Cerebral Micro-Bleed Detection Based on the Convolution Neural Network With Rank Based Average Pooling

Cerebral Micro-Bleed Detection Based on the Convolution Neural Network With Rank Based Average Pooling

Cerebral micro-bleed (CMB) is small perivascular hemosiderin deposits from leakage through cerebral small vessels. They can result from cerebra-vascular disease, dementia, or simply from normal aging. It can be visualized via the susceptibility weighted imaging (SWI). Based on the SWI, we propose to...

Full description

Bibliographic Details
Main Authors: Shuihua Wang, Yongyan Jiang, Xiaoxia Hou, Hong Cheng, Sidan Du
Format: Article
Language:English
Published: IEEE 2017-01-01
Series:IEEE Access
Subjects:
Convolutional neural network
cerebral micro-bleed
network structure
rank based average pooling
Online Access:https://ieeexplore.ieee.org/document/8013653/
id doaj-b853b9baae024d0db4483ead1455a9be
record_format Article
spelling doaj-b853b9baae024d0db4483ead1455a9be2021-03-29T20:04:38ZengIEEEIEEE Access2169-35362017-01-015165761658310.1109/ACCESS.2017.27365588013653Cerebral Micro-Bleed Detection Based on the Convolution Neural Network With Rank Based Average PoolingShuihua Wang0https://orcid.org/0000-0003-2238-6808Yongyan Jiang1Xiaoxia Hou2Hong Cheng3Sidan Du4School of Electronic Engineering, Nanjing University, Nanjing, ChinaCollege of Science, Zhongyuan University of Technology, Zhengzhou, ChinaDepartment of Neurology, First Affiliated Hospital of Nanjing Medical University, Nanjing, ChinaDepartment of Neurology, First Affiliated Hospital of Nanjing Medical University, Nanjing, ChinaSchool of Electronic Engineering, Nanjing University, Nanjing, ChinaCerebral micro-bleed (CMB) is small perivascular hemosiderin deposits from leakage through cerebral small vessels. They can result from cerebra-vascular disease, dementia, or simply from normal aging. It can be visualized via the susceptibility weighted imaging (SWI). Based on the SWI, we propose to use different structures of the CNN with rank-based average pooling to detect the CMB, and compare this method used in this paper to the current state-of-the-art methods. We can find that the CNN with five layers obtains the best performance, with a sensitivity of 96.94%, a specificity of 97.18%, and an accuracy of 97.18%.https://ieeexplore.ieee.org/document/8013653/Convolutional neural networkcerebral micro-bleednetwork structurerank based average pooling
collection DOAJ
language English
format Article
sources DOAJ
author Shuihua Wang
Yongyan Jiang
Xiaoxia Hou
Hong Cheng
Sidan Du
spellingShingle Shuihua Wang
Yongyan Jiang
Xiaoxia Hou
Hong Cheng
Sidan Du
Cerebral Micro-Bleed Detection Based on the Convolution Neural Network With Rank Based Average Pooling
IEEE Access
Convolutional neural network
cerebral micro-bleed
network structure
rank based average pooling
author_facet Shuihua Wang
Yongyan Jiang
Xiaoxia Hou
Hong Cheng
Sidan Du
author_sort Shuihua Wang
title Cerebral Micro-Bleed Detection Based on the Convolution Neural Network With Rank Based Average Pooling
title_short Cerebral Micro-Bleed Detection Based on the Convolution Neural Network With Rank Based Average Pooling
title_full Cerebral Micro-Bleed Detection Based on the Convolution Neural Network With Rank Based Average Pooling
title_fullStr Cerebral Micro-Bleed Detection Based on the Convolution Neural Network With Rank Based Average Pooling
title_full_unstemmed Cerebral Micro-Bleed Detection Based on the Convolution Neural Network With Rank Based Average Pooling
title_sort cerebral micro-bleed detection based on the convolution neural network with rank based average pooling
publisher IEEE
series IEEE Access
issn 2169-3536
publishDate 2017-01-01
description Cerebral micro-bleed (CMB) is small perivascular hemosiderin deposits from leakage through cerebral small vessels. They can result from cerebra-vascular disease, dementia, or simply from normal aging. It can be visualized via the susceptibility weighted imaging (SWI). Based on the SWI, we propose to use different structures of the CNN with rank-based average pooling to detect the CMB, and compare this method used in this paper to the current state-of-the-art methods. We can find that the CNN with five layers obtains the best performance, with a sensitivity of 96.94%, a specificity of 97.18%, and an accuracy of 97.18%.
topic Convolutional neural network
cerebral micro-bleed
network structure
rank based average pooling
url https://ieeexplore.ieee.org/document/8013653/
work_keys_str_mv AT shuihuawang cerebralmicrobleeddetectionbasedontheconvolutionneuralnetworkwithrankbasedaveragepooling
AT yongyanjiang cerebralmicrobleeddetectionbasedontheconvolutionneuralnetworkwithrankbasedaveragepooling
AT xiaoxiahou cerebralmicrobleeddetectionbasedontheconvolutionneuralnetworkwithrankbasedaveragepooling
AT hongcheng cerebralmicrobleeddetectionbasedontheconvolutionneuralnetworkwithrankbasedaveragepooling
AT sidandu cerebralmicrobleeddetectionbasedontheconvolutionneuralnetworkwithrankbasedaveragepooling
_version_ 1724195338987765760

Similar Items