Browse
Submit Data
Databases
API
Help

Dataset Information

0 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

SHAPR predicts 3D cell shapes from 2D microscopic images.

ABSTRACT: Reconstruction of shapes and sizes of three-dimensional (3D) objects from two- dimensional (2D) information is an intensely studied subject in computer vision. We here consider the level of single cells and nuclei and present a neural network-based SHApe PRediction autoencoder. For proof-of-concept, SHAPR reconstructs 3D shapes of red blood cells from single view 2D confocal microscopy images more accurately than naïve stereological models and significantly increases the feature-based prediction of red blood cell types from F1 = 79% to F1 = 87.4%. Applied to 2D images containing spheroidal aggregates of densely grown human induced pluripotent stem cells, we find that SHAPR learns fundamental shape properties of cell nuclei and allows for prediction-based morphometry. Reducing imaging time and data storage, SHAPR will help to optimize and up-scale image-based high-throughput applications for biomedicine.

SUBMITTER: Waibel DJE

PROVIDER: S-EPMC9593790 | biostudies-literature | 2022 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Publications

SHAPR predicts 3D cell shapes from 2D microscopic images.

Waibel Dominik J E DJE Kiermeyer Niklas N Atwell Scott S Sadafi Ario A Meier Matthias M Marr Carsten C

iScience 20221006 11

Reconstruction of shapes and sizes of three-dimensional (3D) objects from two- dimensional (2D) information is an intensely studied subject in computer vision. We here consider the level of single cells and nuclei and present a neural network-based SHApe PRediction autoencoder. For proof-of-concept, SHAPR reconstructs 3D shapes of red blood cells from single view 2D confocal microscopy images more accurately than naïve stereological models and significantly increases the feature-based prediction ...[more]

PMID: 36304119

Similar Datasets

Searching for 3D structural models from a library of biological shapes using a few 2D experimental images.

Project description:BackgroundAdvancements in biophysical experimental techniques have pushed the limits in terms of the types of phenomena that can be characterized, the amount of data that can be produced and the resolution at which we can visualize them. Single particle techniques such as Electron Microscopy (EM) and X-ray free electron laser (XFEL) scattering require a large number of 2D images collected to resolve three-dimensional (3D) structures. In this study, we propose a quick strategy to retrieve potential 3D shapes, as low-resolution models, from a few 2D experimental images by searching a library of 2D projection images generated from existing 3D structures.ResultsWe developed the protocol to assemble a non-redundant set of 3D shapes for generating the 2D image library, and to retrieve potential match 3D shapes for query images, using EM data as a test. In our strategy, we disregard differences in volume size, giving previously unknown structures and conformations a greater number of 3D biological shapes as possible matches. We tested the strategy using images from three EM models as query images for searches against a library of 22750 2D projection images generated from 250 random EM models. We found that our ability to identify 3D shapes that match the query images depends on how complex the outline of the 2D shapes are and whether they are represented in the search image library.ConclusionsThrough our computational method, we are able to quickly retrieve a 3D shape from a few 2D projection images. Our approach has the potential for exploring other types of 2D single particle structural data such as from XFEL scattering experiments, for providing a tool to interpret low-resolution data that may be insufficient for 3D reconstruction, and for estimating the mixing of states or conformations that could exist in such experimental data.

| S-EPMC6134691 | biostudies-literature

Synthesis of large scale 3D microscopic images of 3D cell cultures for training and benchmarking.

Project description:The analysis of 3D microscopic cell culture images plays a vital role in the development of new therapeutics. While 3D cell cultures offer a greater similarity to the human organism than adherent cell cultures, they introduce new challenges for automatic evaluation, like increased heterogeneity. Deep learning algorithms are able to outperform conventional analysis methods in such conditions but require a large amount of training data. Due to data size and complexity, the manual annotation of 3D images to generate large datasets is a nearly impossible task. We therefore propose a pipeline that combines conventional simulation methods with deep-learning-based optimization to generate large 3D synthetic images of 3D cell cultures where the labels are known by design. The hybrid procedure helps to keep the generated image structures consistent with the underlying labels. A new approach and an additional measure are introduced to model and evaluate the reduced brightness and quality in deeper image regions. Our analyses show that the deep learning optimization step consistently improves the quality of the generated images. We could also demonstrate that a deep learning segmentation model trained with our synthetic data outperforms a classical segmentation method on real image data. The presented synthesis method allows selecting a segmentation model most suitable for the user's data, providing an ideal basis for further data analysis.

| S-EPMC10065262 | biostudies-literature

3D Structure From 2D Microscopy Images Using Deep Learning.

