A three-dimensional detector based on focal loss for pulmonary nodules detection

Lei Wang, Yaping Dai*, Zhiyang Jia, Yongkang Nie, Liang Liu

*此作品的通讯作者

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

The problem of class imbalance exists in detecting the pulmonary nodules from Computed Tomography (CT) by means of convolutional neural network. A Three-Dimensional Detector Based on Focal Loss (FLTDD) is designed in this paper to ensure that the pulmonary nodules in CT could be identified more exactly. Its framework focuses more on samples that are difficult to be classified. Besides, three dimensional detector contains richer spatial information and gets more distinguishing features. The experiment results obtained from LIDC-IDRI data set show that the average sensitivity score of FLTDD achieves 89.62%. It has a 1.47% improvement compared with the published CASED method.

源语言英语
主期刊名Proceedings of the 38th Chinese Control Conference, CCC 2019
编辑Minyue Fu, Jian Sun
出版商IEEE Computer Society
8445-8449
页数5
ISBN(电子版)9789881563972
DOI
出版状态已出版 - 7月 2019
活动38th Chinese Control Conference, CCC 2019 - Guangzhou, 中国
期限: 27 7月 201930 7月 2019

出版系列

姓名Chinese Control Conference, CCC
2019-July
ISSN(印刷版)1934-1768
ISSN(电子版)2161-2927

会议

会议38th Chinese Control Conference, CCC 2019
国家/地区中国
Guangzhou
时期27/07/1930/07/19

指纹

探究 'A three-dimensional detector based on focal loss for pulmonary nodules detection' 的科研主题。它们共同构成独一无二的指纹。

引用此