Cerebral Microbleed Detection via Convolutional Neural Network and Extreme Learning Machine
Aim: Cerebral microbleeds (CMBs) are small round dots distributed over the brain which contribute to stroke, dementia, and death. The early diagnosis is significant for the treatment.Method: In this paper, a new CMB detection approach was put forward for brain magnetic resonance images. We leveraged...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2021-09-01
|
Series: | Frontiers in Computational Neuroscience |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fncom.2021.738885/full |
id |
doaj-6294b37515e945988be608a6057e7b5b |
---|---|
record_format |
Article |
spelling |
doaj-6294b37515e945988be608a6057e7b5b2021-09-10T05:52:08ZengFrontiers Media S.A.Frontiers in Computational Neuroscience1662-51882021-09-011510.3389/fncom.2021.738885738885Cerebral Microbleed Detection via Convolutional Neural Network and Extreme Learning MachineSiyuan Lu0Shuaiqi Liu1Shui-Hua Wang2Yu-Dong Zhang3School of Informatics, University of Leicester, Leicester, United KingdomCollege of Electronic and Information Engineering, Hebei University, Baoding, ChinaSchool of Mathematics and Actuarial Science, University of Leicester, Leicester, United KingdomSchool of Informatics, University of Leicester, Leicester, United KingdomAim: Cerebral microbleeds (CMBs) are small round dots distributed over the brain which contribute to stroke, dementia, and death. The early diagnosis is significant for the treatment.Method: In this paper, a new CMB detection approach was put forward for brain magnetic resonance images. We leveraged a sliding window to obtain training and testing samples from input brain images. Then, a 13-layer convolutional neural network (CNN) was designed and trained. Finally, we proposed to utilize an extreme learning machine (ELM) to substitute the last several layers in the CNN for detection. We carried out an experiment to decide the optimal number of layers to be substituted. The parameters in ELM were optimized by a heuristic algorithm named bat algorithm. The evaluation of our approach was based on hold-out validation, and the final predictions were generated by averaging the performance of five runs.Results: Through the experiments, we found replacing the last five layers with ELM can get the optimal results.Conclusion: We offered a comparison with state-of-the-art algorithms, and it can be revealed that our method was accurate in CMB detection.https://www.frontiersin.org/articles/10.3389/fncom.2021.738885/fullcomputer-aided diagnosisdeep learningconvolutional neural networkextreme learning machinebat algorithm |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Siyuan Lu Shuaiqi Liu Shui-Hua Wang Yu-Dong Zhang |
spellingShingle |
Siyuan Lu Shuaiqi Liu Shui-Hua Wang Yu-Dong Zhang Cerebral Microbleed Detection via Convolutional Neural Network and Extreme Learning Machine Frontiers in Computational Neuroscience computer-aided diagnosis deep learning convolutional neural network extreme learning machine bat algorithm |
author_facet |
Siyuan Lu Shuaiqi Liu Shui-Hua Wang Yu-Dong Zhang |
author_sort |
Siyuan Lu |
title |
Cerebral Microbleed Detection via Convolutional Neural Network and Extreme Learning Machine |
title_short |
Cerebral Microbleed Detection via Convolutional Neural Network and Extreme Learning Machine |
title_full |
Cerebral Microbleed Detection via Convolutional Neural Network and Extreme Learning Machine |
title_fullStr |
Cerebral Microbleed Detection via Convolutional Neural Network and Extreme Learning Machine |
title_full_unstemmed |
Cerebral Microbleed Detection via Convolutional Neural Network and Extreme Learning Machine |
title_sort |
cerebral microbleed detection via convolutional neural network and extreme learning machine |
publisher |
Frontiers Media S.A. |
series |
Frontiers in Computational Neuroscience |
issn |
1662-5188 |
publishDate |
2021-09-01 |
description |
Aim: Cerebral microbleeds (CMBs) are small round dots distributed over the brain which contribute to stroke, dementia, and death. The early diagnosis is significant for the treatment.Method: In this paper, a new CMB detection approach was put forward for brain magnetic resonance images. We leveraged a sliding window to obtain training and testing samples from input brain images. Then, a 13-layer convolutional neural network (CNN) was designed and trained. Finally, we proposed to utilize an extreme learning machine (ELM) to substitute the last several layers in the CNN for detection. We carried out an experiment to decide the optimal number of layers to be substituted. The parameters in ELM were optimized by a heuristic algorithm named bat algorithm. The evaluation of our approach was based on hold-out validation, and the final predictions were generated by averaging the performance of five runs.Results: Through the experiments, we found replacing the last five layers with ELM can get the optimal results.Conclusion: We offered a comparison with state-of-the-art algorithms, and it can be revealed that our method was accurate in CMB detection. |
topic |
computer-aided diagnosis deep learning convolutional neural network extreme learning machine bat algorithm |
url |
https://www.frontiersin.org/articles/10.3389/fncom.2021.738885/full |
work_keys_str_mv |
AT siyuanlu cerebralmicrobleeddetectionviaconvolutionalneuralnetworkandextremelearningmachine AT shuaiqiliu cerebralmicrobleeddetectionviaconvolutionalneuralnetworkandextremelearningmachine AT shuihuawang cerebralmicrobleeddetectionviaconvolutionalneuralnetworkandextremelearningmachine AT yudongzhang cerebralmicrobleeddetectionviaconvolutionalneuralnetworkandextremelearningmachine |
_version_ |
1717758610441764864 |