Project description:Understanding the structure of a protein complex is crucial in determining its function. However, retrieving accurate 3D structures from microscopy images is highly challenging, particularly as many imaging modalities are two-dimensional. Recent advances in Artificial Intelligence have been applied to this problem, primarily using voxel based approaches to analyse sets of electron microscopy images. Here we present a deep learning solution for reconstructing the protein complexes from a number of 2D single molecule localization microscopy images, with the solution being completely unconstrained. Our convolutional neural network coupled with a differentiable renderer predicts pose and derives a single structure. After training, the network is discarded, with the output of this method being a structural model which fits the data-set. We demonstrate the performance of our system on two protein complexes: CEP152 (which comprises part of the proximal toroid of the centriole) and centrioles.

| S-EPMC9581024 | biostudies-literature

SAU-Net: A Unified Network for Cell Counting in 2D and 3D Microscopy Images.

Project description:Image-based cell counting is a fundamental yet challenging task with wide applications in biological research. In this paper, we propose a novel unified deep network framework designed to solve this problem for various cell types in both 2D and 3D images. Specifically, we first propose SAU-Net for cell counting by extending the segmentation network U-Net with a Self-Attention module. Second, we design an extension of Batch Normalization (BN) to facilitate the training process for small datasets. In addition, a new 3D benchmark dataset based on the existing mouse blastocyst (MBC) dataset is developed and released to the community. Our SAU-Net achieves state-of-the-art results on four benchmark 2D datasets - synthetic fluorescence microscopy (VGG) dataset, Modified Bone Marrow (MBM) dataset, human subcutaneous adipose tissue (ADI) dataset, and Dublin Cell Counting (DCC) dataset, and the new 3D dataset, MBC. The BN extension is validated using extensive experiments on the 2D datasets, since GPU memory constraints preclude use of 3D datasets. The source code is available at https://github.com/mzlr/sau-net.

| S-EPMC8924707 | biostudies-literature

Fully automatic and robust 3D registration of serial-section microscopic images.

Project description:Robust and fully automatic 3D registration of serial-section microscopic images is critical for detailed anatomical reconstruction of large biological specimens, such as reconstructions of dense neuronal tissues or 3D histology reconstruction to gain new structural insights. However, robust and fully automatic 3D image registration for biological data is difficult due to complex deformations, unbalanced staining and variations on data appearance. This study presents a fully automatic and robust 3D registration technique for microscopic image reconstruction, and we demonstrate our method on two ssTEM datasets of drosophila brain neural tissues, serial confocal laser scanning microscopic images of a drosophila brain, serial histopathological images of renal cortical tissues and a synthetic test case. The results show that the presented fully automatic method is promising to reassemble continuous volumes and minimize artificial deformations for all data and outperforms four state-of-the-art 3D registration techniques to consistently produce solid 3D reconstructed anatomies with less discontinuities and deformations.

| S-EPMC4598826 | biostudies-literature

Nuclear envelope wrinkling predicts mesenchymal progenitor cell mechano-response in 2D and 3D microenvironments.

Project description:Exogenous mechanical cues are transmitted from the extracellular matrix to the nuclear envelope (NE), where mechanical stress on the NE mediates shuttling of transcription factors and other signaling cascades that dictate downstream cellular behavior and fate decisions. To systematically study how nuclear morphology can change across various physiologic microenvironmental contexts, we cultured mesenchymal progenitor cells (MSCs) in engineered 2D and 3D hyaluronic acid hydrogel systems. Across multiple contexts we observed highly 'wrinkled' nuclear envelopes, and subsequently developed a quantitative single-cell imaging metric to better evaluate how wrinkles in the nuclear envelope relate to progenitor cell mechanotransduction. We determined that in soft 2D environments the NE is predominately wrinkled, and that increases in cellular mechanosensing (indicated by cellular spreading, adhesion complex growth, and nuclear localization of YAP/TAZ) occurred only in absence of nuclear envelope wrinkling. Conversely, in 3D hydrogel and tissue contexts, we found NE wrinkling occurred along with increased YAP/TAZ nuclear localization. We further determined that these NE wrinkles in 3D were largely generated by actin impingement, and compared to other nuclear morphometrics, the degree of nuclear wrinkling showed the greatest correlation with nuclear YAP/TAZ localization. These findings suggest that the degree of nuclear envelope wrinkling can predict mechanotransduction state in mesenchymal progenitor cells and highlights the differential mechanisms of NE stress generation operative in 2D and 3D microenvironmental contexts.

| S-EPMC7936657 | biostudies-literature

Machine learning of hierarchical clustering to segment 2D and 3D images.

