TY - GEN
T1 - Detection of cerebral microbleeding based on deep convolutional neural network
AU - Lu, Siyuan
AU - Lu, Zhihai
AU - Hou, Xiaoxia
AU - Cheng, Hong
AU - Wang, Shuihua
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/10/20
Y1 - 2017/10/20
N2 - Background and Objective Cerebral microbleeding (CMB) is associated with many brain diseases, such as dementia and vascular disease. CMBs can be detected by brain magnetic resonance imaging (MRI). Susceptibility weighted imaging (SWI) is commonly employed since it can give better sensitivity than standard MRI. However, CMBs are usually small and they can be distributed throughout brain, manual analysis is arduous and tedious. We proposed to use deep learning methods to detect CMBs. First, we collected 64 brain SWI. We used a sliding window size of 61×61 pixel to generate 10000 samples. Then, we labeled the samples as non-CMB or CMB manually. Finally, we employed convolutional neural network (CNN) for classification. Results In the experiment, we used 8000 samples to train the CNN, the rest 2000 for testing. The proposed method yielded a sensitivity of 97.29%, a specificity of92.23%, and an overall accuracy of 96.05%. Conclusions The results suggested our method can detect and locate CMBs automatically and accurately.
AB - Background and Objective Cerebral microbleeding (CMB) is associated with many brain diseases, such as dementia and vascular disease. CMBs can be detected by brain magnetic resonance imaging (MRI). Susceptibility weighted imaging (SWI) is commonly employed since it can give better sensitivity than standard MRI. However, CMBs are usually small and they can be distributed throughout brain, manual analysis is arduous and tedious. We proposed to use deep learning methods to detect CMBs. First, we collected 64 brain SWI. We used a sliding window size of 61×61 pixel to generate 10000 samples. Then, we labeled the samples as non-CMB or CMB manually. Finally, we employed convolutional neural network (CNN) for classification. Results In the experiment, we used 8000 samples to train the CNN, the rest 2000 for testing. The proposed method yielded a sensitivity of 97.29%, a specificity of92.23%, and an overall accuracy of 96.05%. Conclusions The results suggested our method can detect and locate CMBs automatically and accurately.
KW - Cerebral microbleeding
KW - Computer-aided Diagnosis
KW - Convolutional Neural Network
KW - Deep Learning
KW - Machine Learning
UR - http://www.scopus.com/inward/record.url?scp=85050680539&partnerID=8YFLogxK
U2 - 10.1109/ICCWAMTIP.2017.8301456
DO - 10.1109/ICCWAMTIP.2017.8301456
M3 - Conference Proceeding
AN - SCOPUS:85050680539
T3 - 2016 13th International Computer Conference on Wavelet Active Media Technology and Information Processing, ICCWAMTIP 2017
SP - 93
EP - 96
BT - 2016 13th International Computer Conference on Wavelet Active Media Technology and Information Processing, ICCWAMTIP 2017
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 14th International Computer Conference on Wavelet Active Media Technology and Information Processing, ICCWAMTIP 2017
Y2 - 15 December 2017 through 17 December 2017
ER -