Paper Info
Title
Discrimination of benign and malignant pulmonary tumors in computed tomography - effective priori information of fast learning network architecture.
Abstract
This study explores the influence of prior information for deep learning networks to discriminate the benign and malignant of pulmonary tumors in computed tomography. In this study, because the number of nodule samples is sparse, this study proposes the concept of Multiple-Window to provide prior knowledge for Convolutional neural network (CNN). In the Multiple-Window CNN, we use the 5 windows including lung window, abdomen window, bone window, and chest window to generate the nodule sample. The sparse number of nodule samples, through the characteristics of the CT image dynamic range, make more prior information in a limited amount of data. The results show that the increase of suitably prior information (window channel) be included, CNN performance has improved. When the input is original dicom image, the accuracy of CNN is 0.82, sensitivity is 0.82, and specificity is 0.82. When the input is 4 kinds channel of window type, the accuracy is 0.9, sensitivity is 0.84, and specificity is 0.96.
Year
DOI
Venue
2019
10.1117/12.2512846
Proceedings of SPIE
Keywords
Field
DocType
priori information,pulmonary tumors,Multiple-Window,deep learning
Architecture,Pattern recognition,Computer science,Artificial intelligence,Computed tomography,Learning network
Conference
Volume
ISSN
Citations 
10949
0277-786X
0
PageRank 
References 
Authors
0.34
0
12
Name
Order
Citations
PageRank
Hao-Jen Wang100.68
Leng-Rong Chen200.68
Li-Wei Chen300.68
Yi-Chang Chen400.34
Shun-Mao Yang500.68
Mong-Wei Lin600.68
Joseph Chang700.34
Chia-Chen Li800.34
Chia-Yen Lee912224.93
Jin-Shing Chen1000.34
Yeun-Chung Chang11365.49
Chung-Ming Chen1217616.17