Stacked Sparse Autoencoder (SSAE) based framework for nuclei patch classification on breast cancer histopathology

In this paper, a Stacked Sparse Autoencoder (SSAE) based framework is presented for nuclei classification on breast cancer histopathology. SSAE works very well in learning useful high-level feature for better representation of input raw data. To show the effectiveness of proposed framework, SSAE+Sof...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings (International Symposium on Biomedical Imaging) pp. 999 - 1002
Main Authors: Jun Xu, Lei Xiang, Renlong Hang, Jianzhong Wu
Format: Conference Proceeding
Language:English
Published: IEEE 01.04.2014
Subjects:
Breast cancer
Breast Cancer Histopathology
Decoding
Deep learning
Neural networks
Principal component analysis
Sparse Autoencoder
Testing
Training
ISSN:1945-7928
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, a Stacked Sparse Autoencoder (SSAE) based framework is presented for nuclei classification on breast cancer histopathology. SSAE works very well in learning useful high-level feature for better representation of input raw data. To show the effectiveness of proposed framework, SSAE+Softmax is compared with conventional Softmax classifier, PCA+Softmax, and single layer Sparse Autoencoder (SAE)+Softmax in classifying the nuclei and non-nuclei patches extracted from breast cancer histopathology. The SSAE+Softmax for nuclei patch classification yields an accuracy of 83.7%, F1 score of 82%, and AUC of 0.8992, which outperform Softmax classifier, PCA+Softmax, and SAE+Softmax.
ISSN:1945-7928
DOI:10.1109/ISBI.2014.6868041