Peritumoral features for assessing invasiveness of lung adenocarcinoma manifesting as ground-glass nodules

Abstract We evaluated the predictive value of radiomics features from different peritumoral ranges for the invasiveness of ground-glass nodular lung adenocarcinoma using various machine learning models. This retrospective study included 317 patients with 323 ground-glass nodules diagnosed as minimal...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiao Wang, Hui Xue, Wei Ding, Fei Huang, Yu Zhang, Xin Pang
Format: Article
Language:English
Published: Nature Portfolio 2025-04-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-99180-9
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849713641137373184
author Xiao Wang
Hui Xue
Wei Ding
Fei Huang
Yu Zhang
Xin Pang
author_facet Xiao Wang
Hui Xue
Wei Ding
Fei Huang
Yu Zhang
Xin Pang
author_sort Xiao Wang
collection DOAJ
description Abstract We evaluated the predictive value of radiomics features from different peritumoral ranges for the invasiveness of ground-glass nodular lung adenocarcinoma using various machine learning models. This retrospective study included 317 patients with 323 ground-glass nodules diagnosed as minimally invasive adenocarcinoma (MIA) or invasive adenocarcinoma (IAC) at Benxi Central Hospital (January 2019–December 2023). Radiomic features from tumor margins of 1, 2, 3, 4, and 5 mm were extracted. Eight machine learning models were constructed following dimensionality reduction. The models were evaluated using receiver operating characteristic curves. All models had area under the curve values > 0.75, effectively distinguishing between MIA and IAC. Only the decision tree model showed statistically significant differences (P < 0.05); no differences were found between the other models (P > 0.05). In the training set, the 1-mm margin model achieved the highest ranking, followed by the 2-, 4-, 5-, and 3-mm models. In the validation group, the 3-mm margin model ranked the highest, followed by the 2-, 1-, 4-, and 5-mm models, with no statistically significant differences (P > 0.05). All machine learning models demonstrated good predictive performance for both MIA and IAC. Radiomic features from 1 to 5-mm margins showed strong predictive value, though no optimal margin range was identified.
format Article
id doaj-art-e848928e7b824e648a30ff8d18e8bb04
institution DOAJ
issn 2045-2322
language English
publishDate 2025-04-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-e848928e7b824e648a30ff8d18e8bb042025-08-20T03:13:54ZengNature PortfolioScientific Reports2045-23222025-04-0115111210.1038/s41598-025-99180-9Peritumoral features for assessing invasiveness of lung adenocarcinoma manifesting as ground-glass nodulesXiao Wang0Hui Xue1Wei Ding2Fei Huang3Yu Zhang4Xin Pang5Department of Radiology, Benxi Central HospitalDepartment of Ultrasonography, Benxi Central HospitalDepartment of Radiology, Benxi Central HospitalDepartment of Radiology, Liaoyang Third People’s HospitalDepartment of Radiology, Benxi Central HospitalDepartment of Radiology, Benxi Central HospitalAbstract We evaluated the predictive value of radiomics features from different peritumoral ranges for the invasiveness of ground-glass nodular lung adenocarcinoma using various machine learning models. This retrospective study included 317 patients with 323 ground-glass nodules diagnosed as minimally invasive adenocarcinoma (MIA) or invasive adenocarcinoma (IAC) at Benxi Central Hospital (January 2019–December 2023). Radiomic features from tumor margins of 1, 2, 3, 4, and 5 mm were extracted. Eight machine learning models were constructed following dimensionality reduction. The models were evaluated using receiver operating characteristic curves. All models had area under the curve values > 0.75, effectively distinguishing between MIA and IAC. Only the decision tree model showed statistically significant differences (P < 0.05); no differences were found between the other models (P > 0.05). In the training set, the 1-mm margin model achieved the highest ranking, followed by the 2-, 4-, 5-, and 3-mm models. In the validation group, the 3-mm margin model ranked the highest, followed by the 2-, 1-, 4-, and 5-mm models, with no statistically significant differences (P > 0.05). All machine learning models demonstrated good predictive performance for both MIA and IAC. Radiomic features from 1 to 5-mm margins showed strong predictive value, though no optimal margin range was identified.https://doi.org/10.1038/s41598-025-99180-9Computed tomographyGround-glass noduleLung adenocarcinomaRadiomics
spellingShingle Xiao Wang
Hui Xue
Wei Ding
Fei Huang
Yu Zhang
Xin Pang
Peritumoral features for assessing invasiveness of lung adenocarcinoma manifesting as ground-glass nodules
Scientific Reports
Computed tomography
Ground-glass nodule
Lung adenocarcinoma
Radiomics
title Peritumoral features for assessing invasiveness of lung adenocarcinoma manifesting as ground-glass nodules
title_full Peritumoral features for assessing invasiveness of lung adenocarcinoma manifesting as ground-glass nodules
title_fullStr Peritumoral features for assessing invasiveness of lung adenocarcinoma manifesting as ground-glass nodules
title_full_unstemmed Peritumoral features for assessing invasiveness of lung adenocarcinoma manifesting as ground-glass nodules
title_short Peritumoral features for assessing invasiveness of lung adenocarcinoma manifesting as ground-glass nodules
title_sort peritumoral features for assessing invasiveness of lung adenocarcinoma manifesting as ground glass nodules
topic Computed tomography
Ground-glass nodule
Lung adenocarcinoma
Radiomics
url https://doi.org/10.1038/s41598-025-99180-9
work_keys_str_mv AT xiaowang peritumoralfeaturesforassessinginvasivenessoflungadenocarcinomamanifestingasgroundglassnodules
AT huixue peritumoralfeaturesforassessinginvasivenessoflungadenocarcinomamanifestingasgroundglassnodules
AT weiding peritumoralfeaturesforassessinginvasivenessoflungadenocarcinomamanifestingasgroundglassnodules
AT feihuang peritumoralfeaturesforassessinginvasivenessoflungadenocarcinomamanifestingasgroundglassnodules
AT yuzhang peritumoralfeaturesforassessinginvasivenessoflungadenocarcinomamanifestingasgroundglassnodules
AT xinpang peritumoralfeaturesforassessinginvasivenessoflungadenocarcinomamanifestingasgroundglassnodules