Dataset Information

Accurate and versatile 3D segmentation of plant tissues at cellular resolution.

ABSTRACT: Quantitative analysis of plant and animal morphogenesis requires accurate segmentation of individual cells in volumetric images of growing organs. In the last years, deep learning has provided robust automated algorithms that approach human performance, with applications to bio-image analysis now starting to emerge. Here, we present PlantSeg, a pipeline for volumetric segmentation of plant tissues into cells. PlantSeg employs a convolutional neural network to predict cell boundaries and graph partitioning to segment cells based on the neural network predictions. PlantSeg was trained on fixed and live plant organs imaged with confocal and light sheet microscopes. PlantSeg delivers accurate results and generalizes well across different tissues, scales, acquisition settings even on non plant samples. We present results of PlantSeg applications in diverse developmental contexts. PlantSeg is free and open-source, with both a command line and a user-friendly graphical interface.

SUBMITTER: Wolny A

PROVIDER: S-EPMC7447435 | biostudies-literature | 2020 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Accurate and versatile 3D segmentation of plant tissues at cellular resolution.

Wolny Adrian A Cerrone Lorenzo L Vijayan Athul A Tofanelli Rachele R Barro Amaya Vilches AV Louveaux Marion M Wenzl Christian C Strauss Sören S Wilson-Sánchez David D Lymbouridou Rena R Steigleder Susanne S SS Pape Constantin C Bailoni Alberto A Duran-Nebreda Salva S Bassel George W GW Lohmann Jan U JU Tsiantis Miltos M Hamprecht Fred A FA Schneitz Kay K Maizel Alexis A Kreshuk Anna A

eLife 20200729

Quantitative analysis of plant and animal morphogenesis requires accurate segmentation of individual cells in volumetric images of growing organs. In the last years, deep learning has provided robust automated algorithms that approach human performance, with applications to bio-image analysis now starting to emerge. Here, we present PlantSeg, a pipeline for volumetric segmentation of plant tissues into cells. PlantSeg employs a convolutional neural network to predict cell boundaries and graph pa ...[more]

PMID: 32723478

Similar Datasets

Project description:Computed tomography remains strongly underused in plant sciences despite its high potential in delivering detailed 3D phenotypical information because of the low X-ray absorption of most plant tissues. Existing protocols to study soft tissues display poor performance, especially when compared to those used on animals. More efficient protocols to study plant material are therefore needed. Flowers of Arabidopsis thaliana and Marcgravia caudata were immersed in a selection of contrasting agents used to treat samples for transmission electron microscopy. Grayscale values for floral tissues and background were measured as a function of time. Contrast was quantified via a contrast index. The thick buds of Marcgravia were scanned to determine which contrasting agents best penetrate thick tissues. The highest contrast increase with cytoplasm-rich tissues was obtained with phosphotungstate, whereas osmium tetroxide and bismuth tatrate displayed the highest contrast increase with vacuolated tissues. Phosphotungstate also displayed the best sample penetration. Furthermore, infiltration with phosphotungstate allowed imaging of all plants parts at a high resolution of 3 µm, which approaches the maximum resolution of our equipment: 1.5 µm. The high affinity of phosphotungstate for vasculature, cytoplasm-rich tissue, and pollen causes these tissues to absorb more X-rays than the surrounding tissues, which, in turn, makes these tissues appear brighter on the scan data. Tissues with different brightness can then be virtually dissected from each other by selecting the bracket of grayscale to be visualized. Promising directions for the future include in silico phenotyping and developmental studies of plant inner parts (e.g., ovules, vasculature, pollen, and cell nuclei) via virtual dissection as well as correlations of quantitative phenotypes with omics datasets. Therefore, this work represents a crucial improvement of previous methods, allowing new directions of research to be undertaken in areas ranging from morphology to systems biology.

Project description:BackgroundSpatial mapping of transcriptional states provides valuable biological insights into cellular functions and interactions in the context of the tissue. Accurate 3D cell segmentation is a critical step in the analysis of this data towards understanding diseases and normal development in situ. Current approaches designed to automate 3D segmentation include stitching masks along one dimension, training a 3D neural network architecture from scratch, and reconstructing a 3D volume from 2D segmentations on all dimensions. However, the applicability of existing methods is hampered by inaccurate segmentations along the non-stitching dimensions, the lack of high-quality diverse 3D training data, and inhomogeneity of image resolution along orthogonal directions due to acquisition constraints; as a result, they have not been widely used in practice.MethodsTo address these challenges, we formulate the problem of finding cell correspondence across layers with a novel optimal transport (OT) approach. We propose CellStitch, a flexible pipeline that segments cells from 3D images without requiring large amounts of 3D training data. We further extend our method to interpolate internal slices from highly anisotropic cell images to recover isotropic cell morphology.ResultsWe evaluated the performance of CellStitch through eight 3D plant microscopic datasets with diverse anisotropic levels and cell shapes. CellStitch substantially outperforms the state-of-the art methods on anisotropic images, and achieves comparable segmentation quality against competing methods in isotropic setting. We benchmarked and reported 3D segmentation results of all the methods with instance-level precision, recall and average precision (AP) metrics.ConclusionsThe proposed OT-based 3D segmentation pipeline outperformed the existing state-of-the-art methods on different datasets with nonzero anisotropy, providing high fidelity recovery of 3D cell morphology from microscopic images.

Project description:BackgroundGingival phenotype plays an important role in dental diagnosis and treatment planning. Traditionally, determining the gingival phenotype is done by manual probing of the gingival soft tissues, an invasive and time-consuming procedure. This study aims to evaluate the feasibility and accuracy of an alternatively novel, non-invasive technology based on the precise 3-dimension (3D) soft tissue reconstruction from intraoral scanning and cone beam computed tomography (CBCT) to predict the gingival biotype.MethodsAs a proof-of-concept, Yorkshire pig mandibles were scanned, and the CBCT data were fed into a deep-learning model to reconstruct the teeth and surrounding bone structure in 3D. By overlaying the CBCT scan with the intraoral scans, an accurate superposition was created and used for virtual measurements of the soft tissue thickness. Meanwhile, gingival thicknesses were also measured by a periodontal probe and digital caliper on the buccal and lingual sides at 3 mm apical to the gingival margin of the posterior teeth and compared with the virtual assessment at the same location. The data obtained from virtual and clinical measurements were compared by Wilcoxon matched-pairs signed-rank analysis, while their correlation was determined by Pearson's r value. The Mann-Whitney U test was used for intergroup comparisons of the amount of difference.ResultsAmong 108 investigated locations, the clinical and virtual measurements are strongly positively correlated (r = 0.9656, P < 0.0001), and only clinically insignificant differences (0.066 ± 0.223 mm) were observed between the two assessments. There is no difference in the agreement between the virtual and clinical measurements on sexually matured samples (0.087 ± 0.240 mm) and pre-pubertal samples (0.033 ± 0.195 mm). Noticeably, there is a greater agreement between the virtual and clinical measurements at the buccal sites (0.019 ± 0.233 mm) than at the lingual sites (0.116 ± 0.215 mm).ConclusionIn summary, the artificial intelligence-based virtual measurement proposed in this work provides an innovative technique potentially for accurately measuring soft tissue thickness using clinical routine 3D imaging systems, which will aid clinicians in generating a more comprehensive diagnosis with less invasive procedures and, in turn, optimize the treatment plans with more predictable outcomes.

Dataset Information

Accurate and versatile 3D segmentation of plant tissues at cellular resolution.

Publications

Accurate and versatile 3D segmentation of plant tissues at cellular resolution.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets