The application of series multi-pooling convolutional neural networks for medical image segmentation

Feng Wang; Siwei Huang; Lei Shi; Weiguo Fan

doi:10.1177/1550147717748899

Back

The application of series multi-pooling convolutional neural networks for medical image segmentation

Journal article

Open access

Peer reviewed

The application of series multi-pooling convolutional neural networks for medical image segmentation

Feng Wang, Siwei Huang, Lei Shi and Weiguo Fan

International journal of distributed sensor networks, Vol.13(12), p.155014771774889

12/2017

DOI: 10.1177/1550147717748899

Files and links (1)

url

https://doi.org/10.1177/1550147717748899View

Published (Version of record) Open Access

Abstract

It is crucial to precisely classify the pixels in brain tumor tissues in the brain tumor image segmentation. However, the traditional segmentation method is somewhat restricted and the segmentation accuracy cannot meet the real requirements because of the randomness of brain tumors’ spatial location in the brain. To solve the said problems, the model of convolutional neural network in the deep learning approach was used in this article to cope with classification and labeling tasks of brain tumor images. The main contents of this article were studied as follows: the principle and operating approach of convolutional neural network on image processing was first introduced, and then 12-layer convolutions were skillfully set up for local pathways based on two-way convolutional neural network architectures; considering the inter-label dependency in pixel areas, the situation of conditional random field was simulated to design the input series connection structure; multi-pooling input series connection model was designed to solve the problem that the input pixel area is limited; finally, the classification accuracy upon experiments reached 83%, which has verified the effectiveness of model to improve.

Details

Title: Subtitle: The application of series multi-pooling convolutional neural networks for medical image segmentation
Creators: Feng Wang - Taiyuan University of Technology
Siwei Huang - College of Information Engineering, Taiyuan University of Technology, Taiyuan, P.R. China
Lei Shi - College of Information Engineering, Taiyuan University of Technology, Taiyuan, P.R. China
Weiguo Fan - College of Information Engineering, Taiyuan University of Technology, Taiyuan, P.R. China, Virginia Polytechnic Institute and State University, Blacksburg, VA, USA
Resource Type: Journal article
Publication Details: International journal of distributed sensor networks, Vol.13(12), p.155014771774889
DOI: 10.1177/1550147717748899
ISSN: 1550-1477
eISSN: 1550-1477
Language: English
Date published: 12/2017
Academic Unit: Business Analytics
Record Identifier: 9984083828202771

Metrics

23 Record Views

9 Times Cited - Web of Science