An artificial intelligence algorithm for the detection of pulmonary ground-glass nodules on spectral detector CT: performance on virtual monochromatic images

Abstract Background This study aims to assess the performance of an established an AI algorithm trained on conventional polychromatic computed tomography (CT) images (CPIs) to detect pulmonary ground-glass nodules (GGNs) on virtual monochromatic images (VMIs), and to screen the optimal virtual monoc...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhong-Yan Ma, Hai-lin Zhang, Fa-jin Lv, Wei Zhao, Dan Han, Li-chang Lei, Qin Song, Wei-wei Jing, Hui Duan, Shao-Lei Kang
Format: Article
Language:English
Published: BMC 2024-10-01
Series:BMC Medical Imaging
Subjects:
Online Access:https://doi.org/10.1186/s12880-024-01467-2
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850179310067908608
author Zhong-Yan Ma
Hai-lin Zhang
Fa-jin Lv
Wei Zhao
Dan Han
Li-chang Lei
Qin Song
Wei-wei Jing
Hui Duan
Shao-Lei Kang
author_facet Zhong-Yan Ma
Hai-lin Zhang
Fa-jin Lv
Wei Zhao
Dan Han
Li-chang Lei
Qin Song
Wei-wei Jing
Hui Duan
Shao-Lei Kang
author_sort Zhong-Yan Ma
collection DOAJ
description Abstract Background This study aims to assess the performance of an established an AI algorithm trained on conventional polychromatic computed tomography (CT) images (CPIs) to detect pulmonary ground-glass nodules (GGNs) on virtual monochromatic images (VMIs), and to screen the optimal virtual monochromatic energy for the clinical evaluation of GGNs. Methods Non-enhanced chest SDCT images of patients with pulmonary GGNs in our clinic from January 2022 to December 2022 were continuously collected: adenocarcinoma in situ (AIS, n = 40); minimally invasive adenocarcinoma (MIA, n = 44) and invasive adenocarcinoma (IAC, n = 46). A commercial CAD system based on deep convolutional neural networks (DL-CAD) was used to process the CPIs, 40, 50, 60, 70, and 80 keV monochromatic images of 130 spectral CT images. AI-based histogram parameters by logistic regression analysis. The diagnostic performance was evaluated by the receiver operating characteristic (ROC) curves, and Delong’s test was used to compare the CPIs group with the VMIs group. Results When distinguishing IAC from MIA, the diagnostic efficiency of total mass was obtained at 80 keV, which was superior to those of other energy levels (P < 0.05). And Delong’s test indicated that the differences between the area-under-the-curve (AUC) values of the CPIs group and the VMIs group were not statistically significant (P > 0.05). Conclusion The AI algorithm trained on CPIs showed consistent diagnostic performance on VMIs. When pulmonary GGNs are encountered in clinical practice, 80 keV could be the optimal virtual monochromatic energy for the identification of preoperative IAC on a non-enhanced chest CT.
format Article
id doaj-art-2fcc9dc177544c45b111a56c9a4cd86f
institution OA Journals
issn 1471-2342
language English
publishDate 2024-10-01
publisher BMC
record_format Article
series BMC Medical Imaging
spelling doaj-art-2fcc9dc177544c45b111a56c9a4cd86f2025-08-20T02:18:32ZengBMCBMC Medical Imaging1471-23422024-10-0124111110.1186/s12880-024-01467-2An artificial intelligence algorithm for the detection of pulmonary ground-glass nodules on spectral detector CT: performance on virtual monochromatic imagesZhong-Yan Ma0Hai-lin Zhang1Fa-jin Lv2Wei Zhao3Dan Han4Li-chang Lei5Qin Song6Wei-wei Jing7Hui Duan8Shao-Lei Kang9Department of Radiology, First Affiliated Hospital of Kunming Medical UniversityDepartment of Radiology, Yunnan Cancer Center, Yunnan Cancer Hospital, The Third Affiliated Hospital of Kunming Medical UniversityDepartment of Radiology, First Affiliated Hospital of Chongqing Medical UniversityDepartment of Radiology, First Affiliated Hospital of Kunming Medical UniversityDepartment of Radiology, First Affiliated Hospital of Kunming Medical UniversityDepartment of Radiology, First Affiliated Hospital of Kunming Medical UniversityDepartment of Radiology, First Affiliated Hospital of Kunming Medical UniversityDepartment of Radiology, First Affiliated Hospital of Chongqing Medical UniversityDepartment of Radiology, First Affiliated Hospital of Kunming Medical UniversityDepartment of Radiology, First Affiliated Hospital of Kunming Medical UniversityAbstract Background This study aims to assess the performance of an established an AI algorithm trained on conventional polychromatic computed tomography (CT) images (CPIs) to detect pulmonary ground-glass nodules (GGNs) on virtual monochromatic images (VMIs), and to screen the optimal virtual monochromatic energy for the clinical evaluation of GGNs. Methods Non-enhanced chest SDCT images of patients with pulmonary GGNs in our clinic from January 2022 to December 2022 were continuously collected: adenocarcinoma in situ (AIS, n = 40); minimally invasive adenocarcinoma (MIA, n = 44) and invasive adenocarcinoma (IAC, n = 46). A commercial CAD system based on deep convolutional neural networks (DL-CAD) was used to process the CPIs, 40, 50, 60, 70, and 80 keV monochromatic images of 130 spectral CT images. AI-based histogram parameters by logistic regression analysis. The diagnostic performance was evaluated by the receiver operating characteristic (ROC) curves, and Delong’s test was used to compare the CPIs group with the VMIs group. Results When distinguishing IAC from MIA, the diagnostic efficiency of total mass was obtained at 80 keV, which was superior to those of other energy levels (P < 0.05). And Delong’s test indicated that the differences between the area-under-the-curve (AUC) values of the CPIs group and the VMIs group were not statistically significant (P > 0.05). Conclusion The AI algorithm trained on CPIs showed consistent diagnostic performance on VMIs. When pulmonary GGNs are encountered in clinical practice, 80 keV could be the optimal virtual monochromatic energy for the identification of preoperative IAC on a non-enhanced chest CT.https://doi.org/10.1186/s12880-024-01467-2Pulmonary ground-glass noduleArtificial intelligenceDeep learningDual-layer detector spectralComputed tomographyVirtual monochromatic images
