Elaboration of a multimodal MRI-based radiomics signature for the preoperative prediction of the histological subtype in patients with non-small-cell lung cancer
Abstract Background Non-invasive discrimination between lung squamous cell carcinoma (LUSC) and lung adenocarcinoma (LUAD) subtypes of non-small-cell lung cancer (NSCLC) could be very beneficial to the patients unfit for the invasive diagnostic procedures. The aim of this study was to investigate th...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2020-01-01
|
| Series: | BioMedical Engineering OnLine |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12938-019-0744-0 |
| _version_ | 1818393377371062272 |
|---|---|
| author | Xing Tang Xiaopan Xu Zhiping Han Guoyan Bai Hong Wang Yang Liu Peng Du Zhengrong Liang Jian Zhang Hongbing Lu Hong Yin |
| author_facet | Xing Tang Xiaopan Xu Zhiping Han Guoyan Bai Hong Wang Yang Liu Peng Du Zhengrong Liang Jian Zhang Hongbing Lu Hong Yin |
| author_sort | Xing Tang |
| collection | DOAJ |
| description | Abstract Background Non-invasive discrimination between lung squamous cell carcinoma (LUSC) and lung adenocarcinoma (LUAD) subtypes of non-small-cell lung cancer (NSCLC) could be very beneficial to the patients unfit for the invasive diagnostic procedures. The aim of this study was to investigate the feasibility of utilizing the multimodal magnetic resonance imaging (MRI) radiomics and clinical features in classifying NSCLC. This retrospective study involved 148 eligible patients with postoperative pathologically confirmed NSCLC. The study was conducted in three steps: (1) feature extraction was performed using the online freely available package with the multimodal MRI data; (2) feature selection was performed using the Student’s t test and support vector machine (SVM)-based recursive feature elimination method with the training cohort (n = 100), and the performance of these selected features was evaluated using both the training and the validation cohorts (n = 48) with a non-linear SVM classifier; (3) a Radscore model was then generated using logistic regression algorithm; (4) Integrating the Radscore with the semantic clinical features, a radiomics–clinical nomogram was developed, and its overall performance was evaluated with both cohorts. Results Thirteen optimal features achieved favorable discrimination performance with both cohorts, with area under the curve (AUC) of 0.819 and 0.824, respectively. The radiomics–clinical nomogram integrating the Radscore with the independent clinical predictors exhibited more favorable discriminative power, with AUC improved to 0.901 and 0.872 in both cohorts, respectively. The Hosmer–Lemeshow test and decision curve analysis results furtherly showed good predictive precision and clinical usefulness of the nomogram. Conclusion Non-invasive histological subtype stratification of NSCLC can be done favorably using multimodal MRI radiomics features. Integrating the radiomics features with the clinical features could further improve the performance of the histological subtype stratification in patients with NSCLC. |
| first_indexed | 2024-12-14T05:44:21Z |
| format | Article |
| id | doaj.art-a07d2a41d6f045c288a23c2812a38a9a |
| institution | Directory Open Access Journal |
| issn | 1475-925X |
| language | English |
| last_indexed | 2024-12-14T05:44:21Z |
| publishDate | 2020-01-01 |
| publisher | BMC |
| record_format | Article |
| series | BioMedical Engineering OnLine |
| spelling | doaj.art-a07d2a41d6f045c288a23c2812a38a9a2022-12-21T23:14:55ZengBMCBioMedical Engineering OnLine1475-925X2020-01-0119111710.1186/s12938-019-0744-0Elaboration of a multimodal MRI-based radiomics signature for the preoperative prediction of the histological subtype in patients with non-small-cell lung cancerXing Tang0Xiaopan Xu1Zhiping Han2Guoyan Bai3Hong Wang4Yang Liu5Peng Du6Zhengrong Liang7Jian Zhang8Hongbing Lu9Hong Yin10Department of Radiology, Xijing Hospital, Fourth Military Medical UniversitySchool of Biomedical Engineering, Fourth Military Medical UniversityDepartment of Respiratory Medicine, Xijing Hospital, Fourth Military Medical UniversityDepartment of Clinical Laboratory, Shaanxi Provincial People’s HospitalDepartment of Radiology, Xijing Hospital, Fourth Military Medical UniversitySchool of Biomedical Engineering, Fourth Military Medical UniversitySchool of Biomedical Engineering, Fourth Military Medical UniversityDepartments of Radiology, School of Computer Science and Biomedical Engineering, State University of New YorkDepartment of Respiratory Medicine, Xijing Hospital, Fourth Military Medical UniversitySchool of Biomedical Engineering, Fourth Military Medical UniversityDepartment of Radiology, Xijing Hospital, Fourth Military Medical UniversityAbstract Background Non-invasive discrimination between lung squamous cell carcinoma (LUSC) and lung adenocarcinoma (LUAD) subtypes of non-small-cell lung cancer (NSCLC) could be very beneficial to the patients unfit for the invasive diagnostic procedures. The aim of this study was to investigate the feasibility of utilizing the multimodal magnetic resonance imaging (MRI) radiomics and clinical features in classifying NSCLC. This retrospective study involved 148 