Deep learning-based identification of sub-nuclear structures in FIB-SEM images (2022-07-19T00:00:00.000000Z)

TL;DR

A convolutional neural network, supervised deep learning-based approach which can identify sub-nuclear structures with 90% accuracy is presented which can be optimized for its broad application to other volumetric imaging data as well as in situ cryo-electron tomography.

Abstract

Three-dimensional volumetric imaging of cells allows for in situ visualization, thus preserving contextual insights into cellular processes. Despite recent advances in machine learning methods, morphological analysis of sub-nuclear structures have proven challenging due to both the shallow contrast profile and the technical limitation in feature detection. Here, we present a convolutional neural network, supervised deep learning-based approach which can identify sub-nuclear structures with 90% accuracy. We develop and apply this model to C. elegans gonads imaged using focused ion beam milling combined with scanning electron microscopy resulting in the accurate identification and segmentation of all sub-nuclear structures including entire chromosomes. We discuss in depth the architecture, parameterization, and optimization of the deep learning model, as well as provide evaluation metrics to assess the quality of the network prediction. Lastly, we highlight specific aspects of the model that can be optimized for its broad application to other volumetric imaging data as well as in situ cryo-electron tomography.

Authors

N. Gupta

1 papers

Eric J. Roberts

1 papers

Song Pang

1 papers

TL;DR

Abstract

Authors

References87 items

Optical flow driven interpolation for isotropic FIB-SEM reconstructions

Convolutional networks for supervised mining of molecular patterns within cellular context

Whole-cell organelle segmentation in volume electron microscopy

An open-access volume electron microscopy atlas of whole cells and tissues

Towards Visual Proteomics at High Resolution.

Modality specific U-Net variants for biomedical image segmentation: a survey

ER-to-Golgi protein delivery through an interwoven, tubular network extending from ER

Comparison of segmentation algorithms for FIB/SEM tomography of porous polymers: Importance of image contrast for machine learning segmentation

3D FIB-SEM reconstruction of microtubule–organelle interaction in whole primary mouse β cells

Task-Driven Learned Hyperspectral Data Reduction Using End-to-End Supervised Deep Learning

SHREC 2020: Classification in cryo-electron tomograms

Micro- and Nano-Scale Pore Structure in Gas Shale Using Xμ-CT and FIB-SEM Techniques

Three‐dimensional reconstruction of porous polymer films from FIB‐SEM nanotomography data using random forests

Optimization of FIB–SEM Tomography and Reconstruction for Soft, Porous, and Poorly Conducting Materials

Deep learning improves macromolecule identification in 3D cellular cryo-electron tomograms

Nested Neuronal Dynamics Orchestrate a Behavioral Hierarchy across Timescales

AITom: Open-source AI platform for cryo-electron Tomography data analysis

Methodology of three-dimensional visualization and quantitative characterization of nanopores in coal by using FIB-SEM and its application with anthracite in Qinshui basin

Introducing Hann windows for reducing edge-effects in patch-based image segmentation

Analyses of representative elementary volume for coal using X-ray μ-CT and FIB-SEM and its application in permeability predication model

Learning on the Edge: Investigating Boundary Filters in CNNs

Correlative three-dimensional super-resolution and block-face electron microscopy of whole vitreously frozen cells

Whole-animal connectomes of both Caenorhabditis elegans sexes

Scale-space approximated convolutional neural networks for retinal vessel segmentation

Filter technique of medical image on multiple morphological gradient (MMG) method

PoreSpy: A Python Toolkit for Quantitative Analysis of Porous Media Images

Volume microscopy in biology: FIB-SEM tomography.

Automatic localization and identification of mitochondria in cellular electron cryo-tomography using faster-RCNN

Overfitting remedy by sparsifying regularization on fully-connected layers of CNNs

Improving Tomographic Reconstruction from Limited Data Using Mixed-Scale Dense Convolutional Neural Networks

A quantified study of segmentation techniques on synthetic geological XRM and FIB-SEM images

U-Segnet: Fully Convolutional Neural Network Based Automated Brain Tissue Segmentation Tool

High Efficient Local Feature Matching

A deep learning algorithm for one-step contour aware nuclei segmentation of histopathology images

A mixed-scale dense convolutional neural network for image analysis

Contacts between the endoplasmic reticulum and other membranes in neurons

Enhanced FIB-SEM systems for large-volume 3D imaging

Cryo-FIB-SEM serial milling and block face imaging: Large volume structural analysis of biological tissues preserved close to their native state.

Assessing the utility of FIB-SEM images for shale digital rock physics

The Importance of Skip Connections in Biomedical Image Segmentation

3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation

Feature Adaptive Sampling for Scanning Electron Microscopy

Multi-Scale Context Aggregation by Dilated Convolutions

U-Net: Convolutional Networks for Biomedical Image Segmentation

Challenges of microtome‐based serial block‐face scanning electron microscopy in neuroscience

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

Ultrastructurally-smooth thick partitioning and volume stitching for larger-scale connectomics

Adam: A Method for Stochastic Optimization

A workflow for the automatic segmentation of organelles in electron microscopy image stacks

The Rich Club of the C. elegans Neuronal Connectome

Decision tree for 3-D connected components labeling

EDLines: A real-time line segment detector with a false detection control

Evaluation of Pooling Operations in Convolutional Architectures for Object Recognition

Automating the Collection of Ultrathin Serial Sections for Large Volume TEM Reconstructions

Ultrastructural examination of dentin using focused ion-beam cross-sectioning and transmission electron microscopy.

Electron and ion imaging of gland cells using the FIB/SEM system

Developmental timing in C. elegans is regulated by kin-20 and tim-1, homologs of core circadian clock genes.

Distinctive Image Features from Scale-Invariant Keypoints

Focused ion beam for microscopy and in situ sample preparation: application on a crustacean digestive system.

Serial Block-Face Scanning Electron Microscopy to Reconstruct Three-Dimensional Tissue Nanostructure

Three‐dimensional analysis of porous BaTiO3 ceramics using FIB nanotomography

Best practices for convolutional neural networks applied to visual document analysis

Object recognition from local scale-invariant features

MUC-5 Evaluation Metrics

Non-Linear Dimensionality Reduction

Robust segmentation of edge data

[Genetics of Caenorhabditis elegans].

The structure of the nervous system of the nematode Caenorhabditis elegans.

Toward a physical map of the genome of the nematode Caenorhabditis elegans.

Morphologic edge detection

The neural circuit for touch sensitivity in Caenorhabditis elegans

Mutations causing transformation of sexual phenotype in the nematode Caenorhabditis elegans.

Sequential Operations in Digital Picture Processing

The perceptron: a probabilistic model for information storage and organization in the brain.

cc3d: Connected components on multilabel 3d images

A study in finding effectiveness of Gaussian blur filter over bilateral filter in natural scenes for graph based image segmentation