Using CT texture analysis to differentiate between peripheral lung cancer and pulmonary inflammatory pseudotumor
Abstract Background This study is to distinguish peripheral lung cancer and pulmonary inflammatory pseudotumor using CT-radiomics features extracted from PET/CT images. Methods In this study, the standard 18F-fluorodeoxyglucose positron emission tomography/ computed tomography (18 F-FDG PET/CT) imag...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2020-07-01
|
| Series: | BMC Medical Imaging |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s12880-020-00475-2 |
| _version_ | 1818891074876211200 |
|---|---|
| author | Chenlu Liu Changsheng Ma Jinghao Duan Qingtao Qiu Yanluan Guo Zhenhua Zhang Yong Yin |
| author_facet | Chenlu Liu Changsheng Ma Jinghao Duan Qingtao Qiu Yanluan Guo Zhenhua Zhang Yong Yin |
| author_sort | Chenlu Liu |
| collection | DOAJ |
| description | Abstract Background This study is to distinguish peripheral lung cancer and pulmonary inflammatory pseudotumor using CT-radiomics features extracted from PET/CT images. Methods In this study, the standard 18F-fluorodeoxyglucose positron emission tomography/ computed tomography (18 F-FDG PET/CT) images of 21 patients with pulmonary inflammatory pseudotumor (PIPT) and 21 patients with peripheral lung cancer were retrospectively collected. The dataset was used to extract CT-radiomics features from regions of interest (ROI), The intra-class correlation coefficient (ICC) was used to screen the robust feature from all the radiomic features. Using, then, statistical methods to screen CT-radiomics features, which could distinguish peripheral lung cancer and PIPT. And the ability of radiomics features distinguished peripheral lung cancer and PIPT was estimated by receiver operating characteristic (ROC) curve and compared by the Delong test. Results A total of 435 radiomics features were extracted, of which 361 features showed relatively good repeatability (ICC ≥ 0.6). 20 features showed the ability to distinguish peripheral lung cancer from PIPT. these features were seen in 14 of 330 Gray-Level Co-occurrence Matrix features, 1 of 49 Intensity Histogram features, 5 of 18 Shape features. The area under the curves (AUC) of these features were 0.731 ± 0.075, 0.717, 0.748 ± 0.038, respectively. The P values of statistical differences among ROC were 0.0499 (F9, F20), 0.0472 (F10, F11) and 0.0145 (F11, Mean4). The discrimination ability of forming new features (Parent Features) after averaging the features extracted at different angles and distances was moderate compared to the previous features (Child features). Conclusion Radiomics features extracted from non-contrast CT based on PET/CT images can help distinguish peripheral lung cancer and PIPT. |
| first_indexed | 2024-12-19T17:35:02Z |
| format | Article |
| id | doaj.art-f5ad8c925a044b889ed13fe4a89e05db |
| institution | Directory Open Access Journal |
| issn | 1471-2342 |
| language | English |
| last_indexed | 2024-12-19T17:35:02Z |
| publishDate | 2020-07-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Imaging |
| spelling | doaj.art-f5ad8c925a044b889ed13fe4a89e05db2022-12-21T20:12:22ZengBMCBMC Medical Imaging1471-23422020-07-0120111010.1186/s12880-020-00475-2Using CT texture analysis to differentiate between peripheral lung cancer and pulmonary inflammatory pseudotumorChenlu Liu0Changsheng Ma1Jinghao Duan2Qingtao Qiu3Yanluan Guo4Zhenhua Zhang5Yong Yin6School of Nuclear Science and Technology, University of South ChinaDepartment of Radiotherapy, Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical SciencesDepartment of Radiotherapy, Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical SciencesDepartment of Radiotherapy, Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical SciencesDepartment of Medical Imaging, Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical SciencesSchool of Nuclear Science and Technology, University of South ChinaDepartment of Radiotherapy, Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical SciencesAbstract Background This