Computed tomography-based radiomics prediction model for differentiating invasive pulmonary aspergillosis and Pneumocystis jirovecii pneumonia

BackgroundPneumocystis jirovecii and Aspergillus fumigatus are important pathogens that cause fungal pulmonary infections. Because the manifestations of P. jirovecii pneumonia (PJP) or invasive pulmonary aspergillosis (IPA) are difficult to differentiate on computed tomography (CT) images and the tr...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhiguo Peng, Xingzhe Gao, Miao He, Xinyue Dong, Dongdong Wang, Zhengjun Dai, Dexin Yu, Huaibin Sun, Jun Tian, Yu Hu
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-07-01
Series:Frontiers in Cellular and Infection Microbiology
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fcimb.2025.1552556/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849427964454764544
author Zhiguo Peng
Xingzhe Gao
Miao He
Xinyue Dong
Dongdong Wang
Zhengjun Dai
Dexin Yu
Huaibin Sun
Jun Tian
Yu Hu
author_facet Zhiguo Peng
Xingzhe Gao
Miao He
Xinyue Dong
Dongdong Wang
Zhengjun Dai
Dexin Yu
Huaibin Sun
Jun Tian
Yu Hu
author_sort Zhiguo Peng
collection DOAJ
description BackgroundPneumocystis jirovecii and Aspergillus fumigatus are important pathogens that cause fungal pulmonary infections. Because the manifestations of P. jirovecii pneumonia (PJP) or invasive pulmonary aspergillosis (IPA) are difficult to differentiate on computed tomography (CT) images and the treatment of the two diseases is different, correct imaging for diagnosis is highly significant. The present study developed and validated the diagnostic performance of a CT-based radiomics prediction model for differentiating IPA from PJP.MethodsIn total, 97 patients, 51 with IPA and 46 with PJP, were included in this study. Each patient underwent a non-enhanced chest CT examination. All the patients were randomly divided into two cohorts, training and validation, at a ratio of 7:3 using random seeds automatically generated using the RadCloud platform. Image segmentation, feature extraction, and radiomic feature selection were performed on the RadCloud platform. The regions of interest (ROIs) were manually segmented, including the consolidation area with the surrounding ground-glass opacity (GGO) area and the consolidation area alone. Six supervised-learning classifiers were used to develop a CT-based radiomics prediction model, which was estimated using the receiver operating characteristic (ROC) curve, area under the curve (AUC), sensitivity, specificity, precision, and F1-score. The radiomics score was also calculated to compare the prediction performance.ResultsClassifiers trained with the consolidation area and surrounding GGO area as the ROI showed better prediction efficacy than classifiers trained using only the consolidation area as the ROI. The XGBoost model performed better than the other classifiers and radiomics scores in the validation cohort, with an AUC of 0.808 (95% CI, 0.655–0.961).ConclusionsThis radiomics model can effectively assist in the differential diagnosis of PJP and IPA. The consolidation area with the surrounding GGO area was more suitable for ROI segmentation.
format Article
id doaj-art-445902de34c94db2a11eee33740e9cf4
institution Kabale University
issn 2235-2988
language English
publishDate 2025-07-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Cellular and Infection Microbiology
spelling doaj-art-445902de34c94db2a11eee33740e9cf42025-08-20T03:28:51ZengFrontiers Media S.A.Frontiers in Cellular and Infection Microbiology2235-29882025-07-011510.3389/fcimb.2025.15525561552556Computed tomography-based radiomics prediction model for differentiating invasive pulmonary aspergillosis and Pneumocystis jirovecii pneumoniaZhiguo Peng0Xingzhe Gao1Miao He2Xinyue Dong3Dongdong Wang4Zhengjun Dai5Dexin Yu6Huaibin Sun7Jun Tian8Yu Hu9Department of Organ Transplantation, Qilu Hospital, Cheeloo College of Medicine, Shandong University, Jinan, ChinaDepartment of Anesthesiology, Qilu Hospital (Qingdao), Cheeloo College of Medicine, Shandong University, Qingdao, ChinaDepartment of Medical Oncology, Qilu Hospital (Qingdao), Cheeloo College of Medicine, Shandong University, Qingdao, ChinaDepartment of Oncology, Qilu Hospital of Shandong University, Dezhou Hospital, Dezhou, ChinaDepartment of Radiology, Qilu Hospital, Cheeloo College of Medicine, Shandong University, Jinan, ChinaScientific Research Department, Huiying Medical Technology Co., Ltd, Beijing, ChinaDepartment of Radiology, Qilu Hospital, Cheeloo College of Medicine, Shandong University, Jinan, ChinaDepartment of Organ Transplantation, Qilu Hospital, Cheeloo College of Medicine, Shandong University, Jinan, ChinaDepartment of Organ Transplantation, Qilu Hospital, Cheeloo College of Medicine, Shandong University, Jinan, ChinaDepartment of Oncology, Qilu Hospital, Cheeloo College of Medicine, Shandong University, Jinan, ChinaBackgroundPneumocystis jirovecii and Aspergillus fumigatus are important pathogens that cause fungal pulmonary