The application of different machine learning models based on PET/CT images and EGFR in predicting brain metastasis of adenocarcinoma of the lung
Abstract Objective To explore the value of six machine learning models based on PET/CT radiomics combined with EGFR in predicting brain metastases of lung adenocarcinoma. Methods Retrospectively collected 204 patients with lung adenocarcinoma who underwent PET/CT examination and EGFR gene detection...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2024-04-01
|
| Series: | BMC Cancer |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12885-024-12158-0 |
| _version_ | 1797209271672242176 |
|---|---|
| author | Chao Kong Xiaoyan Yin Jingmin Zou Changsheng Ma Kai Liu |
| author_facet | Chao Kong Xiaoyan Yin Jingmin Zou Changsheng Ma Kai Liu |
| author_sort | Chao Kong |
| collection | DOAJ |
| description | Abstract Objective To explore the value of six machine learning models based on PET/CT radiomics combined with EGFR in predicting brain metastases of lung adenocarcinoma. Methods Retrospectively collected 204 patients with lung adenocarcinoma who underwent PET/CT examination and EGFR gene detection before treatment from Cancer Hospital Affiliated to Shandong First Medical University in 2020. Using univariate analysis and multivariate logistic regression analysis to find the independent risk factors for brain metastasis. Based on PET/CT imaging combined with EGFR and PET metabolic indexes, established six machine learning models to predict brain metastases of lung adenocarcinoma. Finally, using ten-fold cross-validation to evaluate the predictive effectiveness. Results In univariate analysis, patients with N2-3, EGFR mutation-positive, LYM%≤20, and elevated tumor markers(P<0.05) were more likely to develop brain metastases. In multivariate Logistic regression analysis, PET metabolic indices revealed that SUVmax, SUVpeak, Volume, and TLG were risk factors for lung adenocarcinoma brain metastasis(P<0.05). The SVM model was the most efficient predictor of brain metastasis with an AUC of 0.82 (PET/CT group),0.70 (CT group),0.76 (PET group). Conclusions Radiomics combined with EGFR machine learning model as a new method have higher accuracy than EGFR mutation alone. SVM model is the most effective method for predicting brain metastases of lung adenocarcinoma, and the prediction efficiency of PET/CT group is better than PET group and CT group. |
| first_indexed | 2024-04-24T09:52:03Z |
| format | Article |
| id | doaj.art-425d08635f00444f9c2698ba44258d82 |
| institution | Directory Open Access Journal |
| issn | 1471-2407 |
| language | English |
| last_indexed | 2024-04-24T09:52:03Z |
| publishDate | 2024-04-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Cancer |
| spelling | doaj.art-425d08635f00444f9c2698ba44258d822024-04-14T11:18:52ZengBMCBMC Cancer1471-24072024-04-0124111310.1186/s12885-024-12158-0The application of different machine learning models based on PET/CT images and EGFR in predicting brain metastasis of adenocarcinoma of the lungChao Kong0Xiaoyan Yin1Jingmin Zou2Changsheng Ma3Kai Liu4Department of Graduate, Shandong First Medical University, Shandong Academy of Medical SciencesDepartment of Graduate, Shandong First Medical University, Shandong Academy of Medical SciencesDepartment of Graduate, Shandong First Medical University, Shandong Academy of Medical SciencesDepartment of Radiation Physics, Shandong Cancer Hospital and Institute, Shandong First Medical University, Shandong Academy of Medical SciencesDepartment of Head and Neck Comprehensive Radiotherapy, Affiliated Tumor Hospital of Xinjiang Medical UniversityAbstract Objective To explore the value of six machine learning models based on PET/CT radiomics combined with EGFR in predicting brain metastases of lung adenocarcinoma. Methods Retrospectively collected 204 patients with lung adenocarcinoma who underwent PET/CT examination and EGFR gene detection before treatment from Cancer Hospital Affiliated to Shandong First Medical University in 2020. Using univariate analysis and