Next Article in Journal
New Similarity Measures of Single-Valued Neutrosophic Multisets Based on the Decomposition Theorem and Its Application in Medical Diagnosis
Next Article in Special Issue
Low-Rank Multi-Channel Features for Robust Visual Object Tracking
Previous Article in Journal
The Structure Theorems of Pseudo-BCI Algebras in Which Every Element is Quasi-Maximal
Previous Article in Special Issue
Deep Learning-Based Multinational Banknote Fitness Classification with a Combination of Visible-Light Reflection and Infrared-Light Transmission Images
Open AccessArticle

An Adversarial and Densely Dilated Network for Connectomes Segmentation

by 1, 1, 1,2,* and 1,*
School of Software Enginnering, Tongji University, Shanghai 201804, China
Institute of Translational Medicine, Tongji University, Shanghai 201804, China
Authors to whom correspondence should be addressed.
Symmetry 2018, 10(10), 467;
Received: 28 August 2018 / Revised: 5 October 2018 / Accepted: 8 October 2018 / Published: 9 October 2018
(This article belongs to the Special Issue Deep Learning-Based Biometric Technologies)
Automatic reconstructing of neural circuits in the brain is one of the most crucial studies in neuroscience. Connectomes segmentation plays an important role in reconstruction from electron microscopy (EM) images; however, it is rather challenging due to highly anisotropic shapes with inferior quality and various thickness. In our paper, we propose a novel connectomes segmentation framework called adversarial and densely dilated network (ADDN) to address these issues. ADDN is based on the conditional Generative Adversarial Network (cGAN) structure which is the latest advance in machine learning with power to generate images similar to the ground truth especially when the training data is limited. Specifically, we design densely dilated network (DDN) as the segmentor to allow a deeper architecture and larger receptive fields for more accurate segmentation. Discriminator is trained to distinguish generated segmentation from manual segmentation. During training, such adversarial loss function is optimized together with dice loss. Extensive experimental results demonstrate that our ADDN is effective for such connectomes segmentation task, helping to retrieve more accurate segmentation and attenuate the blurry effects of generated boundary map. Our method obtains state-of-the-art performance while requiring less computation on ISBI 2012 EM dataset and mouse piriform cortex dataset. View Full-Text
Keywords: electron microscopy images; connectomes segmentation; adversarial training; densely dilated network; cGAN electron microscopy images; connectomes segmentation; adversarial training; densely dilated network; cGAN
Show Figures

Figure 1

MDPI and ACS Style

Chen, K.; Zhu, D.; Lu, J.; Luo, Y. An Adversarial and Densely Dilated Network for Connectomes Segmentation. Symmetry 2018, 10, 467.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map

Back to TopTop