Sparse autoencoder based deep neural network for voxelwise detection of cerebral microbleed

Yu Dong Zhang; Xiao Xia Hou; Yi Ding Lv; Hong Chen; Yin Zhang; Shui Hua Wang

doi:10.1109/ICPADS.2016.0166

Sparse autoencoder based deep neural network for voxelwise detection of cerebral microbleed

Yu Dong Zhang, Xiao Xia Hou, Yi Ding Lv, Hong Chen, Yin Zhang, Shui Hua Wang^*

^*Corresponding author for this work

Research output: Chapter in Book or Report/Conference proceeding › Conference Proceeding › peer-review

20 Citations (Scopus)

Abstract

In order to detect cerebral microbleed more efficiently, we developed a novel computer-aided detection method based on susceptibility-weighted imaging. We enrolled five CADASIL patients and five healthy controls. We used a 20x20 neighboring window to generate samples on each slice of the volumetric brain images. The sparse autoencoder (SAE) was used to unsupervised feature learning. Then, a deep neural network was established using the learned features. The results over 10x10-fold cross validation showed our method yielded a sensitivity of 93.20±1.37%, a specificity of 93.25±1.38%, and an accuracy of 93.22±1.37%. Our result is better than Roy's method, which was proposed in 2015.

Original language	English
Title of host publication	Proceedings - 22nd IEEE International Conference on Parallel and Distributed Systems, ICPADS 2016
Editors	Xiaofei Liao, Robert Lovas, Xipeng Shen, Ran Zheng
Publisher	IEEE Computer Society
Pages	1229-1232
Number of pages	4
ISBN (Electronic)	9781509044573
DOIs	https://doi.org/10.1109/ICPADS.2016.0166
Publication status	Published - 2 Jul 2016
Externally published	Yes
Event	22nd IEEE International Conference on Parallel and Distributed Systems, ICPADS 2016 - Wuhan, Hubei, China Duration: 13 Dec 2016 → 16 Dec 2016

Publication series

Name	Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS
Volume	0
ISSN (Print)	1521-9097

Conference

Conference	22nd IEEE International Conference on Parallel and Distributed Systems, ICPADS 2016
Country/Territory	China
City	Wuhan, Hubei
Period	13/12/16 → 16/12/16

Keywords

Cerebral microbleed
Cross validation
Deep neural network
Sparse autoencoder
Susceptibility weighted imaging

Access to Document

10.1109/ICPADS.2016.0166

Cite this

Zhang, Y. D., Hou, X. X., Lv, Y. D., Chen, H., Zhang, Y., & Wang, S. H. (2016). Sparse autoencoder based deep neural network for voxelwise detection of cerebral microbleed. In X. Liao, R. Lovas, X. Shen, & R. Zheng (Eds.), Proceedings - 22nd IEEE International Conference on Parallel and Distributed Systems, ICPADS 2016 (pp. 1229-1232). Article 7823881 (Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS; Vol. 0). IEEE Computer Society. https://doi.org/10.1109/ICPADS.2016.0166

Zhang, Yu Dong ; Hou, Xiao Xia ; Lv, Yi Ding et al. / Sparse autoencoder based deep neural network for voxelwise detection of cerebral microbleed. Proceedings - 22nd IEEE International Conference on Parallel and Distributed Systems, ICPADS 2016. editor / Xiaofei Liao ; Robert Lovas ; Xipeng Shen ; Ran Zheng. IEEE Computer Society, 2016. pp. 1229-1232 (Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS).

@inproceedings{74b078f3ca3e41deb4d3f8124c95f781,

title = "Sparse autoencoder based deep neural network for voxelwise detection of cerebral microbleed",

abstract = "In order to detect cerebral microbleed more efficiently, we developed a novel computer-aided detection method based on susceptibility-weighted imaging. We enrolled five CADASIL patients and five healthy controls. We used a 20x20 neighboring window to generate samples on each slice of the volumetric brain images. The sparse autoencoder (SAE) was used to unsupervised feature learning. Then, a deep neural network was established using the learned features. The results over 10x10-fold cross validation showed our method yielded a sensitivity of 93.20±1.37%, a specificity of 93.25±1.38%, and an accuracy of 93.22±1.37%. Our result is better than Roy's method, which was proposed in 2015.",

keywords = "Cerebral microbleed, Cross validation, Deep neural network, Sparse autoencoder, Susceptibility weighted imaging",

author = "Zhang, {Yu Dong} and Hou, {Xiao Xia} and Lv, {Yi Ding} and Hong Chen and Yin Zhang and Wang, {Shui Hua}",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 22nd IEEE International Conference on Parallel and Distributed Systems, ICPADS 2016 ; Conference date: 13-12-2016 Through 16-12-2016",

year = "2016",

month = jul,

day = "2",

doi = "10.1109/ICPADS.2016.0166",

language = "English",

series = "Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS",

publisher = "IEEE Computer Society",

pages = "1229--1232",

editor = "Xiaofei Liao and Robert Lovas and Xipeng Shen and Ran Zheng",

booktitle = "Proceedings - 22nd IEEE International Conference on Parallel and Distributed Systems, ICPADS 2016",

