Pulmonary Nodules Detection Algorithm Combining Multi-view and Attention Mechanism

To solve the problems of low detection rate and high false positive of nodules in low-dose lung CT images by traditional computer-aided diagnosis system, a two-stage pulmonary nodules detection model based on U-Net network and attention mechanism was proposed. In order to improve the detection speed...

Full description

Saved in:
Bibliographic Details
Main Authors: LIU Yu-bo, LIU Guo-zhu, SHI Cao, XU Can-hui
Format: Article
Language:zho
Published: Harbin University of Science and Technology Publications 2022-12-01
Series:Journal of Harbin University of Science and Technology
Subjects:
Online Access:https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=2165
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849713700249796608
author LIU Yu-bo
LIU Guo-zhu
SHI Cao
XU Can-hui
author_facet LIU Yu-bo
LIU Guo-zhu
SHI Cao
XU Can-hui
author_sort LIU Yu-bo
collection DOAJ
description To solve the problems of low detection rate and high false positive of nodules in low-dose lung CT images by traditional computer-aided diagnosis system, a two-stage pulmonary nodules detection model based on U-Net network and attention mechanism was proposed. In order to improve the detection speed and detection rate of pulmonary nodules, a 3D network was constructed to detect the candidate nodules firstly. It optimized the detection speed while the three-dimensional information of nodules was fully utilized to improve the detection rate of the candidate nodules. Then, the multi-view input method was used to ensure that the spatial features of nodules was obtained. The sections from 9 angles in three-dimensional space, including sagittal plane, coronal plane and horizontal plane, were input into the network together.The ViT network was used as a feature extractor and combined with the feature pyramid network to achieve the classification of nodules, and we fused all section results to achieve the screening of false positive nodules. The final experimental results on LUNA16 data set show that the accuracy of the proposed model reaches 94.7%, which improves the accuracy and reduces the rate of misdiagnosis and missed diagnosis.
format Article
id doaj-art-80d2bdf23bbf4f3f971245d6bb9c67dc
institution DOAJ
issn 1007-2683
language zho
publishDate 2022-12-01
publisher Harbin University of Science and Technology Publications
record_format Article
series Journal of Harbin University of Science and Technology
spelling doaj-art-80d2bdf23bbf4f3f971245d6bb9c67dc2025-08-20T03:13:54ZzhoHarbin University of Science and Technology PublicationsJournal of Harbin University of Science and Technology1007-26832022-12-01270611512310.15938/j.jhust.2022.06.014Pulmonary Nodules Detection Algorithm Combining Multi-view and Attention MechanismLIU Yu-bo0LIU Guo-zhu1SHI Cao2XU Can-hui3College of Information Science and Technology, Qingdao University of Science and Technology, Qingdao 266061, ChinaCollege of Information Science and Technology, Qingdao University of Science and Technology, Qingdao 266061, ChinaCollege of Information Science and Technology, Qingdao University of Science and Technology, Qingdao 266061, ChinaCollege of Information Science and Technology, Qingdao University of Science and Technology, Qingdao 266061, ChinaTo solve the problems of low detection rate and high false positive of nodules in low-dose lung CT images by traditional computer-aided diagnosis system, a two-stage pulmonary nodules detection model based on U-Net network and attention mechanism was proposed. In order to improve the detection speed and detection rate of pulmonary nodules, a 3D network was constructed to detect the candidate nodules firstly. It optimized the detection speed while the three-dimensional information of nodules was fully utilized to improve the detection rate of the candidate nodules. Then, the multi-view input method was used to ensure that the spatial features of nodules was obtained. The sections from 9 angles in three-dimensional space, including sagittal plane, coronal plane and horizontal plane, were input into the network together.The ViT network was used as a feature extractor and combined with the feature pyramid network to achieve the classification of nodules, and we fused all section results to achieve the screening of false positive nodules. The final experimental results on LUNA16 data set show that the accuracy of the proposed model reaches 94.7%, which improves the accuracy and reduces the rate of misdiagnosis and missed diagnosis.https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=2165deep learningpulmonary nodules detectioncandidate nodesfalse-positive reducesensitivity
spellingShingle LIU Yu-bo
LIU Guo-zhu
SHI Cao
XU Can-hui
Pulmonary Nodules Detection Algorithm Combining Multi-view and Attention Mechanism
Journal of Harbin University of Science and Technology
deep learning
pulmonary nodules detection
candidate nodes
false-positive reduce
sensitivity
title Pulmonary Nodules Detection Algorithm Combining Multi-view and Attention Mechanism
title_full Pulmonary Nodules Detection Algorithm Combining Multi-view and Attention Mechanism
title_fullStr Pulmonary Nodules Detection Algorithm Combining Multi-view and Attention Mechanism
title_full_unstemmed Pulmonary Nodules Detection Algorithm Combining Multi-view and Attention Mechanism
title_short Pulmonary Nodules Detection Algorithm Combining Multi-view and Attention Mechanism
title_sort pulmonary nodules detection algorithm combining multi view and attention mechanism
topic deep learning
pulmonary nodules detection
candidate nodes
false-positive reduce
sensitivity
url https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=2165
work_keys_str_mv AT liuyubo pulmonarynodulesdetectionalgorithmcombiningmultiviewandattentionmechanism
AT liuguozhu pulmonarynodulesdetectionalgorithmcombiningmultiviewandattentionmechanism
AT shicao pulmonarynodulesdetectionalgorithmcombiningmultiviewandattentionmechanism
AT xucanhui pulmonarynodulesdetectionalgorithmcombiningmultiviewandattentionmechanism