Application of deep learning reconstruction at prone position chest scanning of early interstitial lung disease

Abstract Aim Timely intervention of interstitial lung disease (ILD) was promising for attenuating the lung function decline and improving clinical outcomes. The prone position HRCT is essential for early diagnosis of ILD, but limited by its high radiation exposure. This study was aimed to explore wh...

Full description

Saved in:
Bibliographic Details
Main Authors: Ruijie Zhao, Yun Wang, Jiaru Wang, Zixing Wang, Ran Xiao, Ying Ming, Sirong Piao, Jinhua Wang, Lan Song, Yinghao Xu, Zhuangfei Ma, Peilin Fan, Xin Sui, Wei Song
Format: Article
Language:English
Published: BMC 2025-08-01
Series:BMC Medical Imaging
Subjects:
Online Access:https://doi.org/10.1186/s12880-025-01871-2
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849225781586165760
author Ruijie Zhao
Yun Wang
Jiaru Wang
Zixing Wang
Ran Xiao
Ying Ming
Sirong Piao
Jinhua Wang
Lan Song
Yinghao Xu
Zhuangfei Ma
Peilin Fan
Xin Sui
Wei Song
author_facet Ruijie Zhao
Yun Wang
Jiaru Wang
Zixing Wang
Ran Xiao
Ying Ming
Sirong Piao
Jinhua Wang
Lan Song
Yinghao Xu
Zhuangfei Ma
Peilin Fan
Xin Sui
Wei Song
author_sort Ruijie Zhao
collection DOAJ
description Abstract Aim Timely intervention of interstitial lung disease (ILD) was promising for attenuating the lung function decline and improving clinical outcomes. The prone position HRCT is essential for early diagnosis of ILD, but limited by its high radiation exposure. This study was aimed to explore whether deep learning reconstruction (DLR) could keep the image quality and reduce the radiation dose compared with hybrid iterative reconstruction (HIR) in prone position scanning for patients of early-stage ILD. Methods This study prospectively enrolled 21 patients with early-stage ILD. All patients underwent high-resolution CT (HRCT) and low-dose CT (LDCT) scans. HRCT images were reconstructed with HIR using standard settings, and LDCT images were reconstructed with DLR (lung/bone kernel) in a mild, standard, or strong setting. Overall image quality, image noise, streak artifacts, and visualization of normal and abnormal ILD features were analysed. Results The effective dose of LDCT was 1.22 ± 0.09 mSv, 63.7% less than the HRCT dose. The objective noise of the LDCT DLR images was 35.9–112.6% that of the HRCT HIR images. The LDCT DLR was comparable to the HRCT HIR in terms of overall image quality. LDCT DLR (bone, strong) visualization of bronchiectasis and/or bronchiolectasis was significantly weaker than that of HRCT HIR (p = 0.046). The LDCT DLR (all settings) did not significantly differ from the HRCT HIR in the evaluation of other abnormal features, including ground glass opacities (GGOs), architectural distortion, reticulation and honeycombing. Conclusion With 63.7% reduction of radiation dose, the overall image quality of LDCT DLR was comparable to HRCT HIR in prone scanning for early ILD patients. This study supported that DLR was promising for maintaining image quality under a lower radiation dose in prone scanning, and it offered valuable insights for the selection of images reconstruction algorithms for the diagnosis and follow-up of early ILD.
format Article
id doaj-art-9bb13b7511d24bc28772bc561b44af0a
institution Kabale University
issn 1471-2342
language English
publishDate 2025-08-01
publisher BMC
record_format Article
series BMC Medical Imaging
spelling doaj-art-9bb13b7511d24bc28772bc561b44af0a2025-08-24T11:57:38ZengBMCBMC Medical Imaging1471-23422025-08-0125111010.1186/s12880-025-01871-2Application of deep learning reconstruction at prone position chest scanning of early interstitial lung diseaseRuijie Zhao0Yun Wang1Jiaru Wang2Zixing Wang3Ran Xiao4Ying Ming5Sirong Piao6Jinhua Wang7Lan Song8Yinghao Xu9Zhuangfei Ma10Peilin Fan11Xin Sui12Wei Song13Department of Radiology, Peking Union Medical College Hospital, Chinese Academy of Medical SciencesDepartment of Radiology, Peking Union Medical College Hospital, Chinese Academy of Medical SciencesDepartment of Radiology, Peking Union Medical College Hospital, Chinese Academy of Medical SciencesDepartment of Epidemiology and Biostatistics, Institute of Basic Medical Sciences, School of Basic Medicine, Chinese Academy of Medical Sciences, Peking Union Medical CollegeDepartment of Radiology, Peking Union Medical College Hospital, Chinese Academy of Medical SciencesDepartment of Radiology, Peking Union Medical College Hospital, Chinese Academy of Medical SciencesDepartment of Radiology, Peking Union Medical College Hospital, Chinese Academy of Medical SciencesDepartment of Radiology, Peking Union Medical College Hospital, Chinese Academy of Medical SciencesDepartment of Radiology, Peking Union Medical College Hospital, Chinese Academy of Medical SciencesCanon Medical System (China)Canon Medical System (China)Department of Radiology, Peking Union Medical College Hospital, Chinese Academy of Medical SciencesDepartment of Radiology, Peking Union Medical College Hospital, Chinese Academy of Medical