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

Quan, Tran Minh and Hildebrand, David Grant Colburn and Jeong, Won-Ki (2021) FusionNet: A Deep Fully Residual Convolutional Neural Network for Image Segmentation in Connectomics. Frontiers in Computer Science, 3. ISSN 2624-9898

[thumbnail of pubmed-zip/versions/1/package-entries/fcomp-03-613981.pdf] Text
pubmed-zip/versions/1/package-entries/fcomp-03-613981.pdf - Published Version

Download (3MB)

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.

Item Type: Article
Subjects: STM Library > Computer Science
Depositing User: Managing Editor
Date Deposited: 19 Dec 2022 12:38
Last Modified: 01 Jan 2024 12:44
URI: http://open.journal4submit.com/id/eprint/291

Actions (login required)

View Item
View Item