Chest CT imaging for differentiating normal, PRISm, and COPD in comparison with pulmonary function tests.
Uloženo v:
| Název: | Chest CT imaging for differentiating normal, PRISm, and COPD in comparison with pulmonary function tests. |
|---|---|
| Autoři: | Ma Z; Department of Radiology, Huadong Hospital, Fudan University, Shanghai, China., Sun Y; Department of Radiology, Huadong Hospital, Fudan University, Shanghai, China., Ma Z; Department of Radiology, Huadong Hospital, Fudan University, Shanghai, China., Zhang L; Department of Radiology, Fudan University Shanghai Cancer Centre, Shanghai, China., Cheng F; Kashi Prefecture Second People's Hospital, Xinjiang, China., Ma H; Kashi Prefecture Second People's Hospital, Xinjiang, China. 1727359370@qq.com., Jin L; Department of Radiology, Huadong Hospital, Fudan University, Shanghai, China. jin_liang@fudan.edu.cn., Li M; Department of Radiology, Huadong Hospital, Fudan University, Shanghai, China. ming_li@fudan.edu.com. |
| Zdroj: | La Radiologia medica [Radiol Med] 2025 Nov; Vol. 130 (11), pp. 1786-1796. Date of Electronic Publication: 2025 Aug 21. |
| Způsob vydávání: | Journal Article; Multicenter Study; Comparative Study |
| Jazyk: | English |
| Informace o časopise: | Publisher: Springer Milan Country of Publication: Italy NLM ID: 0177625 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1826-6983 (Electronic) Linking ISSN: 00338362 NLM ISO Abbreviation: Radiol Med Subsets: MEDLINE |
| Imprint Name(s): | Publication: Milan : Springer Milan Original Publication: Torino [etc.] Minerva medica. |
| Výrazy ze slovníku MeSH: | Pulmonary Disease, Chronic Obstructive*/diagnostic imaging , Pulmonary Disease, Chronic Obstructive*/physiopathology , Tomography, X-Ray Computed*/methods , Respiratory Function Tests*, Humans ; Female ; Male ; Retrospective Studies ; Middle Aged ; Aged ; Diagnosis, Differential ; Lung/diagnostic imaging ; Lung/physiopathology ; Spirometry |
| Abstrakt: | Competing Interests: Declarations. Ethics approval and consent to participate: This retrospective study was approved by the Ethics Review Committee of Huadong hospital (No.20240123). The requirement for obtaining written informed consent was waived. Consent for publication: All authors have read and approved the paper content and agreed to the publication. Competing interests: The authors declare that they have no competing interests. Background: Preserved ratio impaired spirometry (PRISm) and chronic obstructive pulmonary disease (COPD) are progressive respiratory disorders associated with accelerated pulmonary function decline and systemic comorbidities. This multicenter study aimed to develop a three-category classification model that integrates clinical variables with thoracic computed tomography (CT) radiomics to distinguish normal pulmonary function, PRISm, and COPD. Methods: A total of 1018 participants from three centers (A, B, C) who underwent chest CT and pulmonary function tests (PFTs) within a 2-week interval were retrospectively analyzed. After applying inclusion and exclusion criteria, 797 individuals were included for analysis (Center A: 667 [training/internal test = 534:133]; Centers B, C: 130 external test). CT images were preprocessed via resampling and intensity normalization, followed by semi-automated segmentation of the airway tree and whole lung parenchyma using Mimics Research. PyRadiomics extracted 2436 radiomic features (1218 per region). Feature selection combined maximum relevance minimum redundancy with least absolute shrinkage and selection operator regression, employing tenfold cross-validation. Five models were developed using multinomial logistic regression: (1) clinical model, (2) airway model, (3) lung model, (4) airway fusion model, and (5) lung fusion model. Performance metrics included accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and the area under the receiver operating characteristic curve (AUC), with DeLong tests comparing model efficacy. Results: 35 airway tree and 48 lung radiomic features were ultimately selected. The best performing model was the lung fusion model, which integrated three clinical predictors (age, gender, and BMI) with selected lung radiomic features. In external test set, it achieved superior performance with AUCs of 0.939 (95% CI 0.898-0.979) for PFT-normal, 0.830 (0.758-0.902) for PRISm, and 0.904 (0.841-0.966) for COPD, with an overall accuracy of 83.59%. DeLong tests indicated that across all three datasets, the lung fusion model outperformed the other four models. Conclusion: Combining age, gender, BMI, and lung radiomic features significantly improves detection of PRISm and COPD compared to alternative models. These findings underscore the potential of CT-based radiomics for the early identification and risk stratification of abnormal pulmonary function. (© 2025. The Author(s).) |
