A Machine Learning Model Based on PET/CT Radiomics and Clinical Characteristics Predicts ALK Rearrangement Status in Lung Adenocarcinoma
ObjectivesAnaplastic lymphoma kinase (ALK) rearrangement status examination has been widely used in clinic for non-small cell lung cancer (NSCLC) patients in order to find patients that can be treated with targeted ALK inhibitors. This study intended to non-invasively predict the ALK rearrangement s...
| Main Authors: | , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2021-03-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2021.603882/full |
| _version_ | 1818870505273294848 |
|---|---|
| author | Cheng Chang Cheng Chang Xiaoyan Sun Xiaoyan Sun Gang Wang Hong Yu Wenlu Zhao Yaqiong Ge Shaofeng Duan Xiaohua Qian Rui Wang Bei Lei Lihua Wang Liu Liu Liu Liu Maomei Ruan Hui Yan Ciyi Liu Jie Chen Wenhui Xie Wenhui Xie |
| author_facet | Cheng Chang Cheng Chang Xiaoyan Sun Xiaoyan Sun Gang Wang Hong Yu Wenlu Zhao Yaqiong Ge Shaofeng Duan Xiaohua Qian Rui Wang Bei Lei Lihua Wang Liu Liu Liu Liu Maomei Ruan Hui Yan Ciyi Liu Jie Chen Wenhui Xie Wenhui Xie |
| author_sort | Cheng Chang |
| collection | DOAJ |
| description | ObjectivesAnaplastic lymphoma kinase (ALK) rearrangement status examination has been widely used in clinic for non-small cell lung cancer (NSCLC) patients in order to find patients that can be treated with targeted ALK inhibitors. This study intended to non-invasively predict the ALK rearrangement status in lung adenocarcinomas by developing a machine learning model that combines PET/CT radiomic features and clinical characteristics.MethodsFive hundred twenty-six patients of lung adenocarcinoma with PET/CT scan examination were enrolled, including 109 positive and 417 negative patients for ALK rearrangements from February 2016 to March 2019. The Artificial Intelligence Kit software was used to extract radiomic features of PET/CT images. The maximum relevance minimum redundancy (mRMR) and least absolute shrinkage and selection operator (LASSO) logistic regression were further employed to select the most distinguishable radiomic features to construct predictive models. The mRMR is a feature selection method, which selects the features with high correlation to the pathological results (maximum correlation), meanwhile retain the features with minimum correlation between them (minimum redundancy). LASSO is a statistical formula whose main purpose is the feature selection and regularization of data model. LASSO method regularizes model parameters by shrinking the regression coefficients, reducing some of them to zero. The feature selection phase occurs after the shrinkage, where every non-zero value is selected to be used in the model. Receiver operating characteristic (ROC) analysis was used to evaluate the performance of the models, and the performance of different models was compared by the DeLong test.ResultsA total of 22 radiomic features were extracted from PET/CT images for constructing the PET/CT radiomic model, and majority of these features used were based on CT features (20 out of 22), only 2 PET features were included (PET percentile 10 and PET difference entropy). Moreover, three clinical features associated with ALK mutation (age, burr and pleural effusion) were also employed to construct a combined model of PET/CT and clinical model. We found that this combined model PET/CT-clinical model has a significant advantage to predict the ALK mutation status in the training group (AUC = 0.87) and the testing group (AUC = 0.88) compared with the clinical model alone in the training group (AUC = 0.76) and the testing group (AUC = 0.74) respectively. However, there is no significant difference between the combined model and PET/CT radiomic model.ConclusionsThis study demonstrated that PET/CT radiomics-based machine learning model has potential to be used as a non-invasive diagnostic method to help diagnose ALK mutation status for lung adenocarcinoma patients in the clinic. |
| first_indexed | 2024-12-19T12:08:05Z |
| format | Article |
| id | doaj.art-c7b713a041f74dd28d3fbdb9420195a3 |
| institution | Directory Open Access Journal |
| issn | 2234-943X |
| language | English |
| last_indexed | 2024-12-19T12:08:05Z |
| publishDate | 2021-03-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj.art-c7b713a041f74dd28d3fbdb9420195a32022-12-21T20:22:18ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2021-03-011110.3389/fonc.2021.603882603882A Machine Learning Model Based on PET/CT Radiomics and Clinical Characteristics Predicts ALK Rearrangement Status in Lung AdenocarcinomaCheng Chang0Cheng Chang1Xiaoyan Sun2Xiaoyan Sun3Gang Wang4Hong Yu5Wenlu Zhao6Yaqiong Ge7Shaofeng Duan8Xiaohua Qian9Rui Wang10Bei Lei11Lihua Wang12Liu Liu13Liu Liu14Maomei Ruan15Hui Yan16Ciyi Liu17Jie Chen18Wenhui Xie19Wenhui Xie20Department of Nuclear Medicine, Shanghai Chest Hospital, Shanghai Jiao Tong University, Shanghai, ChinaClinical and Translational Center in Shanghai Chest Hospital, Shanghai Key Laboratory for Molecular Imaging, Shanghai University of Medicine and Health Sciences, Shanghai, ChinaDepartment of Nuclear Medicine, Shanghai Chest Hospital, Shanghai Jiao Tong