}

Zhang, YD, Hou, XX, Lv, YD, Chen, H, Zhang, Y & Wang, SH 2016, Sparse autoencoder based deep neural network for voxelwise detection of cerebral microbleed. in X Liao, R Lovas, X Shen & R Zheng (eds), Proceedings - 22nd IEEE International Conference on Parallel and Distributed Systems, ICPADS 2016., 7823881, Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS, vol. 0, IEEE Computer Society, pp. 1229-1232, 22nd IEEE International Conference on Parallel and Distributed Systems, ICPADS 2016, Wuhan, Hubei, China, 13/12/16. https://doi.org/10.1109/ICPADS.2016.0166

Sparse autoencoder based deep neural network for voxelwise detection of cerebral microbleed. / Zhang, Yu Dong; Hou, Xiao Xia; Lv, Yi Ding et al.
Proceedings - 22nd IEEE International Conference on Parallel and Distributed Systems, ICPADS 2016. ed. / Xiaofei Liao; Robert Lovas; Xipeng Shen; Ran Zheng. IEEE Computer Society, 2016. p. 1229-1232 7823881 (Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS; Vol. 0).

Research output: Chapter in Book or Report/Conference proceeding › Conference Proceeding › peer-review

TY - GEN

T1 - Sparse autoencoder based deep neural network for voxelwise detection of cerebral microbleed

AU - Zhang, Yu Dong

AU - Hou, Xiao Xia

AU - Lv, Yi Ding

AU - Chen, Hong

AU - Zhang, Yin

AU - Wang, Shui Hua

PY - 2016/7/2

Y1 - 2016/7/2

N2 - In order to detect cerebral microbleed more efficiently, we developed a novel computer-aided detection method based on susceptibility-weighted imaging. We enrolled five CADASIL patients and five healthy controls. We used a 20x20 neighboring window to generate samples on each slice of the volumetric brain images. The sparse autoencoder (SAE) was used to unsupervised feature learning. Then, a deep neural network was established using the learned features. The results over 10x10-fold cross validation showed our method yielded a sensitivity of 93.20±1.37%, a specificity of 93.25±1.38%, and an accuracy of 93.22±1.37%. Our result is better than Roy's method, which was proposed in 2015.

AB - In order to detect cerebral microbleed more efficiently, we developed a novel computer-aided detection method based on susceptibility-weighted imaging. We enrolled five CADASIL patients and five healthy controls. We used a 20x20 neighboring window to generate samples on each slice of the volumetric brain images. The sparse autoencoder (SAE) was used to unsupervised feature learning. Then, a deep neural network was established using the learned features. The results over 10x10-fold cross validation showed our method yielded a sensitivity of 93.20±1.37%, a specificity of 93.25±1.38%, and an accuracy of 93.22±1.37%. Our result is better than Roy's method, which was proposed in 2015.

KW - Cerebral microbleed

KW - Cross validation

KW - Deep neural network

KW - Sparse autoencoder

KW - Susceptibility weighted imaging

UR - http://www.scopus.com/inward/record.url?scp=85018503992&partnerID=8YFLogxK

U2 - 10.1109/ICPADS.2016.0166

DO - 10.1109/ICPADS.2016.0166

M3 - Conference Proceeding

AN - SCOPUS:85018503992

T3 - Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS

SP - 1229

EP - 1232

BT - Proceedings - 22nd IEEE International Conference on Parallel and Distributed Systems, ICPADS 2016

A2 - Liao, Xiaofei

A2 - Lovas, Robert

A2 - Shen, Xipeng

A2 - Zheng, Ran

PB - IEEE Computer Society

T2 - 22nd IEEE International Conference on Parallel and Distributed Systems, ICPADS 2016

Y2 - 13 December 2016 through 16 December 2016

ER -

Zhang YD, Hou XX, Lv YD, Chen H, Zhang Y, Wang SH. Sparse autoencoder based deep neural network for voxelwise detection of cerebral microbleed. In Liao X, Lovas R, Shen X, Zheng R, editors, Proceedings - 22nd IEEE International Conference on Parallel and Distributed Systems, ICPADS 2016. IEEE Computer Society. 2016. p. 1229-1232. 7823881. (Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS). doi: 10.1109/ICPADS.2016.0166

Sparse autoencoder based deep neural network for voxelwise detection of cerebral microbleed

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this