| References: | Int J Chron Obstruct Pulmon Dis. 2024 Mar 15;19:753-764. (PMID: 38505581) Eur Heart J. 2022 Jun 14;43(23):2196-2208. (PMID: 35467708) Front Med (Lausanne). 2024 Apr 09;11:1375457. (PMID: 38654838) Lancet Respir Med. 2022 Feb;10(2):149-157. (PMID: 34739861) Int J Environ Res Public Health. 2023 Jan 27;20(3):. (PMID: 36767660) Psychol Med. 2024 Sep 26;:1-9. (PMID: 39324390) Respir Res. 2022 Nov 11;23(1):309. (PMID: 36369019) Chest. 2022 Mar;161(3):651-661. (PMID: 34592319) Arch Bronconeumol. 2023 Apr;59(4):232-248. (PMID: 36933949) Radiat Oncol. 2025 Jan 17;20(1):9. (PMID: 39825409) Front Med (Lausanne). 2025 Feb 05;12:1517765. (PMID: 39975681) Pharmacol Ther. 2024 May;257:108635. (PMID: 38508342) Thorax. 2025 Mar 18;80(4):227-235. (PMID: 39832944) Front Oncol. 2024 Oct 09;14:1447132. (PMID: 39445066) ERJ Open Res. 2024 Feb 12;10(1):. (PMID: 38348246) JAMA. 2019 Jun 25;321(24):2438-2447. (PMID: 31237643) Respir Res. 2024 Sep 3;25(1):329. (PMID: 39227894) Chest. 2016 Dec;150(6):1281-1290. (PMID: 27522957) BMC Med. 2024 Dec 31;22(1):606. (PMID: 39736738) Lancet Reg Health West Pac. 2024 Feb 06;45:101021. (PMID: 38352242) China CDC Wkly. 2024 Oct 25;6(43):1120-1125. (PMID: 39507567) Respirology. 2025 Apr;30(4):326-334. (PMID: 39800892) Chest. 2025 Jun;167(6):1591-1614. (PMID: 39742912) Mil Med Res. 2024 Feb 20;11(1):14. (PMID: 38374260) Lancet Reg Health West Pac. 2023 Dec 18;44:100984. (PMID: 38186582) Radiology. 2023 Apr;307(2):e221488. (PMID: 36786699) |
| Contributed Indexing: | Keywords: Chronic obstructive pulmonary disease; Multinomial logistic regression; Preserved ratio impaired spirometry; Radiomics |
| Entry Date(s): | Date Created: 20250821 Date Completed: 20251113 Latest Revision: 20251114 |
| Update Code: | 20251114 |
| PubMed Central ID: | PMC12605617 |
| DOI: | 10.1007/s11547-025-02061-4 |
| PMID: | 40839063 |
| Databáze: | MEDLINE |
Full Text Finder 
Nájsť tento článok vo Web of Science | Abstrakt: | Competing Interests: Declarations. Ethics approval and consent to participate: This retrospective study was approved by the Ethics Review Committee of Huadong hospital (No.20240123). The requirement for obtaining written informed consent was waived. Consent for publication: All authors have read and approved the paper content and agreed to the publication. Competing interests: The authors declare that they have no competing interests.<br />Background: Preserved ratio impaired spirometry (PRISm) and chronic obstructive pulmonary disease (COPD) are progressive respiratory disorders associated with accelerated pulmonary function decline and systemic comorbidities. This multicenter study aimed to develop a three-category classification model that integrates clinical variables with thoracic computed tomography (CT) radiomics to distinguish normal pulmonary function, PRISm, and COPD.<br />Methods: A total of 1018 participants from three centers (A, B, C) who underwent chest CT and pulmonary function tests (PFTs) within a 2-week interval were retrospectively analyzed. After applying inclusion and exclusion criteria, 797 individuals were included for analysis (Center A: 667 [training/internal test = 534:133]; Centers B, C: 130 external test). CT images were preprocessed via resampling and intensity normalization, followed by semi-automated segmentation of the airway tree and whole lung parenchyma using Mimics Research. PyRadiomics extracted 2436 radiomic features (1218 per region). Feature selection combined maximum relevance minimum redundancy with least absolute shrinkage and selection operator regression, employing tenfold cross-validation. Five models were developed using multinomial logistic regression: (1) clinical model, (2) airway model, (3) lung model, (4) airway fusion model, and (5) lung fusion model. Performance metrics included accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and the area under the receiver operating characteristic curve (AUC), with DeLong tests comparing model efficacy.<br />Results: 35 airway tree and 48 lung radiomic features were ultimately selected. The best performing model was the lung fusion model, which integrated three clinical predictors (age, gender, and BMI) with selected lung radiomic features. In external test set, it achieved superior performance with AUCs of 0.939 (95% CI 0.898-0.979) for PFT-normal, 0.830 (0.758-0.902) for PRISm, and 0.904 (0.841-0.966) for COPD, with an overall accuracy of 83.59%. DeLong tests indicated that across all three datasets, the lung fusion model outperformed the other four models.<br />Conclusion: Combining age, gender, BMI, and lung radiomic features significantly improves detection of PRISm and COPD compared to alternative models. These findings underscore the potential of CT-based radiomics for the early identification and risk stratification of abnormal pulmonary function.<br /> (© 2025. The Author(s).) |
|---|---|
| ISSN: | 1826-6983 |
| DOI: | 10.1007/s11547-025-02061-4 |