Neuron Segmentation Using Deep Complete Bipartite Networks

05/31/2017
by   Jianxu Chen, et al.
0

In this paper, we consider the problem of automatically segmenting neuronal cells in dual-color confocal microscopy images. This problem is a key task in various quantitative analysis applications in neuroscience, such as tracing cell genesis in Danio rerio (zebrafish) brains. Deep learning, especially using fully convolutional networks (FCN), has profoundly changed segmentation research in biomedical imaging. We face two major challenges in this problem. First, neuronal cells may form dense clusters, making it difficult to correctly identify all individual cells (even to human experts). Consequently, segmentation results of the known FCN-type models are not accurate enough. Second, pixel-wise ground truth is difficult to obtain. Only a limited amount of approximate instance-wise annotation can be collected, which makes the training of FCN models quite cumbersome. We propose a new FCN-type deep learning model, called deep complete bipartite networks (CB-Net), and a new scheme for leveraging approximate instance-wise annotation to train our pixel-wise prediction model. Evaluated using seven real datasets, our proposed new CB-Net model outperforms the state-of-the-art FCN models and produces neuron segmentation results of remarkable quality

READ FULL TEXT

page 3

page 6

page 8

research
12/05/2017

Fully Automatic Segmentation of Lumbar Vertebrae from CT Images using Cascaded 3D Fully Convolutional Networks

We present a method to address the challenging problem of segmentation o...
research
04/15/2023

An Instance Segmentation Dataset of Yeast Cells in Microstructures

Extracting single-cell information from microscopy data requires accurat...
research
12/30/2016

Automatic labeling of molecular biomarkers of whole slide immunohistochemistry images using fully convolutional networks

This paper addresses the problem of quantifying biomarkers in multi-stai...
research
05/21/2019

Task Decomposition and Synchronization for Semantic Biomedical Image Segmentation

Semantic segmentation is essentially important to biomedical image analy...
research
01/25/2019

Joint shape learning and segmentation for medical images using a minimalistic deep network

Recently, state-of-the-art results have been achieved in semantic segmen...
research
02/22/2022

An Object Aware Hybrid U-Net for Breast Tumour Annotation

In the clinical settings, during digital examination of histopathologica...
research
02/24/2021

Automatic Cell Counting in Flourescent Microscopy Using Deep Learning

Counting cells in fluorescent microscopy is a tedious, time-consuming ta...

Please sign up or login with your details

Forgot password? Click here to reset