multivariate logistic regression analysis to find the independent risk factors for brain metastasis. Based on PET/CT imaging combined with EGFR and PET metabolic indexes, established six machine learning models to predict brain metastases of lung adenocarcinoma. Finally, using ten-fold cross-validation to evaluate the predictive effectiveness. Results In univariate analysis, patients with N2-3, EGFR mutation-positive, LYM%≤20, and elevated tumor markers(P<0.05) were more likely to develop brain metastases. In multivariate Logistic regression analysis, PET metabolic indices revealed that SUVmax, SUVpeak, Volume, and TLG were risk factors for lung adenocarcinoma brain metastasis(P<0.05). The SVM model was the most efficient predictor of brain metastasis with an AUC of 0.82 (PET/CT group),0.70 (CT group),0.76 (PET group). Conclusions Radiomics combined with EGFR machine learning model as a new method have higher accuracy than EGFR mutation alone. SVM model is the most effective method for predicting brain metastases of lung adenocarcinoma, and the prediction efficiency of PET/CT group is better than PET group and CT group.https://doi.org/10.1186/s12885-024-12158-0PET/CT radiomicsMachine learning modelLung adenocarcinomaBrain metastases |
| spellingShingle | Chao Kong Xiaoyan Yin Jingmin Zou Changsheng Ma Kai Liu The application of different machine learning models based on PET/CT images and EGFR in predicting brain metastasis of adenocarcinoma of the lung BMC Cancer PET/CT radiomics Machine learning model Lung adenocarcinoma Brain metastases |
| title | The application of different machine learning models based on PET/CT images and EGFR in predicting brain metastasis of adenocarcinoma of the lung |
| title_full | The application of different machine learning models based on PET/CT images and EGFR in predicting brain metastasis of adenocarcinoma of the lung |
| title_fullStr | The application of different machine learning models based on PET/CT images and EGFR in predicting brain metastasis of adenocarcinoma of the lung |
| title_full_unstemmed | The application of different machine learning models based on PET/CT images and EGFR in predicting brain metastasis of adenocarcinoma of the lung |
| title_short | The application of different machine learning models based on PET/CT images and EGFR in predicting brain metastasis of adenocarcinoma of the lung |
| title_sort | application of different machine learning models based on pet ct images and egfr in predicting brain metastasis of adenocarcinoma of the lung |
| topic | PET/CT radiomics Machine learning model Lung adenocarcinoma Brain metastases |
| url | https://doi.org/10.1186/s12885-024-12158-0 |
| work_keys_str_mv | AT chaokong theapplicationofdifferentmachinelearningmodelsbasedonpetctimagesandegfrinpredictingbrainmetastasisofadenocarcinomaofthelung AT xiaoyanyin theapplicationofdifferentmachinelearningmodelsbasedonpetctimagesandegfrinpredictingbrainmetastasisofadenocarcinomaofthelung AT jingminzou theapplicationofdifferentmachinelearningmodelsbasedonpetctimagesandegfrinpredictingbrainmetastasisofadenocarcinomaofthelung AT changshengma theapplicationofdifferentmachinelearningmodelsbasedonpetctimagesandegfrinpredictingbrainmetastasisofadenocarcinomaofthelung AT kailiu theapplicationofdifferentmachinelearningmodelsbasedonpetctimagesandegfrinpredictingbrainmetastasisofadenocarcinomaofthelung AT chaokong applicationofdifferentmachinelearningmodelsbasedonpetctimagesandegfrinpredictingbrainmetastasisofadenocarcinomaofthelung AT xiaoyanyin applicationofdifferentmachinelearningmodelsbasedonpetctimagesandegfrinpredictingbrainmetastasisofadenocarcinomaofthelung AT jingminzou applicationofdifferentmachinelearningmodelsbasedonpetctimagesandegfrinpredictingbrainmetastasisofadenocarcinomaofthelung AT changshengma applicationofdifferentmachinelearningmodelsbasedonpetctimagesandegfrinpredictingbrainmetastasisofadenocarcinomaofthelung AT kailiu applicationofdifferentmachinelearningmodelsbasedonpetctimagesandegfrinpredictingbrainmetastasisofadenocarcinomaofthelung |