Paper Info
Title
A Hybrid Deep Learning And Handcrafted Feature Approach For Cervical Cancer Digital Histology Image Classification
Abstract
Cervical cancer is the second most common cancer affecting women worldwide but is curable if diagnosed early. Routinely, expert pathologists visually examine histology slides for assessing cervix tissue abnormalities. A localized, fusion-based, hybrid imaging and deep learning approach is explored to classify squamous epithelium into cervical intraepithelial neoplasia (CIN) grades for a dataset of 83 digitized histology images. Partitioning the epithelium region into 10 vertical segments, 27 handcrafted image features and rectangular patch, sliding window-based convolutional neural network features are computed for each segment. The imaging and deep learning patch features are combined and used as inputs to a secondary classifier for individual segment and whole epithelium classification. The hybrid method achieved a 15.51% and 11.66% improvement over the deep learning and imaging approaches alone, respectively, with a 80.72% whole epithelium CIN classification accuracy, showing the enhanced epithelium CIN classification potential of fusing image and deep learning features.
Year
DOI
Venue
2019
10.4018/IJHISI.2019040105
INTERNATIONAL JOURNAL OF HEALTHCARE INFORMATION SYSTEMS AND INFORMATICS
Keywords
Field
DocType
Cervical Cancer, Clinical Decision Support Systems, Convolutional Neural Networks, Data Fusion, Deep Learning, Feature Extraction, Image Classification
Cervical cancer,Data mining,Artificial intelligence,Natural language processing,Deep learning,Contextual image classification,Medicine
Journal
Volume
Issue
ISSN
14
2
1555-3396
Citations 
PageRank 
References 
0
0.34
5
Authors
9
Name
Order
Citations
PageRank
Haidar A. Almubarak1101.53
R. Joe Stanley29212.80
Peng Guo32916.63
L. Rodney Long453456.98
Sameer Antani51402134.03
George R. Thoma61207132.81
Rosemary Zuna710.83
Shelliane R. Frazier800.34
William V. Stoecker937142.00