Share Email Print

Proceedings Paper

A multi-stage fusion strategy for multi-scale GLCM-CNN model in differentiating malignant from benign polyps
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Computer aided diagnosis (CADx) of polyps has shown great potential to advance the computed tomography colonography (CTC) technique with diagnostic capability. Facing the problem of numerous uncertainties such as polyp size, shape, and orientation in CTC, GLCM-CNN has been proved to be an effective deep learning based tumor classification method, where convolution neural network (CNN) makes decision based on the texture pattern encoded in gray level co-occurrence matrix (GLCM) containing 13 directions. The 13 directional GLCM, by sampling displacement, can be classified into 3 subgroups. Based on our evaluation on the information encoded in the three subgroups, we propose a multi-stage fusion CNN model, which makes the final decision based on two types of features, i.e. (1) a gate module selected group-specific features and (2) fused features learnt from all the features from three groups. On our polyp dataset, which contains 87 polyp masses, our proposed method outperforms both single sub-group based and 13 directional GLCM based CNN model by at least 1.3% in AUC by the average of 20 times 2 fold cross validation experiment results.

Paper Details

Date Published: 16 March 2020
PDF: 5 pages
Proc. SPIE 11314, Medical Imaging 2020: Computer-Aided Diagnosis, 113141S (16 March 2020); doi: 10.1117/12.2549831
Show Author Affiliations
Jiaxing Tan, Stony Brook Univ. (United States)
Shu Zhang, Stony Brook Univ. (United States)
Weiguo Cao, Stony Brook Univ. (United States)
Yongfeng Gao, Stony Brook Univ. (United States)
Lihong Li, The City Univ. of New York (United States)
Yumei Huo, The City Univ. of New York (United States)
Zhengrong Liang, Stony Brook Univ. (United States)

Published in SPIE Proceedings Vol. 11314:
Medical Imaging 2020: Computer-Aided Diagnosis
Horst K. Hahn; Maciej A. Mazurowski, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?