TY - GEN
T1 - Mass detection using deep convolutional neural network for mammographic computer-aided diagnosis
AU - Suzuki, Shintaro
AU - Zhang, Xiaoyong
AU - Homma, Noriyasu
AU - Ichiji, Kei
AU - Sugita, Norihiro
AU - Kawasumi, Yusuke
AU - Ishibashi, Tadashi
AU - Yoshizawa, Makoto
N1 - Publisher Copyright:
© 2016 The Society of Instrument and Control Engineers - SICE.
PY - 2016/11/18
Y1 - 2016/11/18
N2 - In recent years, a deep convolutional neural network (DCNN) has attracted great attention due to its outstanding performance in recognition of natural images. However, the DCNN performance for medical image recognition is still uncertain because collecting a large amount of training data is difficult. To solve the problem of the DCNN, we adopt a transfer learning strategy, and demonstrate feasibilities of the DCNN and of the transfer learning strategy for mass detection in mammographic images. We adopt a DCNN architecture that consists of 8 layers with weight, including 5 convolutional layers, and 3 fully-connected layers in this study. We first train the DCNN using about 1.2 million natural images for classification of 1,000 classes. Then, we modify the last fully-connected layer of the DCNN and subsequently train the DCNN using 1,656 regions of interest in mammographic image for two classes classification: mass and normal. The detection test is conducted on 198 mammographic images including 99 mass images and 99 normal images. The experimental results showed that the sensitivity of the mass detection was 89.9 % and the false positive was 19.2 %. These results demonstrated that the DCNN trained by transfer learning strategy has a potential to be a key system for mammographic mass detection computer-aided diagnosis (CAD). In addition, to the best of our knowledge, our study is the first demonstration of the DCNN for mammographic CAD application.
AB - In recent years, a deep convolutional neural network (DCNN) has attracted great attention due to its outstanding performance in recognition of natural images. However, the DCNN performance for medical image recognition is still uncertain because collecting a large amount of training data is difficult. To solve the problem of the DCNN, we adopt a transfer learning strategy, and demonstrate feasibilities of the DCNN and of the transfer learning strategy for mass detection in mammographic images. We adopt a DCNN architecture that consists of 8 layers with weight, including 5 convolutional layers, and 3 fully-connected layers in this study. We first train the DCNN using about 1.2 million natural images for classification of 1,000 classes. Then, we modify the last fully-connected layer of the DCNN and subsequently train the DCNN using 1,656 regions of interest in mammographic image for two classes classification: mass and normal. The detection test is conducted on 198 mammographic images including 99 mass images and 99 normal images. The experimental results showed that the sensitivity of the mass detection was 89.9 % and the false positive was 19.2 %. These results demonstrated that the DCNN trained by transfer learning strategy has a potential to be a key system for mammographic mass detection computer-aided diagnosis (CAD). In addition, to the best of our knowledge, our study is the first demonstration of the DCNN for mammographic CAD application.
KW - Computer-Aided Diagnosis/Detection
KW - DCNN
KW - Deep Learning
KW - Medical and Welfare Systems
KW - Neural Networks
KW - Signal and/or Image Processing
KW - Transfer Learning
KW - mammogram
UR - http://www.scopus.com/inward/record.url?scp=85008248276&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85008248276&partnerID=8YFLogxK
U2 - 10.1109/SICE.2016.7749265
DO - 10.1109/SICE.2016.7749265
M3 - Conference contribution
AN - SCOPUS:85008248276
T3 - 2016 55th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2016
SP - 1382
EP - 1386
BT - 2016 55th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2016
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 55th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2016
Y2 - 20 September 2016 through 23 September 2016
ER -