Non-contrast computed tomography-based radiomics for staging of connective tissue disease-associated interstitial lung disease
Rationale and introductionIt is of significance to assess the severity and predict the mortality of patients with connective tissue disease-associated interstitial lung disease (CTD-ILD). In this double-center retrospective study, we developed and validated a radiomics nomogram for clinical manageme...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-10-01
|
| Series: | Frontiers in Immunology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fimmu.2023.1213008/full |
| _version_ | 1797665247695208448 |
|---|---|
| author | Songnan Qin Bingxuan Jiao Bing Kang Haiou Li Hongwu Liu Congshan Ji Shifeng Yang Hongtao Yuan Ximing Wang Ximing Wang |
| author_facet | Songnan Qin Bingxuan Jiao Bing Kang Haiou Li Hongwu Liu Congshan Ji Shifeng Yang Hongtao Yuan Ximing Wang Ximing Wang |
| author_sort | Songnan Qin |
| collection | DOAJ |
| description | Rationale and introductionIt is of significance to assess the severity and predict the mortality of patients with connective tissue disease-associated interstitial lung disease (CTD-ILD). In this double-center retrospective study, we developed and validated a radiomics nomogram for clinical management by using the ILD-GAP (gender, age, and pulmonary physiology) index system.Materials and methodsPatients with CTD-ILD were staged using the ILD-GAP index system. A clinical factor model was built by demographics and CT features, and a radiomics signature was developed using radiomics features extracted from CT images. Combined with the radiomics signature and independent clinical factors, a radiomics nomogram was constructed and evaluated by the area under the curve (AUC) from receiver operating characteristic (ROC) analyses. The models were externally validated in dataset 2 to evaluate the model generalization ability using ROC analysis.ResultsA total of 245 patients from two clinical centers (dataset 1, n = 202; dataset 2, n = 43) were screened. Pack-years of smoking, traction bronchiectasis, and nine radiomics features were used to build the radiomics nomogram, which showed favorable calibration and discrimination in the training cohort {AUC, 0.887 [95% confidence interval (CI): 0.827–0.940]}, the internal validation cohort [AUC, 0.885 (95% CI: 0.816–0.922)], and the external validation cohort [AUC, 0.85 (95% CI: 0.720–0.919)]. Decision curve analysis demonstrated that the nomogram outperformed the clinical factor model and radiomics signature in terms of clinical usefulness.ConclusionThe CT-based radiomics nomogram showed favorable efficacy in predicting individual ILD-GAP stages. |
| first_indexed | 2024-03-11T19:42:09Z |
| format | Article |
| id | doaj.art-182fd4b8a95647268ac5d3ece893627d |
| institution | Directory Open Access Journal |
| issn | 1664-3224 |
| language | English |
| last_indexed | 2024-03-11T19:42:09Z |
| publishDate | 2023-10-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Immunology |
| spelling | doaj.art-182fd4b8a95647268ac5d3ece893627d2023-10-06T07:58:13ZengFrontiers Media S.A.Frontiers in Immunology1664-32242023-10-011410.3389/fimmu.2023.12130081213008Non-contrast computed tomography-based radiomics for staging of connective tissue disease-associated interstitial lung diseaseSongnan Qin0Bingxuan Jiao1Bing Kang2Haiou Li3Hongwu Liu4Congshan Ji5Shifeng Yang6Hongtao Yuan7Ximing Wang8Ximing Wang9Department of Radiology, Shandong Provincial Hospital, Shandong University, Jinan, Shandong, ChinaDepartment of Radiology, Shandong Provincial Hospital, Shandong University, Jinan, Shandong, ChinaDepartment of Radiology, Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, Shandong, ChinaDepartment of Radiology, Qilu Hospital, Cheeloo College of Medicine, Shandong University, Jinan, Shandong, ChinaDepartment of Radiology, Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, Shandong, ChinaDepartment of Radiology, Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, Shandong, ChinaDepartment of Radiology, Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, Shandong, ChinaDepartment of Radiology, Shandong Provincial Hospital, Shandong University, Jinan, Shandong, ChinaDepartment of Radiology, Shandong Provincial Hospital, Shandong University, Jinan, Shandong, ChinaDepartment of Radiology, Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, Shandong, ChinaRationale and introductionIt is of significance to assess the severity and predict the mortality