SciencesDepartment of Radiology, Peking Union Medical College Hospital, Chinese Academy of Medical SciencesAbstract Aim Timely intervention of interstitial lung disease (ILD) was promising for attenuating the lung function decline and improving clinical outcomes. The prone position HRCT is essential for early diagnosis of ILD, but limited by its high radiation exposure. This study was aimed to explore whether deep learning reconstruction (DLR) could keep the image quality and reduce the radiation dose compared with hybrid iterative reconstruction (HIR) in prone position scanning for patients of early-stage ILD. Methods This study prospectively enrolled 21 patients with early-stage ILD. All patients underwent high-resolution CT (HRCT) and low-dose CT (LDCT) scans. HRCT images were reconstructed with HIR using standard settings, and LDCT images were reconstructed with DLR (lung/bone kernel) in a mild, standard, or strong setting. Overall image quality, image noise, streak artifacts, and visualization of normal and abnormal ILD features were analysed. Results The effective dose of LDCT was 1.22 ± 0.09 mSv, 63.7% less than the HRCT dose. The objective noise of the LDCT DLR images was 35.9–112.6% that of the HRCT HIR images. The LDCT DLR was comparable to the HRCT HIR in terms of overall image quality. LDCT DLR (bone, strong) visualization of bronchiectasis and/or bronchiolectasis was significantly weaker than that of HRCT HIR (p = 0.046). The LDCT DLR (all settings) did not significantly differ from the HRCT HIR in the evaluation of other abnormal features, including ground glass opacities (GGOs), architectural distortion, reticulation and honeycombing. Conclusion With 63.7% reduction of radiation dose, the overall image quality of LDCT DLR was comparable to HRCT HIR in prone scanning for early ILD patients. This study supported that DLR was promising for maintaining image quality under a lower radiation dose in prone scanning, and it offered valuable insights for the selection of images reconstruction algorithms for the diagnosis and follow-up of early ILD.https://doi.org/10.1186/s12880-025-01871-2Deep learning reconstructionInterstitial lung diseaseProne positionLow doseImage quality
spellingShingle Ruijie Zhao
Yun Wang
Jiaru Wang
Zixing Wang
Ran Xiao
Ying Ming
Sirong Piao
Jinhua Wang
Lan Song
Yinghao Xu
Zhuangfei Ma
Peilin Fan
Xin Sui
Wei Song
Application of deep learning reconstruction at prone position chest scanning of early interstitial lung disease
BMC Medical Imaging
Deep learning reconstruction
Interstitial lung disease
Prone position
Low dose
Image quality
title Application of deep learning reconstruction at prone position chest scanning of early interstitial lung disease
title_full Application of deep learning reconstruction at prone position chest scanning of early interstitial lung disease
title_fullStr Application of deep learning reconstruction at prone position chest scanning of early interstitial lung disease
title_full_unstemmed Application of deep learning reconstruction at prone position chest scanning of early interstitial lung disease
title_short Application of deep learning reconstruction at prone position chest scanning of early interstitial lung disease
title_sort application of deep learning reconstruction at prone position chest scanning of early interstitial lung disease
topic Deep learning reconstruction
Interstitial lung disease
Prone position
Low dose
Image quality
url https://doi.org/10.1186/s12880-025-01871-2
work_keys_str_mv AT ruijiezhao applicationofdeeplearningreconstructionatpronepositionchestscanningofearlyinterstitiallungdisease
AT yunwang applicationofdeeplearningreconstructionatpronepositionchestscanningofearlyinterstitiallungdisease
AT jiaruwang applicationofdeeplearningreconstructionatpronepositionchestscanningofearlyinterstitiallungdisease
AT zixingwang applicationofdeeplearningreconstructionatpronepositionchestscanningofearlyinterstitiallungdisease
AT ranxiao applicationofdeeplearningreconstructionatpronepositionchestscanningofearlyinterstitiallungdisease
AT yingming applicationofdeeplearningreconstructionatpronepositionchestscanningofearlyinterstitiallungdisease
AT sirongpiao applicationofdeeplearningreconstructionatpronepositionchestscanningofearlyinterstitiallungdisease
AT jinhuawang applicationofdeeplearningreconstructionatpronepositionchestscanningofearlyinterstitiallungdisease
AT lansong applicationofdeeplearningreconstructionatpronepositionchestscanningofearlyinterstitiallungdisease
AT yinghaoxu applicationofdeeplearningreconstructionatpronepositionchestscanningofearlyinterstitiallungdisease
AT zhuangfeima applicationofdeeplearningreconstructionatpronepositionchestscanningofearlyinterstitiallungdisease
AT peilinfan applicationofdeeplearningreconstructionatpronepositionchestscanningofearlyinterstitiallungdisease
AT xinsui applicationofdeeplearningreconstructionatpronepositionchestscanningofearlyinterstitiallungdisease
AT weisong applicationofdeeplearningreconstructionatpronepositionchestscanningofearlyinterstitiallungdisease