Deep Convolutional Neural Networks for Chest Diseases Detection

Journal of Healthcare Engineering - Tập 2018 - Trang 1-11 - 2018
Rahib H. Abiyev1, Mohammad Khaleel Sallam Ma’aitah1
1Department, of Computer Engineering, Near East University, North Cyprus, Mersin-10, Turkey

Tóm tắt

Chest diseases are very serious health problems in the life of people. These diseases include chronic obstructive pulmonary disease, pneumonia, asthma, tuberculosis, and lung diseases. The timely diagnosis of chest diseases is very important. Many methods have been developed for this purpose. In this paper, we demonstrate the feasibility of classifying the chest pathologies in chest X-rays using conventional and deep learning approaches. In the paper, convolutional neural networks (CNNs) are presented for the diagnosis of chest diseases. The architecture of CNN and its design principle are presented. For comparative purpose, backpropagation neural networks (BPNNs) with supervised learning, competitive neural networks (CpNNs) with unsupervised learning are also constructed for diagnosis chest diseases. All the considered networks CNN, BPNN, and CpNN are trained and tested on the same chest X-ray database, and the performance of each network is discussed. Comparative results in terms of accuracy, error rate, and training time between the networks are presented.

Từ khóa


Tài liệu tham khảo

10.1016/j.eswa.2010.04.078

10.1378/chest.116.4.968

10.1016/s1076-6332(99)80055-5

10.1007/s10916-008-9209-x

10.1016/j.media.2017.07.005

10.1109/tmi.2016.2528120

10.1162/neco.2006.18.7.1527

10.1016/j.media.2016.01.005

2016, Learning to read chest X-rays: recurrent neural cascade model for automated image annotation

10.1007/s12555-009-0103-1

10.5815/ijisa.2016.01.03

2015

10.14569/ijacsa.2017.080622

10.14569/ijacsa.2017.081204

10.1109/tsmc.1983.6313075

10.1016/j.eij.2013.08.001

2004, Competitive neural networks for fault detection and diagnosis in 3G cellular systems

10.1038/nature14539

10.1155/2017/3105053

10.1016/j.image.2017.08.010

10.1016/j.neucom.2017.12.032

10.1016/j.patcog.2017.10.013

2007, Iris recognition for biometric personal identification using neural networks

10.1007/s11263-015-0816-y

Thông tin
Thông tin xuất bản

Journal of Healthcare Engineering

Tập 2018

1-11

Thông tin tác giả