Deep Learning Convolutional Networks for Multiphoton Microscopy Vasculature Segmentation (2016-06-08T00:00:00.000000Z)

TL;DR

This work provided a freely available dataset of 12 annotated two-photon vasculature microscopy stacks and demonstrated the use of deep learning framework consisting both 2D and 3D convolutional filters (ConvNet) that produced promising segmentation result.

Abstract

Recently there has been an increasing trend to use deep learning frameworks for both 2D consumer images and for 3D medical images. However, there has been little effort to use deep frameworks for volumetric vascular segmentation. We wanted to address this by providing a freely available dataset of 12 annotated two-photon vasculature microscopy stacks. We demonstrated the use of deep learning framework consisting both 2D and 3D convolutional filters (ConvNet). Our hybrid 2D-3D architecture produced promising segmentation result. We derived the architectures from Lee et al. who used the ZNN framework initially designed for electron microscope image segmentation. We hope that by sharing our volumetric vasculature datasets, we will inspire other researchers to experiment with vasculature dataset and improve the used network architectures.

Authors

Petteri Teikari

1 papers

Marc A. Santos

1 papers

Charissa Poon

1 papers

TL;DR

Abstract

Authors

References257 items

Computational mammography using deep neural networks

Feature Space Optimization for Semantic Video Segmentation

Theano: A Python framework for fast computation of mathematical expressions

Multi-scale deep networks and regression forests for direct bi-ventricular volume estimation

Efficient multi‐scale 3D CNN with fully connected CRF for accurate brain lesion segmentation

Ensemble of Deep Convolutional Neural Networks for Learning to Detect Retinal Vessels in Fundus Images

Metadata management for high content screening in OMERO

Stenosis map for volume visualization of constricted tubular structures: Application to coronary artery stenosis

Hybrid CNN and Dictionary-Based Models for Scene Recognition and Domain Adaptation

TensorFlow: Biology's Gateway to Deep Learning?

Learning Transferrable Knowledge for Semantic Segmentation with Deep Convolutional Neural Network

Recent advances in convolutional neural networks

Blind inpainting using the fully convolutional neural network

Human-level concept learning through probabilistic program induction

Projection onto the Manifold of Elongated Structures for Accurate Extraction

Matrix Backpropagation for Deep Networks with Structured Layers

Driverseat: Crowdstrapping Learning Tasks for Autonomous Driving

Bidirectional Recurrent Convolutional Networks for Multi-Frame Super-Resolution

Rethinking the Inception Architecture for Computer Vision

Active Learning for Delineation of Curvilinear Structures

Gradient-based enhancement of tubular structures in medical images

Machine Learning Approaches for Predicting Radiation Therapy Outcomes: A Clinician's Perspective.

Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)

Superpixel Convolutional Networks Using Bilateral Inceptions

Doctor AI: Predicting Clinical Events via Recurrent Neural Networks

Classifying and segmenting microscopy images with deep multiple instance learning

Deeply-Recursive Convolutional Network for Image Super-Resolution

Efficient Training of Very Deep Neural Networks for Supervised Hashing

Supervised Hashing with Deep Neural Networks

Deep Feature Learning for EEG Recordings

Deep Gaussian Conditional Random Field Network: A Model-Based Deep Network for Discriminative Denoising

The Fast Bilateral Solver

Attention to Scale: Scale-Aware Semantic Image Segmentation

Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding

High quality surface reconstruction in radiotherapy: Cross-sectional contours to 3D mesh using wavelets

A vascular perspective on neuronal migration

Crowdsourcing the creation of image segmentation algorithms for connectomics

ZNN -- A Fast and Scalable Algorithm for Training 3D Convolutional Networks on Multi-core and Many-Core Shared Memory Machines

Neural networks in the future of neuroscience research

Cerebral microvascular pericytes and neurogliovascular signaling in health and disease

Automatic Feature Learning for Glaucoma Detection Based on Deep Learning

Multi-scale 3D convolutional neural networks for lesion segmentation in brain MRI

3D Deep Learning for Efficient and Robust Landmark Detection in Volumetric Data

Marginal Space Deep Learning: Efficient Architecture for Detection in Volumetric Image Data

Unregistered Multiview Mammogram Analysis with Pre-trained Deep Learning Models

Model Accuracy and Runtime Tradeoff in Distributed Deep Learning: A Systematic Study

Manipulating neuronal activity in the mouse brain with ultrasound: A comparison with optogenetic activation of the cerebral cortex

An integrated approach to quantitative modelling in angiogenesis research

Recursive Training of 2D-3D Convolutional Networks for Neuronal Boundary Detection

Introducing Geometry in Active Learning for Image Segmentation

Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool

Testing Foundations of Biological Scaling Theory Using Automated Measurements of Vascular Networks

Optical electrocorticogram (OECoG) using wide-field calcium imaging reveals the divergence of neuronal and glial activity during acute rodent seizures

Better reporting for better research: a checklist for reproducibility

Tools and techniques for computational reproducibility

Semi-supervised Learning with Ladder Networks

From the neuron doctrine to neural networks

Quantum dots: bright and versatile in vitro and in vivo fluorescence imaging biosensors.

Deep Edge-Aware Filters

The ImageJ ecosystem: An open platform for biomedical image analysis

Predicting Semantic Descriptions from Medical Images with Convolutional Neural Networks

Parallel Multi-Dimensional LSTM, With Application to Fast Biomedical Volumetric Image Segmentation

An Iterative Convolutional Neural Network Algorithm Improves Electron Microscopy Image Segmentation

An Ensemble of 2D Convolutional Neural Networks for Tumor Segmentation

Combinatorial Energy Learning for Image Segmentation

Spectral Representations for Convolutional Neural Networks

Retinal Artery-Vein Classification via Topology Estimation

Variational Dropout and the Local Reparameterization Trick

Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning

Open source tools for large-scale neuroscience

Probabilistic machine learning and artificial intelligence

A Bottom-Up Approach for Pancreas Segmentation Using Cascaded Superpixels and (Deep) Image Patch Labeling

Two-Photon Absorbing Dyes with Minimal Autofluorescence in Tissue Imaging: Application to in Vivo Imaging of Amyloid-β Plaques with a Negligible Background Signal.

U-Net: Convolutional Networks for Biomedical Image Segmentation

Brain tumor segmentation with Deep Neural Networks

Blind Depth-variant Deconvolution of 3D Data in Wide-field Fluorescence Microscopy