infections. Because the manifestations of P. jirovecii pneumonia (PJP) or invasive pulmonary aspergillosis (IPA) are difficult to differentiate on computed tomography (CT) images and the treatment of the two diseases is different, correct imaging for diagnosis is highly significant. The present study developed and validated the diagnostic performance of a CT-based radiomics prediction model for differentiating IPA from PJP.MethodsIn total, 97 patients, 51 with IPA and 46 with PJP, were included in this study. Each patient underwent a non-enhanced chest CT examination. All the patients were randomly divided into two cohorts, training and validation, at a ratio of 7:3 using random seeds automatically generated using the RadCloud platform. Image segmentation, feature extraction, and radiomic feature selection were performed on the RadCloud platform. The regions of interest (ROIs) were manually segmented, including the consolidation area with the surrounding ground-glass opacity (GGO) area and the consolidation area alone. Six supervised-learning classifiers were used to develop a CT-based radiomics prediction model, which was estimated using the receiver operating characteristic (ROC) curve, area under the curve (AUC), sensitivity, specificity, precision, and F1-score. The radiomics score was also calculated to compare the prediction performance.ResultsClassifiers trained with the consolidation area and surrounding GGO area as the ROI showed better prediction efficacy than classifiers trained using only the consolidation area as the ROI. The XGBoost model performed better than the other classifiers and radiomics scores in the validation cohort, with an AUC of 0.808 (95% CI, 0.655–0.961).ConclusionsThis radiomics model can effectively assist in the differential diagnosis of PJP and IPA. The consolidation area with the surrounding GGO area was more suitable for ROI segmentation.https://www.frontiersin.org/articles/10.3389/fcimb.2025.1552556/fullinvasive pulmonary aspergillosisPneumocystis jirovecii pneumoniadiscriminant modelradiomicsCT
spellingShingle Zhiguo Peng
Xingzhe Gao
Miao He
Xinyue Dong
Dongdong Wang
Zhengjun Dai
Dexin Yu
Huaibin Sun
Jun Tian
Yu Hu
Computed tomography-based radiomics prediction model for differentiating invasive pulmonary aspergillosis and Pneumocystis jirovecii pneumonia
Frontiers in Cellular and Infection Microbiology
invasive pulmonary aspergillosis
Pneumocystis jirovecii pneumonia
discriminant model
radiomics
CT
title Computed tomography-based radiomics prediction model for differentiating invasive pulmonary aspergillosis and Pneumocystis jirovecii pneumonia
title_full Computed tomography-based radiomics prediction model for differentiating invasive pulmonary aspergillosis and Pneumocystis jirovecii pneumonia
title_fullStr Computed tomography-based radiomics prediction model for differentiating invasive pulmonary aspergillosis and Pneumocystis jirovecii pneumonia
title_full_unstemmed Computed tomography-based radiomics prediction model for differentiating invasive pulmonary aspergillosis and Pneumocystis jirovecii pneumonia
title_short Computed tomography-based radiomics prediction model for differentiating invasive pulmonary aspergillosis and Pneumocystis jirovecii pneumonia
title_sort computed tomography based radiomics prediction model for differentiating invasive pulmonary aspergillosis and pneumocystis jirovecii pneumonia
topic invasive pulmonary aspergillosis
Pneumocystis jirovecii pneumonia
discriminant model
radiomics
CT
url https://www.frontiersin.org/articles/10.3389/fcimb.2025.1552556/full
work_keys_str_mv AT zhiguopeng computedtomographybasedradiomicspredictionmodelfordifferentiatinginvasivepulmonaryaspergillosisandpneumocystisjiroveciipneumonia
AT xingzhegao computedtomographybasedradiomicspredictionmodelfordifferentiatinginvasivepulmonaryaspergillosisandpneumocystisjiroveciipneumonia
AT miaohe computedtomographybasedradiomicspredictionmodelfordifferentiatinginvasivepulmonaryaspergillosisandpneumocystisjiroveciipneumonia
AT xinyuedong computedtomographybasedradiomicspredictionmodelfordifferentiatinginvasivepulmonaryaspergillosisandpneumocystisjiroveciipneumonia
AT dongdongwang computedtomographybasedradiomicspredictionmodelfordifferentiatinginvasivepulmonaryaspergillosisandpneumocystisjiroveciipneumonia
AT zhengjundai computedtomographybasedradiomicspredictionmodelfordifferentiatinginvasivepulmonaryaspergillosisandpneumocystisjiroveciipneumonia
AT dexinyu computedtomographybasedradiomicspredictionmodelfordifferentiatinginvasivepulmonaryaspergillosisandpneumocystisjiroveciipneumonia
AT huaibinsun computedtomographybasedradiomicspredictionmodelfordifferentiatinginvasivepulmonaryaspergillosisandpneumocystisjiroveciipneumonia
AT juntian computedtomographybasedradiomicspredictionmodelfordifferentiatinginvasivepulmonaryaspergillosisandpneumocystisjiroveciipneumonia
AT yuhu computedtomographybasedradiomicspredictionmodelfordifferentiatinginvasivepulmonaryaspergillosisandpneumocystisjiroveciipneumonia