Deep learning reconstruction improves computer-aided pulmonary nodule detection and measurement accuracy for ultra-low-dose chest CT

Abstract Purpose To compare the image quality and pulmonary nodule detectability and measurement accuracy between deep learning reconstruction (DLR) and hybrid iterative reconstruction (HIR) of chest ultra-low-dose CT (ULDCT). Materials and Methods Participants who underwent chest standard-dose CT (...

Full description

Saved in:
Bibliographic Details
Main Authors: Jinhua Wang, Zhenchen Zhu, Zhengsong Pan, Weixiong Tan, Wei Han, Zhen Zhou, Ge Hu, Zhuangfei Ma, Yinghao Xu, Zhoumeng Ying, Xin Sui, Zhengyu Jin, Lan Song, Wei Song
Format: Article
Language:English
Published: BMC 2025-05-01
Series:BMC Medical Imaging
Subjects:
Online Access:https://doi.org/10.1186/s12880-025-01746-6
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850243135525879808
author Jinhua Wang
Zhenchen Zhu
Zhengsong Pan
Weixiong Tan
Wei Han
Zhen Zhou
Ge Hu
Zhuangfei Ma
Yinghao Xu
Zhoumeng Ying
Xin Sui
Zhengyu Jin
Lan Song
Wei Song
author_facet Jinhua Wang
Zhenchen Zhu
Zhengsong Pan
Weixiong Tan
Wei Han
Zhen Zhou
Ge Hu
Zhuangfei Ma
Yinghao Xu
Zhoumeng Ying
Xin Sui
Zhengyu Jin
Lan Song
Wei Song
author_sort Jinhua Wang
collection DOAJ
description Abstract Purpose To compare the image quality and pulmonary nodule detectability and measurement accuracy between deep learning reconstruction (DLR) and hybrid iterative reconstruction (HIR) of chest ultra-low-dose CT (ULDCT). Materials and Methods Participants who underwent chest standard-dose CT (SDCT) followed by ULDCT from October 2020 to January 2022 were prospectively included. ULDCT images reconstructed with HIR and DLR were compared with SDCT images to evaluate image quality, nodule detection rate, and measurement accuracy using a commercially available deep learning–based nodule evaluation system. Wilcoxon signed-rank test was used to evaluate the percentage errors of nodule size and nodule volume between HIR and DLR images. Results Eighty-four participants (54 ± 13 years; 26 men) were finally enrolled. The effective radiation doses of ULDCT and SDCT were 0.16 ± 0.02 mSv and 1.77 ± 0.67 mSv, respectively (P < 0.001). The mean ± standard deviation of the lung tissue noises was 61.4 ± 3.0 HU for SDCT, 61.5 ± 2.8 HU and 55.1 ± 3.4 HU for ULDCT reconstructed with HIR-Strong setting (HIR-Str) and DLR-Strong setting (DLR-Str), respectively (P < 0.001). A total of 535 nodules were detected. The nodule detection rates of ULDCT HIR-Str and ULDCT DLR-Str were 74.0% and 83.4%, respectively (P < 0.001). The absolute percentage error in nodule volume from that of SDCT was 19.5% in ULDCT HIR-Str versus 17.9% in ULDCT DLR-Str (P < 0.001). Conclusion Compared with HIR, DLR reduced image noise, increased nodule detection rate, and improved measurement accuracy of nodule volume at chest ULDCT. Clinical trial number Not applicable.
format Article
id doaj-art-e7b0e071e7b34a7fa44f5979d81fc464
institution OA Journals
issn 1471-2342
language English
publishDate 2025-05-01
publisher BMC
record_format Article
series BMC Medical Imaging
spelling doaj-art-e7b0e071e7b34a7fa44f5979d81fc4642025-08-20T02:00:06ZengBMCBMC Medical Imaging1471-23422025-05-0125111210.1186/s12880-025-01746-6Deep learning reconstruction improves computer-aided pulmonary nodule detection and measurement accuracy for ultra-low-dose chest CTJinhua Wang0Zhenchen Zhu1Zhengsong Pan2Weixiong Tan3Wei Han4Zhen Zhou5Ge Hu6Zhuangfei Ma7Yinghao Xu8Zhoumeng Ying9Xin Sui10Zhengyu Jin11Lan Song12Wei Song13Department of Radiology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical CollegeDepartment of Radiology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical CollegeDepartment of Radiology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical CollegeDeepwise AI Lab, Beijing Deepwise & League of PhD Technology Co.LtdDepartment of Epidemiology and Health Statistics, Institute of Basic Medicine Sciences, Chinese Academy of Medical Sciences and Peking Union Medical CollegeDeepwise AI Lab, Beijing Deepwise & League of PhD Technology Co.LtdTheranostics and Translational Research Center, National Infrastructures for Translational Medicine, Institute of Clinical Medicine, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical CollegeCanon Medical System (China)Canon Medical System (China)Department of Radiology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical CollegeDepartment of Radiology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical CollegeDepartment of Radiology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical CollegeDepartment of Radiology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical CollegeDepartment of Radiology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical CollegeAbstract Purpose To compare the image quality and pulmonary nodule detectability and measurement