spellingShingle Zhong-Yan Ma
Hai-lin Zhang
Fa-jin Lv
Wei Zhao
Dan Han
Li-chang Lei
Qin Song
Wei-wei Jing
Hui Duan
Shao-Lei Kang
An artificial intelligence algorithm for the detection of pulmonary ground-glass nodules on spectral detector CT: performance on virtual monochromatic images
BMC Medical Imaging
Pulmonary ground-glass nodule
Artificial intelligence
Deep learning
Dual-layer detector spectral
Computed tomography
Virtual monochromatic images
title An artificial intelligence algorithm for the detection of pulmonary ground-glass nodules on spectral detector CT: performance on virtual monochromatic images
title_full An artificial intelligence algorithm for the detection of pulmonary ground-glass nodules on spectral detector CT: performance on virtual monochromatic images
title_fullStr An artificial intelligence algorithm for the detection of pulmonary ground-glass nodules on spectral detector CT: performance on virtual monochromatic images
title_full_unstemmed An artificial intelligence algorithm for the detection of pulmonary ground-glass nodules on spectral detector CT: performance on virtual monochromatic images
title_short An artificial intelligence algorithm for the detection of pulmonary ground-glass nodules on spectral detector CT: performance on virtual monochromatic images
title_sort artificial intelligence algorithm for the detection of pulmonary ground glass nodules on spectral detector ct performance on virtual monochromatic images
topic Pulmonary ground-glass nodule
Artificial intelligence
Deep learning
Dual-layer detector spectral
Computed tomography
Virtual monochromatic images
url https://doi.org/10.1186/s12880-024-01467-2
work_keys_str_mv AT zhongyanma anartificialintelligencealgorithmforthedetectionofpulmonarygroundglassnodulesonspectraldetectorctperformanceonvirtualmonochromaticimages
AT hailinzhang anartificialintelligencealgorithmforthedetectionofpulmonarygroundglassnodulesonspectraldetectorctperformanceonvirtualmonochromaticimages
AT fajinlv anartificialintelligencealgorithmforthedetectionofpulmonarygroundglassnodulesonspectraldetectorctperformanceonvirtualmonochromaticimages
AT weizhao anartificialintelligencealgorithmforthedetectionofpulmonarygroundglassnodulesonspectraldetectorctperformanceonvirtualmonochromaticimages
AT danhan anartificialintelligencealgorithmforthedetectionofpulmonarygroundglassnodulesonspectraldetectorctperformanceonvirtualmonochromaticimages
AT lichanglei anartificialintelligencealgorithmforthedetectionofpulmonarygroundglassnodulesonspectraldetectorctperformanceonvirtualmonochromaticimages
AT qinsong anartificialintelligencealgorithmforthedetectionofpulmonarygroundglassnodulesonspectraldetectorctperformanceonvirtualmonochromaticimages
AT weiweijing anartificialintelligencealgorithmforthedetectionofpulmonarygroundglassnodulesonspectraldetectorctperformanceonvirtualmonochromaticimages
AT huiduan anartificialintelligencealgorithmforthedetectionofpulmonarygroundglassnodulesonspectraldetectorctperformanceonvirtualmonochromaticimages
AT shaoleikang anartificialintelligencealgorithmforthedetectionofpulmonarygroundglassnodulesonspectraldetectorctperformanceonvirtualmonochromaticimages
AT zhongyanma artificialintelligencealgorithmforthedetectionofpulmonarygroundglassnodulesonspectraldetectorctperformanceonvirtualmonochromaticimages
AT hailinzhang artificialintelligencealgorithmforthedetectionofpulmonarygroundglassnodulesonspectraldetectorctperformanceonvirtualmonochromaticimages
AT fajinlv artificialintelligencealgorithmforthedetectionofpulmonarygroundglassnodulesonspectraldetectorctperformanceonvirtualmonochromaticimages
AT weizhao artificialintelligencealgorithmforthedetectionofpulmonarygroundglassnodulesonspectraldetectorctperformanceonvirtualmonochromaticimages
AT danhan artificialintelligencealgorithmforthedetectionofpulmonarygroundglassnodulesonspectraldetectorctperformanceonvirtualmonochromaticimages
AT lichanglei artificialintelligencealgorithmforthedetectionofpulmonarygroundglassnodulesonspectraldetectorctperformanceonvirtualmonochromaticimages
AT qinsong artificialintelligencealgorithmforthedetectionofpulmonarygroundglassnodulesonspectraldetectorctperformanceonvirtualmonochromaticimages
AT weiweijing artificialintelligencealgorithmforthedetectionofpulmonarygroundglassnodulesonspectraldetectorctperformanceonvirtualmonochromaticimages
AT huiduan artificialintelligencealgorithmforthedetectionofpulmonarygroundglassnodulesonspectraldetectorctperformanceonvirtualmonochromaticimages
AT shaoleikang artificialintelligencealgorithmforthedetectionofpulmonarygroundglassnodulesonspectraldetectorctperformanceonvirtualmonochromaticimages