment in soil. We describe the utility of an imaging platform called RhizoVision Crown to study RSA of alfalfa, a perennial forage crop affected by Phymatotrichopsis Root Rot (PRR) disease. Phymatotrichopsis omnivora is the causal agent of PRR disease that reduces alfalfa stand longevity. During the lifetime of the stand, PRR disease rings enlarge and the field can be categorized into three zones based upon plant status: asymptomatic, disease front and survivor. To study root architectural changes associated with PRR, a four-year old 25.6-hectare alfalfa stand infested with PRR was selected at the Red River Farm, Burneyville, OK during October 2017. Line transect sampling was conducted from four actively growing PRR disease rings. At each disease ring, six line transects were positioned spanning 15 m on either side of the disease front with one alfalfa root sampled at every 3 m interval. Each alfalfa root was imaged with the RhizoVision Crown platform using a backlight and a high-resolution monochrome CMOS camera enabling preservation of the natural root architectural integrity. The platforms image analysis software, RhizoVision Analyzer, automatically segmented images, skeletonized, and extracted a suite of features. Data indicated that the survivor plants compensated for damage or loss to the taproot through the development of more lateral and crown roots, and that a suite of multivariate features could be used to automatically classify roots as from survivor or asymptomatic zones. Root growth is a dynamic process adapting to ever changing interactions among various phytobiome components, by utilizing a low-cost, efficient and high-throughput Rhizo-Vision Crown platform we showed quantification of these changes occurring in a mature perennial forage crop.

plant biology↗

bioRxiv2018

A novel multi-perspective imaging platform (M-PIP) for phenotyping soybean root crowns in the field increases throughput and separation ability of genotype root properties

BackgroundRoot crown phenotyping has linked root properties to shoot mass, nutrient uptake, and yield in the field, which increases the understanding of soil resource acquisition and presents opportunities for breeding. The original methods using manual measurements have been largely supplanted by image-based approaches. However, most image-based systems have been limited to one or two perspectives and rely on segmentation from grayscale images. An efficient high-throughput root crown phenotyping system is introduced that takes images from five perspectives simultaneously, constituting the Multi-Perspective Imaging Platform (M-PIP). A segmentation procedure using the Expectation-Maximization Gaussian Mixture Model (EM-GMM) algorithm was developed to distinguish plant root pixels from background pixels in color images and using hardware acceleration (CPU and GPU). Phenes were extracted using MatLab scripts. Placement of excavated root crowns for image acquisition was standardized and is ergonomic. The M-PIP was tested on 24 soybean [Glycine max (L.) Merr.] cultivars released between 1930 and 2005.\n\nResultsRelative to previous reports of imaging throughput, this system provides greater throughput with sustained rates of 1.66 root crowns min-1. The EM-GMM segmentation algorithm with hardware acceleration was able to segment images in 10 s, faster than previous methods, and the output images were consistently better connected with less loss of fine detail. Image-based phenes had similar heritabilities as manual measures with the greatest effect sizes observed for Maximum Radius and Fine Radius Frequency. Correlations were also noted, especially among the manual Complexity score and phenes such as number of roots and Total Root Length. Averaging phenes across perspectives generally increased heritability, and no single perspective consistently performed better than others. Angle-based phenes, Fineness Index, Maximum Width, Holes, Solidity and Width-to-Depth Ratio were the most sensitive to perspective with decreased correlations among perspectives.\n\nConclusionThe substantial heritabilities measured for many phenes suggest that they are potentially useful for breeding. Multiple perspectives together often produced the greatest heritabilities, and no single perspective consistently performed better than others. Thus, as illustrated here for soybean, multiple perspectives may be beneficial for root crown phenotyping systems. This system can contribute to breeding efforts that incorporate under-utilized root phenotypes to increase food security and sustainability.

physiology↗