You are viewing a javascript disabled version of the site. Please enable Javascript for this site to function properly.
Go to headerGo to navigationGo to searchGo to contentsGo to footer
In content section. Select this link to jump to navigation

A new method based on MTANNs for cutting down false-positives: An evaluation on different versions of commercial pulmonary nodule detection CAD software

Issue title: Frontiers in Biomedical Engineering and Biotechnology – Proceedings of the 3rd International Conference on Biomedical Engineering and Biotechnology, 25–28 September 2014, Beijing, China

Article type: Research Article

Authors: Shi, Zhenghao; ; | Si, Chunjiao | Feng, Yaning | He, Lifeng | Suzuki, Kenji

Affiliations: School of Computer Science and Engineering, Xi'an University of Technology, Xi'an, 710048, China | Department of Radiology, University of Chicago, Chicago, IL 60637, USA | School of Information Science and Technology, Aichi Prefectural University, Nagakute, Aichi 4801198, Japan

Note: [] This work is partially supported by a grant from the Nature Science Foundation of Shaanxi Education Department (No.2013JK1136) and the Nature Science Foundation of Science Department of PeiLin count at Xi'an (GX1213).

Note: [] Corresponding author: Zheng-hao Shi, School of Computer Science and Engineering, Xi'an University of Technology, Xi'an 710048, China. Tel.: +1 029 8231 2231; E-mail: ylshi@xaut.edu.cn.

Keywords: False Positive, cutting down, Mixture of MTANNs, Commercial CAD

DOI: 10.3233/BME-141102

Journal: Bio-Medical Materials and Engineering, vol. 24, no. 6, pp. 2839-2846, 2014

Published: 2014
Get PDF open access

Abstract

One of the major problems for computer-aided pulmonary nodule detection in chest radiographs is that a high falsepositive (FP) rate exists. In an effort to overcome this problem, a new method based on the MTANN (Massive Training Artificial Neural Network) is proposed in this paper. An MTANN comprises a multi-layer neural network where a linear function rather than a sigmoid function is used as its activity function in the output layer. In this work, a mixture of multiple MTANNs were employed rather than only a single MTANN. 50 MTANNs for 50 different types of FPs were prepared firstly. Then, several effective MTANNs that had higher performances were selected to construct the MTANNs mixture. Finally, the outputs of the multiple MTANNs were combined with a mixing neural network to reduce various different types of FPs. The performance of this MTANNs mixture in FPs reduction is validated on three different versions of commercial CAD software with a validation database consisting of 52 chest radiographs. Experimental results demonstrate that the proposed MTANN approach is useful in cutting down FPs in different CAD software for detecting pulmonary nodules in chest radiographs.

Show more