TY - GEN
T1 - Feature extraction and Cluster analysis of Pancreatic Pathological Image Based on Unsupervised Convolutional Neural Network
AU - Asanou, Konosuke
AU - Ono, Naoaki
AU - Iwamoto, Chika
AU - Ohuchida, Kenoki
AU - Shindo, Koji
AU - Kanaya, Shigehiko
PY - 2019/1/21
Y1 - 2019/1/21
N2 - In recent years, computer-aided diagnosis based on machine learning, mainly based on Convolutional Neural Network (CNN) has been studied and developed rapidly. Those methods are not only helpful for classification, but also useful for feature extraction from given images, especially encoding image data into discrete representation helps us obtain new knowledge. Previous researches showed that CNN can by trainded for not only dection of cancers but also classification of gene expression subtypes. Although most of these studies are based on supervised learning that needs curated pathological knowledge, it is useful to extract characteristic features in the given images, using unsupervised machine learning in order to obtain new pathological findings. We applied cluster analysis using CNN which is trained based on adversarial training and maximization of mutual information and showed that it can classify those pathological images into discrete categories. Next, we applied our model for comparison of the two staining method in order to evaluate the degree of malignancy according to fibrosis and cell differentiation. The results showed that encoding of the histopathological image into discrete representations helps us to interpret tumor images.
AB - In recent years, computer-aided diagnosis based on machine learning, mainly based on Convolutional Neural Network (CNN) has been studied and developed rapidly. Those methods are not only helpful for classification, but also useful for feature extraction from given images, especially encoding image data into discrete representation helps us obtain new knowledge. Previous researches showed that CNN can by trainded for not only dection of cancers but also classification of gene expression subtypes. Although most of these studies are based on supervised learning that needs curated pathological knowledge, it is useful to extract characteristic features in the given images, using unsupervised machine learning in order to obtain new pathological findings. We applied cluster analysis using CNN which is trained based on adversarial training and maximization of mutual information and showed that it can classify those pathological images into discrete categories. Next, we applied our model for comparison of the two staining method in order to evaluate the degree of malignancy according to fibrosis and cell differentiation. The results showed that encoding of the histopathological image into discrete representations helps us to interpret tumor images.
UR - http://www.scopus.com/inward/record.url?scp=85062517906&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85062517906&partnerID=8YFLogxK
U2 - 10.1109/BIBM.2018.8621323
DO - 10.1109/BIBM.2018.8621323
M3 - Conference contribution
AN - SCOPUS:85062517906
T3 - Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018
SP - 2738
EP - 2740
BT - Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018
A2 - Zheng, Huiru
A2 - Callejas, Zoraida
A2 - Griol, David
A2 - Wang, Haiying
A2 - Hu, Xiaohua
A2 - Schmidt, Harald
A2 - Baumbach, Jan
A2 - Dickerson, Julie
A2 - Zhang, Le
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018
Y2 - 3 December 2018 through 6 December 2018
ER -