TY - GEN
T1 - Cervical Histopathology Image Classification Using Ensembled Transfer Learning
AU - Li, Chen
AU - Xue, Dan
AU - Kong, Fanjie
AU - Hu, Zhijie
AU - Chen, Hao
AU - Yao, Yudong
AU - Sun, Hongzan
AU - Zhang, Le
AU - Zhang, Jinpeng
AU - Jiang, Tao
AU - Yuan, Jianying
AU - Xu, Ning
N1 - Publisher Copyright:
© 2019, Springer Nature Switzerland AG.
PY - 2019
Y1 - 2019
N2 - In recent years, Transfer Learning makes a great breakthrough in the field of machine learning, and the use of transfer learning technology in Cervical Histopathology Image Classification (CHIC) becomes a new research domain. In this paper, we propose an Ensembled Transfer Learning (ETL) framework to classify well, moderately and poorly differentiated cervical histopathology images. In this ETL framework, Inception-V3 and VGG-16 based transfer learning structures are first built up. Then, a fine-tuning approach is applied to extract effective deep learning features from these two structures. Finally, a late fusion based ensemble learning strategy is designed for the final classification. In the experiment, a practical dataset with 100 VEGF stained cervical histopathology images is applied to test the proposed ETL method in the CHIC task, and an average accuracy of 80% is achieved.
AB - In recent years, Transfer Learning makes a great breakthrough in the field of machine learning, and the use of transfer learning technology in Cervical Histopathology Image Classification (CHIC) becomes a new research domain. In this paper, we propose an Ensembled Transfer Learning (ETL) framework to classify well, moderately and poorly differentiated cervical histopathology images. In this ETL framework, Inception-V3 and VGG-16 based transfer learning structures are first built up. Then, a fine-tuning approach is applied to extract effective deep learning features from these two structures. Finally, a late fusion based ensemble learning strategy is designed for the final classification. In the experiment, a practical dataset with 100 VEGF stained cervical histopathology images is applied to test the proposed ETL method in the CHIC task, and an average accuracy of 80% is achieved.
KW - Cervical cancer
KW - Classification
KW - Deep learning
KW - Differentiation stages
KW - Ensemble learning
KW - Histopathology image
KW - Transfer learning
UR - https://www.scopus.com/pages/publications/85070760761
UR - https://www.scopus.com/pages/publications/85070760761#tab=citedBy
U2 - 10.1007/978-3-030-23762-2_3
DO - 10.1007/978-3-030-23762-2_3
M3 - Conference contribution
AN - SCOPUS:85070760761
SN - 9783030237615
T3 - Advances in Intelligent Systems and Computing
SP - 26
EP - 37
BT - Information Technology in Biomedicine, 2019
A2 - Pietka, Ewa
A2 - Badura, Pawel
A2 - Kawa, Jacek
A2 - Wieclawek, Wojciech
T2 - 7th International Conference on Information Technology in Biomedicine, ITIB 2019
Y2 - 18 June 2019 through 20 June 2019
ER -