of patients with connective tissue disease-associated interstitial lung disease (CTD-ILD). In this double-center retrospective study, we developed and validated a radiomics nomogram for clinical management by using the ILD-GAP (gender, age, and pulmonary physiology) index system.Materials and methodsPatients with CTD-ILD were staged using the ILD-GAP index system. A clinical factor model was built by demographics and CT features, and a radiomics signature was developed using radiomics features extracted from CT images. Combined with the radiomics signature and independent clinical factors, a radiomics nomogram was constructed and evaluated by the area under the curve (AUC) from receiver operating characteristic (ROC) analyses. The models were externally validated in dataset 2 to evaluate the model generalization ability using ROC analysis.ResultsA total of 245 patients from two clinical centers (dataset 1, n = 202; dataset 2, n = 43) were screened. Pack-years of smoking, traction bronchiectasis, and nine radiomics features were used to build the radiomics nomogram, which showed favorable calibration and discrimination in the training cohort {AUC, 0.887 [95% confidence interval (CI): 0.827–0.940]}, the internal validation cohort [AUC, 0.885 (95% CI: 0.816–0.922)], and the external validation cohort [AUC, 0.85 (95% CI: 0.720–0.919)]. Decision curve analysis demonstrated that the nomogram outperformed the clinical factor model and radiomics signature in terms of clinical usefulness.ConclusionThe CT-based radiomics nomogram showed favorable efficacy in predicting individual ILD-GAP stages.https://www.frontiersin.org/articles/10.3389/fimmu.2023.1213008/fullconnective tissue diseasesinterstitial lung diseasesradiomicsmachine learningcomputed tomography |
| spellingShingle | Songnan Qin Bingxuan Jiao Bing Kang Haiou Li Hongwu Liu Congshan Ji Shifeng Yang Hongtao Yuan Ximing Wang Ximing Wang Non-contrast computed tomography-based radiomics for staging of connective tissue disease-associated interstitial lung disease Frontiers in Immunology connective tissue diseases interstitial lung diseases radiomics machine learning computed tomography |
| title | Non-contrast computed tomography-based radiomics for staging of connective tissue disease-associated interstitial lung disease |
| title_full | Non-contrast computed tomography-based radiomics for staging of connective tissue disease-associated interstitial lung disease |
| title_fullStr | Non-contrast computed tomography-based radiomics for staging of connective tissue disease-associated interstitial lung disease |
| title_full_unstemmed | Non-contrast computed tomography-based radiomics for staging of connective tissue disease-associated interstitial lung disease |
| title_short | Non-contrast computed tomography-based radiomics for staging of connective tissue disease-associated interstitial lung disease |
| title_sort | non contrast computed tomography based radiomics for staging of connective tissue disease associated interstitial lung disease |
| topic | connective tissue diseases interstitial lung diseases radiomics machine learning computed tomography |
| url | https://www.frontiersin.org/articles/10.3389/fimmu.2023.1213008/full |
| work_keys_str_mv | AT songnanqin noncontrastcomputedtomographybasedradiomicsforstagingofconnectivetissuediseaseassociatedinterstitiallungdisease AT bingxuanjiao noncontrastcomputedtomographybasedradiomicsforstagingofconnectivetissuediseaseassociatedinterstitiallungdisease AT bingkang noncontrastcomputedtomographybasedradiomicsforstagingofconnectivetissuediseaseassociatedinterstitiallungdisease AT haiouli noncontrastcomputedtomographybasedradiomicsforstagingofconnectivetissuediseaseassociatedinterstitiallungdisease AT hongwuliu noncontrastcomputedtomographybasedradiomicsforstagingofconnectivetissuediseaseassociatedinterstitiallungdisease AT congshanji noncontrastcomputedtomographybasedradiomicsforstagingofconnectivetissuediseaseassociatedinterstitiallungdisease AT shifengyang noncontrastcomputedtomographybasedradiomicsforstagingofconnectivetissuediseaseassociatedinterstitiallungdisease AT hongtaoyuan noncontrastcomputedtomographybasedradiomicsforstagingofconnectivetissuediseaseassociatedinterstitiallungdisease AT ximingwang noncontrastcomputedtomographybasedradiomicsforstagingofconnectivetissuediseaseassociatedinterstitiallungdisease AT ximingwang noncontrastcomputedtomographybasedradiomicsforstagingofconnectivetissuediseaseassociatedinterstitiallungdisease |