eligible patients with postoperative pathologically confirmed NSCLC. The study was conducted in three steps: (1) feature extraction was performed using the online freely available package with the multimodal MRI data; (2) feature selection was performed using the Student’s t test and support vector machine (SVM)-based recursive feature elimination method with the training cohort (n = 100), and the performance of these selected features was evaluated using both the training and the validation cohorts (n = 48) with a non-linear SVM classifier; (3) a Radscore model was then generated using logistic regression algorithm; (4) Integrating the Radscore with the semantic clinical features, a radiomics–clinical nomogram was developed, and its overall performance was evaluated with both cohorts. Results Thirteen optimal features achieved favorable discrimination performance with both cohorts, with area under the curve (AUC) of 0.819 and 0.824, respectively. The radiomics–clinical nomogram integrating the Radscore with the independent clinical predictors exhibited more favorable discriminative power, with AUC improved to 0.901 and 0.872 in both cohorts, respectively. The Hosmer–Lemeshow test and decision curve analysis results furtherly showed good predictive precision and clinical usefulness of the nomogram. Conclusion Non-invasive histological subtype stratification of NSCLC can be done favorably using multimodal MRI radiomics features. Integrating the radiomics features with the clinical features could further improve the performance of the histological subtype stratification in patients with NSCLC.https://doi.org/10.1186/s12938-019-0744-0Non-small-cell lung cancerLung squamous cell carcinomaLung adenocarcinomaMultimodal MRI radiomics featuresClinical featuresNomogram |
| spellingShingle | Xing Tang Xiaopan Xu Zhiping Han Guoyan Bai Hong Wang Yang Liu Peng Du Zhengrong Liang Jian Zhang Hongbing Lu Hong Yin Elaboration of a multimodal MRI-based radiomics signature for the preoperative prediction of the histological subtype in patients with non-small-cell lung cancer BioMedical Engineering OnLine Non-small-cell lung cancer Lung squamous cell carcinoma Lung adenocarcinoma Multimodal MRI radiomics features Clinical features Nomogram |
| title | Elaboration of a multimodal MRI-based radiomics signature for the preoperative prediction of the histological subtype in patients with non-small-cell lung cancer |
| title_full | Elaboration of a multimodal MRI-based radiomics signature for the preoperative prediction of the histological subtype in patients with non-small-cell lung cancer |
| title_fullStr | Elaboration of a multimodal MRI-based radiomics signature for the preoperative prediction of the histological subtype in patients with non-small-cell lung cancer |
| title_full_unstemmed | Elaboration of a multimodal MRI-based radiomics signature for the preoperative prediction of the histological subtype in patients with non-small-cell lung cancer |
| title_short | Elaboration of a multimodal MRI-based radiomics signature for the preoperative prediction of the histological subtype in patients with non-small-cell lung cancer |
| title_sort | elaboration of a multimodal mri based radiomics signature for the preoperative prediction of the histological subtype in patients with non small cell lung cancer |
| topic | Non-small-cell lung cancer Lung squamous cell carcinoma Lung adenocarcinoma Multimodal MRI radiomics features Clinical features Nomogram |
| url | https://doi.org/10.1186/s12938-019-0744-0 |
| work_keys_str_mv | AT xingtang elaborationofamultimodalmribasedradiomicssignatureforthepreoperativepredictionofthehistologicalsubtypeinpatientswithnonsmallcelllungcancer AT xiaopanxu elaborationofamultimodalmribasedradiomicssignatureforthepreoperativepredictionofthehistologicalsubtypeinpatientswithnonsmallcelllungcancer AT zhipinghan elaborationofamultimodalmribasedradiomicssignatureforthepreoperativepredictionofthehistologicalsubtypeinpatientswithnonsmallcelllungcancer AT guoyanbai elaborationofamultimodalmribasedradiomicssignatureforthepreoperativepredictionofthehistologicalsubtypeinpatientswithnonsmallcelllungcancer AT hongwang elaborationofamultimodalmribasedradiomicssignatureforthepreoperativepredictionofthehistologicalsubtypeinpatientswithnonsmallcelllungcancer AT yangliu elaborationofamultimodalmribasedradiomicssignatureforthepreoperativepredictionofthehistologicalsubtypeinpatientswithnonsmallcelllungcancer AT pengdu elaborationofamultimodalmribasedradiomicssignatureforthepreoperativepredictionofthehistologicalsubtypeinpatientswithnonsmallcelllungcancer AT zhengrongliang elaborationofamultimodalmribasedradiomicssignatureforthepreoperativepredictionofthehistologicalsubtypeinpatientswithnonsmallcelllungcancer AT jianzhang elaborationofamultimodalmribasedradiomicssignatureforthepreoperativepredictionofthehistologicalsubtypeinpatientswithnonsmallcelllungcancer AT hongbinglu elaborationofamultimodalmribasedradiomicssignatureforthepreoperativepredictionofthehistologicalsubtypeinpatientswithnonsmallcelllungcancer AT hongyin elaborationofamultimodalmribasedradiomicssignatureforthepreoperativepredictionofthehistologicalsubtypeinpatientswithnonsmallcelllungcancer |