FusionNet: A Deep Fully Residual Convolutional Neural Network for Image Segmentation in Connectomics

Published in

(2016)

External Links:

Generate Graph DownloadPDF

TL;DR

A deep neural network architecture, FusionNet, is introduced with a focus on its application to accomplish automatic segmentation of neuronal structures in connectomics data, which results in a much deeper network architecture and improves segmentation accuracy.

Abstract

Cellular-resolution connectomics is an ambitious research direction with the goal of generating comprehensive brain connectivity maps using high-throughput, nano-scale electron microscopy. One of the main challenges in connectomics research is developing scalable image analysis algorithms that require minimal user intervention. Deep learning has provided exceptional performance in image classification tasks in computer vision, leading to a recent explosion in popularity. Similarly, its application to connectomic analyses holds great promise. Here, we introduce a deep neural network architecture, FusionNet, with a focus on its application to accomplish automatic segmentation of neuronal structures in connectomics data. FusionNet combines recent advances in machine learning, such as semantic segmentation and residual neural networks, with summation-based skip connections. This results in a much deeper network architecture and improves segmentation accuracy. We demonstrate the performance of the proposed method by comparing it with several other popular electron microscopy segmentation methods. We further illustrate its flexibility through segmentation results for two different tasks: cell membrane segmentation and cell nucleus segmentation.

Authors

Tran Minh Quan

1 papers

David Grant Colburn Hildebrand

1 papers

W. Jeong

1 papers

References58 items

PatchPerPix for Instance Segmentation

ACE-Net: Biomedical Image Segmentation with Augmented Contracting and Expansive Paths

High-throughput transmission electron microscopy with automated serial sectioning

Leveraging Domain Knowledge to Improve Microscopy Image Segmentation With Lifted Multicuts

The Mutex Watershed and its Objective: Efficient, Parameter-Free Image Partitioning

FusionNet: A Deep Fully Residual Convolutional Neural Network for Image Segmentation in Connectomics

Published in

(2016)

External Links:

Generate Graph DownloadPDF

TL;DR

Abstract

Authors

Tran Minh Quan

1 papers

David Grant Colburn Hildebrand

1 papers

W. Jeong

1 papers

References58 items

PatchPerPix for Instance Segmentation

ACE-Net: Biomedical Image Segmentation with Augmented Contracting and Expansive Paths

High-throughput transmission electron microscopy with automated serial sectioning

Leveraging Domain Knowledge to Improve Microscopy Image Segmentation With Lifted Multicuts

The Mutex Watershed and its Objective: Efficient, Parameter-Free Image Partitioning

Multi-Beam Scanning Electron Microscopy for High-Throughput Imaging in Connectomics Research

DeepHCS: Bright-Field to Fluorescence Microscopy Image Conversion Using Deep Learning for Label-Free High-Content Screening

Deep contextual residual network for electron microscopy image segmentation in connectomics

Learning Steerable Filters for Rotation Equivariant CNNs

TL;DR

Abstract

Authors

References58 items

PatchPerPix for Instance Segmentation

ACE-Net: Biomedical Image Segmentation with Augmented Contracting and Expansive Paths

High-throughput transmission electron microscopy with automated serial sectioning

Leveraging Domain Knowledge to Improve Microscopy Image Segmentation With Lifted Multicuts

The Mutex Watershed and its Objective: Efficient, Parameter-Free Image Partitioning

TL;DR

Abstract

Authors

References58 items

PatchPerPix for Instance Segmentation

ACE-Net: Biomedical Image Segmentation with Augmented Contracting and Expansive Paths

High-throughput transmission electron microscopy with automated serial sectioning

Leveraging Domain Knowledge to Improve Microscopy Image Segmentation With Lifted Multicuts

The Mutex Watershed and its Objective: Efficient, Parameter-Free Image Partitioning

Multi-Beam Scanning Electron Microscopy for High-Throughput Imaging in Connectomics Research

DeepHCS: Bright-Field to Fluorescence Microscopy Image Conversion Using Deep Learning for Label-Free High-Content Screening

Deep contextual residual network for electron microscopy image segmentation in connectomics

Learning Steerable Filters for Rotation Equivariant CNNs

Compressed Sensing MRI Reconstruction Using a Generative Adversarial Network With a Cyclic Loss

A Complete Electron Microscopy Volume of the Brain of Adult Drosophila melanogaster

Whole-brain serial-section electron microscopy in larval zebrafish

Multi-stage Multi-recursive-input Fully Convolutional Networks for Neuronal Boundary Detection

Residual Deconvolutional Networks for Brain Electron Microscopy Image Segmentation

Multicut brings automated neurite segmentation closer to human performance

Review of MRI-based Brain Tumor Image Segmentation Using Deep Learning Methods

An Efficient Fusion Move Algorithm for the Minimum Cost Lifted Multicut Problem

Registering large volume serial-section electron microscopy image sets for neural circuit reconstruction using FFT signal whitening

Combining Fully Convolutional and Recurrent Neural Networks for 3D Biomedical Image Segmentation

The Importance of Skip Connections in Biomedical Image Segmentation

Deep models for brain EM image segmentation: novel insights and improved performance

Semantic segmentation of bioimages using convolutional neural networks

Image Style Transfer Using Convolutional Neural Networks

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

Deep Contextual Networks for Neuronal Structure Segmentation

Deep Residual Learning for Image Recognition

Efficient Classifier Training to Minimize False Merges in Electron Microscopy Segmentation

Crowdsourcing the creation of image segmentation algorithms for connectomics

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

Saturated Reconstruction of a Volume of Neocortex

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

An Iterative Convolutional Neural Network Algorithm Improves Electron Microscopy Image Segmentation

U-Net: Convolutional Networks for Biomedical Image Segmentation

Whole-brain functional and structural examination in larval zebrafish

Fully convolutional networks for semantic segmentation

Going deeper with convolutions

Very Deep Convolutional Networks for Large-Scale Image Recognition

ImageNet Large Scale Visual Recognition Challenge

Imaging ATUM ultrathin section libraries with WaferMapper: a multi-scale approach to EM reconstruction of neural circuits

Network In Network

Visualizing and Understanding Convolutional Networks

Cellular-resolution connectomics: challenges of dense neural circuit reconstruction

Large-Scale Automatic Reconstruction of Neuronal Processes from Electron Microscopy Images

Deep Neural Networks Segment Neuronal Membranes in Electron Microscopy Images

ImageNet classification with deep convolutional neural networks

Fiji: an open-source platform for biological-image analysis

TrakEM2 Software for Neural Circuit Reconstruction

The Big and the Small: Challenges of Imaging the Brain’s Circuits

Ilastik: Interactive learning and segmentation toolkit

Wiring specificity in the direction-selectivity circuit of the retina

Network anatomy and in vivo physiology of visual cortical neurons

An Integrated Micro- and Macroarchitectural Analysis of the Drosophila Brain by Computer-Assisted Serial Section Electron Microscopy

Ssecrett and NeuroTrace: Interactive Visualization and Analysis Tools for Large-Scale Neuroscience Data Sets

Convolutional Networks Can Learn to Generate Affinity Graphs for Image Segmentation

Deep Learning

Keras: Deep learning library for theano and tensorflow

3D reconstruction of neurons in electron microscopy images

Matrix-based Multigrid

Field of Study