accuracy between deep learning reconstruction (DLR) and hybrid iterative reconstruction (HIR) of chest ultra-low-dose CT (ULDCT). Materials and Methods Participants who underwent chest standard-dose CT (SDCT) followed by ULDCT from October 2020 to January 2022 were prospectively included. ULDCT images reconstructed with HIR and DLR were compared with SDCT images to evaluate image quality, nodule detection rate, and measurement accuracy using a commercially available deep learning–based nodule evaluation system. Wilcoxon signed-rank test was used to evaluate the percentage errors of nodule size and nodule volume between HIR and DLR images. Results Eighty-four participants (54 ± 13 years; 26 men) were finally enrolled. The effective radiation doses of ULDCT and SDCT were 0.16 ± 0.02 mSv and 1.77 ± 0.67 mSv, respectively (P < 0.001). The mean ± standard deviation of the lung tissue noises was 61.4 ± 3.0 HU for SDCT, 61.5 ± 2.8 HU and 55.1 ± 3.4 HU for ULDCT reconstructed with HIR-Strong setting (HIR-Str) and DLR-Strong setting (DLR-Str), respectively (P < 0.001). A total of 535 nodules were detected. The nodule detection rates of ULDCT HIR-Str and ULDCT DLR-Str were 74.0% and 83.4%, respectively (P < 0.001). The absolute percentage error in nodule volume from that of SDCT was 19.5% in ULDCT HIR-Str versus 17.9% in ULDCT DLR-Str (P < 0.001). Conclusion Compared with HIR, DLR reduced image noise, increased nodule detection rate, and improved measurement accuracy of nodule volume at chest ULDCT. Clinical trial number Not applicable.https://doi.org/10.1186/s12880-025-01746-6Lung nodulesTomography, X-ray computedDeep learning reconstructionImage quality
spellingShingle Jinhua Wang
Zhenchen Zhu
Zhengsong Pan
Weixiong Tan
Wei Han
Zhen Zhou
Ge Hu
Zhuangfei Ma
Yinghao Xu
Zhoumeng Ying
Xin Sui
Zhengyu Jin
Lan Song
Wei Song
Deep learning reconstruction improves computer-aided pulmonary nodule detection and measurement accuracy for ultra-low-dose chest CT
BMC Medical Imaging
Lung nodules
Tomography, X-ray computed
Deep learning reconstruction
Image quality
title Deep learning reconstruction improves computer-aided pulmonary nodule detection and measurement accuracy for ultra-low-dose chest CT
title_full Deep learning reconstruction improves computer-aided pulmonary nodule detection and measurement accuracy for ultra-low-dose chest CT
title_fullStr Deep learning reconstruction improves computer-aided pulmonary nodule detection and measurement accuracy for ultra-low-dose chest CT
title_full_unstemmed Deep learning reconstruction improves computer-aided pulmonary nodule detection and measurement accuracy for ultra-low-dose chest CT
title_short Deep learning reconstruction improves computer-aided pulmonary nodule detection and measurement accuracy for ultra-low-dose chest CT
title_sort deep learning reconstruction improves computer aided pulmonary nodule detection and measurement accuracy for ultra low dose chest ct
topic Lung nodules
Tomography, X-ray computed
Deep learning reconstruction
Image quality
url https://doi.org/10.1186/s12880-025-01746-6
work_keys_str_mv AT jinhuawang deeplearningreconstructionimprovescomputeraidedpulmonarynoduledetectionandmeasurementaccuracyforultralowdosechestct
AT zhenchenzhu deeplearningreconstructionimprovescomputeraidedpulmonarynoduledetectionandmeasurementaccuracyforultralowdosechestct
AT zhengsongpan deeplearningreconstructionimprovescomputeraidedpulmonarynoduledetectionandmeasurementaccuracyforultralowdosechestct
AT weixiongtan deeplearningreconstructionimprovescomputeraidedpulmonarynoduledetectionandmeasurementaccuracyforultralowdosechestct
AT weihan deeplearningreconstructionimprovescomputeraidedpulmonarynoduledetectionandmeasurementaccuracyforultralowdosechestct
AT zhenzhou deeplearningreconstructionimprovescomputeraidedpulmonarynoduledetectionandmeasurementaccuracyforultralowdosechestct
AT gehu deeplearningreconstructionimprovescomputeraidedpulmonarynoduledetectionandmeasurementaccuracyforultralowdosechestct
AT zhuangfeima deeplearningreconstructionimprovescomputeraidedpulmonarynoduledetectionandmeasurementaccuracyforultralowdosechestct
AT yinghaoxu deeplearningreconstructionimprovescomputeraidedpulmonarynoduledetectionandmeasurementaccuracyforultralowdosechestct
AT zhoumengying deeplearningreconstructionimprovescomputeraidedpulmonarynoduledetectionandmeasurementaccuracyforultralowdosechestct
AT xinsui deeplearningreconstructionimprovescomputeraidedpulmonarynoduledetectionandmeasurementaccuracyforultralowdosechestct
AT zhengyujin deeplearningreconstructionimprovescomputeraidedpulmonarynoduledetectionandmeasurementaccuracyforultralowdosechestct
AT lansong deeplearningreconstructionimprovescomputeraidedpulmonarynoduledetectionandmeasurementaccuracyforultralowdosechestct
AT weisong deeplearningreconstructionimprovescomputeraidedpulmonarynoduledetectionandmeasurementaccuracyforultralowdosechestct