study is to distinguish peripheral lung cancer and pulmonary inflammatory pseudotumor using CT-radiomics features extracted from PET/CT images. Methods In this study, the standard 18F-fluorodeoxyglucose positron emission tomography/ computed tomography (18 F-FDG PET/CT) images of 21 patients with pulmonary inflammatory pseudotumor (PIPT) and 21 patients with peripheral lung cancer were retrospectively collected. The dataset was used to extract CT-radiomics features from regions of interest (ROI), The intra-class correlation coefficient (ICC) was used to screen the robust feature from all the radiomic features. Using, then, statistical methods to screen CT-radiomics features, which could distinguish peripheral lung cancer and PIPT. And the ability of radiomics features distinguished peripheral lung cancer and PIPT was estimated by receiver operating characteristic (ROC) curve and compared by the Delong test. Results A total of 435 radiomics features were extracted, of which 361 features showed relatively good repeatability (ICC ≥ 0.6). 20 features showed the ability to distinguish peripheral lung cancer from PIPT. these features were seen in 14 of 330 Gray-Level Co-occurrence Matrix features, 1 of 49 Intensity Histogram features, 5 of 18 Shape features. The area under the curves (AUC) of these features were 0.731 ± 0.075, 0.717, 0.748 ± 0.038, respectively. The P values of statistical differences among ROC were 0.0499 (F9, F20), 0.0472 (F10, F11) and 0.0145 (F11, Mean4). The discrimination ability of forming new features (Parent Features) after averaging the features extracted at different angles and distances was moderate compared to the previous features (Child features). Conclusion Radiomics features extracted from non-contrast CT based on PET/CT images can help distinguish peripheral lung cancer and PIPT.http://link.springer.com/article/10.1186/s12880-020-00475-2Radiomics featuresPeripheral lung cancerPET/CTPulmonary inflammatory pseudotumor |
| spellingShingle | Chenlu Liu Changsheng Ma Jinghao Duan Qingtao Qiu Yanluan Guo Zhenhua Zhang Yong Yin Using CT texture analysis to differentiate between peripheral lung cancer and pulmonary inflammatory pseudotumor BMC Medical Imaging Radiomics features Peripheral lung cancer PET/CT Pulmonary inflammatory pseudotumor |
| title | Using CT texture analysis to differentiate between peripheral lung cancer and pulmonary inflammatory pseudotumor |
| title_full | Using CT texture analysis to differentiate between peripheral lung cancer and pulmonary inflammatory pseudotumor |
| title_fullStr | Using CT texture analysis to differentiate between peripheral lung cancer and pulmonary inflammatory pseudotumor |
| title_full_unstemmed | Using CT texture analysis to differentiate between peripheral lung cancer and pulmonary inflammatory pseudotumor |
| title_short | Using CT texture analysis to differentiate between peripheral lung cancer and pulmonary inflammatory pseudotumor |
| title_sort | using ct texture analysis to differentiate between peripheral lung cancer and pulmonary inflammatory pseudotumor |
| topic | Radiomics features Peripheral lung cancer PET/CT Pulmonary inflammatory pseudotumor |
| url | http://link.springer.com/article/10.1186/s12880-020-00475-2 |
| work_keys_str_mv | AT chenluliu usingcttextureanalysistodifferentiatebetweenperipherallungcancerandpulmonaryinflammatorypseudotumor AT changshengma usingcttextureanalysistodifferentiatebetweenperipherallungcancerandpulmonaryinflammatorypseudotumor AT jinghaoduan usingcttextureanalysistodifferentiatebetweenperipherallungcancerandpulmonaryinflammatorypseudotumor AT qingtaoqiu usingcttextureanalysistodifferentiatebetweenperipherallungcancerandpulmonaryinflammatorypseudotumor AT yanluanguo usingcttextureanalysistodifferentiatebetweenperipherallungcancerandpulmonaryinflammatorypseudotumor AT zhenhuazhang usingcttextureanalysistodifferentiatebetweenperipherallungcancerandpulmonaryinflammatorypseudotumor AT yongyin usingcttextureanalysistodifferentiatebetweenperipherallungcancerandpulmonaryinflammatorypseudotumor |