Project description:We aim to improve segmentation through the use of machine learning tools during region agglomeration. We propose an active learning approach for performing hierarchical agglomerative segmentation from superpixels. Our method combines multiple features at all scales of the agglomerative process, works for data with an arbitrary number of dimensions, and scales to very large datasets. We advocate the use of variation of information to measure segmentation accuracy, particularly in 3D electron microscopy (EM) images of neural tissue, and using this metric demonstrate an improvement over competing algorithms in EM and natural images.

| S-EPMC3748125 | biostudies-literature

2D protrusion but not motility predicts growth factor-induced cancer cell migration in 3D collagen.

Project description:Growth factor-induced migration is a critical step in the dissemination and metastasis of solid tumors. Although differences in properties characterizing cell migration on two-dimensional (2D) substrata versus within three-dimensional (3D) matrices have been noted for particular growth factor stimuli, the 2D approach remains in more common use as an efficient surrogate, especially for high-throughput experiments. We therefore were motivated to investigate which migration properties measured in various 2D assays might be reflective of 3D migratory behavioral responses. We used human triple-negative breast cancer lines stimulated by a panel of receptor tyrosine kinase ligands relevant to mammary carcinoma progression. Whereas 2D migration properties did not correlate well with 3D behavior across multiple growth factors, we found that increased membrane protrusion elicited by growth factor stimulation did relate robustly to enhanced 3D migration properties of the MDA-MB-231 and MDA-MB-157 lines. Interestingly, we observed this to be a more reliable relationship than cognate receptor expression or activation levels across these and two additional mammary tumor lines.

| S-EPMC3373410 | biostudies-literature

Semi-automated 3D leaf reconstruction and analysis of trichome patterning from light microscopic images.

Project description:Trichomes are leaf hairs that are formed by single cells on the leaf surface. They are known to be involved in pathogen resistance. Their patterning is considered to emerge from a field of initially equivalent cells through the action of a gene regulatory network involving trichome fate promoting and inhibiting factors. For a quantitative analysis of single and double mutants or the phenotypic variation of patterns in different ecotypes, it is imperative to statistically evaluate the pattern reliably on a large number of leaves. Here we present a method that enables the analysis of trichome patterns at early developmental leaf stages and the automatic analysis of various spatial parameters. We focus on the most challenging young leaf stages that require the analysis in three dimensions, as the leaves are typically not flat. Our software TrichEratops reconstructs 3D surface models from 2D stacks of conventional light-microscope pictures. It allows the GUI-based annotation of different stages of trichome development, which can be analyzed with respect to their spatial distribution to capture trichome patterning events. We show that 3D modeling removes biases of simpler 2D models and that novel trichome patterning features increase the sensitivity for inter-accession comparisons.

| S-EPMC3630213 | biostudies-literature

Accurate patient alignment without unnecessary imaging using patient-specific 3D CT images synthesized from 2D kV images.

Project description:BackgroundIn radiotherapy, 2D orthogonally projected kV images are used for patient alignment when 3D-on-board imaging (OBI) is unavailable. However, tumor visibility is constrained due to the projection of patient's anatomy onto a 2D plane, potentially leading to substantial setup errors. In treatment room with 3D-OBI such as cone beam CT (CBCT), the field of view (FOV) of CBCT is limited with unnecessarily high imaging dose. A solution to this dilemma is to reconstruct 3D CT from kV images obtained at the treatment position.MethodsWe propose a dual-models framework built with hierarchical ViT blocks. Unlike a proof-of-concept approach, our framework considers kV images acquired by 2D imaging devices in the treatment room as the solo input and can synthesize accurate, full-size 3D CT within milliseconds.ResultsWe demonstrate the feasibility of the proposed approach on 10 patients with head and neck (H&N) cancer using image quality (MAE: < 45HU), dosimetric accuracy (Gamma passing rate ((2%/2 mm/10%): > 97%) and patient position uncertainty (shift error: < 0.4 mm).ConclusionsThe proposed framework can generate accurate 3D CT faithfully mirroring patient position effectively, thus substantially improving patient setup accuracy, keeping imaging dose minimal, and maintaining treatment veracity.

| S-EPMC11582647 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data