University, Shanghai, ChinaClinical and Translational Center in Shanghai Chest Hospital, Shanghai Key Laboratory for Molecular Imaging, Shanghai University of Medicine and Health Sciences, Shanghai, ChinaStatistical Center, Shanghai Chest Hospital, Shanghai Jiao Tong University, Shanghai, ChinaDepartment of Radiology, Shanghai Chest Hospital, Shanghai Jiao Tong University, Shanghai, ChinaDepartment of Radiology, Second Affiliated Hospital of Soochow University, Suzhou, ChinaPharmaceutical Diagnostic Department, GE Healthcare China, Shanghai, ChinaPharmaceutical Diagnostic Department, GE Healthcare China, Shanghai, ChinaInstitute for Medical Imaging Technology, School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, ChinaDepartment of Thoracic Surgery, Shanghai Chest Hospital, Shanghai Jiao Tong University, Shanghai, ChinaDepartment of Nuclear Medicine, Shanghai Chest Hospital, Shanghai Jiao Tong University, Shanghai, ChinaDepartment of Nuclear Medicine, Shanghai Chest Hospital, Shanghai Jiao Tong University, Shanghai, ChinaDepartment of Nuclear Medicine, Shanghai Chest Hospital, Shanghai Jiao Tong University, Shanghai, ChinaClinical and Translational Center in Shanghai Chest Hospital, Shanghai Key Laboratory for Molecular Imaging, Shanghai University of Medicine and Health Sciences, Shanghai, ChinaDepartment of Nuclear Medicine, Shanghai Chest Hospital, Shanghai Jiao Tong University, Shanghai, ChinaDepartment of Nuclear Medicine, Shanghai Chest Hospital, Shanghai Jiao Tong University, Shanghai, ChinaDepartment of Nuclear Medicine, Shanghai Chest Hospital, Shanghai Jiao Tong University, Shanghai, ChinaDepartment of Ultrasound, Shanghai Chest Hospital, Shanghai Jiao Tong University, Shanghai, ChinaDepartment of Nuclear Medicine, Shanghai Chest Hospital, Shanghai Jiao Tong University, Shanghai, ChinaClinical and Translational Center in Shanghai Chest Hospital, Shanghai Key Laboratory for Molecular Imaging, Shanghai University of Medicine and Health Sciences, Shanghai, ChinaObjectivesAnaplastic lymphoma kinase (ALK) rearrangement status examination has been widely used in clinic for non-small cell lung cancer (NSCLC) patients in order to find patients that can be treated with targeted ALK inhibitors. This study intended to non-invasively predict the ALK rearrangement status in lung adenocarcinomas by developing a machine learning model that combines PET/CT radiomic features and clinical characteristics.MethodsFive hundred twenty-six patients of lung adenocarcinoma with PET/CT scan examination were enrolled, including 109 positive and 417 negative patients for ALK rearrangements from February 2016 to March 2019. The Artificial Intelligence Kit software was used to extract radiomic features of PET/CT images. The maximum relevance minimum redundancy (mRMR) and least absolute shrinkage and selection operator (LASSO) logistic regression were further employed to select the most distinguishable radiomic features to construct predictive models. The mRMR is a feature selection method, which selects the features with high correlation to the pathological results (maximum correlation), meanwhile retain the features with minimum correlation between them (minimum redundancy). LASSO is a statistical formula whose main purpose is the feature selection and regularization of data model. LASSO method regularizes model parameters by shrinking the regression coefficients, reducing some of them to zero. The feature selection phase occurs after the shrinkage, where every non-zero value is selected to be used in the model. Receiver operating characteristic (ROC) analysis was used to evaluate the performance of the models, and the performance of different models was compared by the DeLong test.ResultsA total of 22 radiomic features were extracted from PET/CT images for constructing the PET/CT radiomic model, and majority of these features used were based on CT features (20 out of 22), only 2 PET features were included (PET percentile 10 and PET difference entropy). Moreover, three clinical features associated with ALK mutation (age, burr and pleural effusion) were also employed to construct a combined model of PET/CT and clinical model. We found that this combined model PET/CT-clinical model has a significant advantage to predict the ALK mutation status in the training group (AUC = 0.87) and the testing group (AUC = 0.88) compared with the clinical model alone in the training group (AUC = 0.76) and the testing group (AUC = 0.74) respectively. However, there is no significant difference between the combined model and PET/CT radiomic model.ConclusionsThis study demonstrated that PET/CT radiomics-based machine learning model has potential to be used as a non-invasive diagnostic method to help diagnose ALK mutation status for lung adenocarcinoma patients in the clinic.https://www.frontiersin.org/articles/10.3389/fonc.2021.603882/fullpositron emission tomography/computed tomography (PET/CT)machine learningradiomicsanaplastic lymphoma kinase (ALK) rearrangementlung adenocarcinoma |
| spellingShingle | Cheng Chang Cheng Chang Xiaoyan Sun Xiaoyan Sun Gang Wang Hong Yu Wenlu Zhao Yaqiong Ge Shaofeng Duan Xiaohua Qian Rui Wang Bei Lei Lihua Wang Liu Liu Liu Liu Maomei Ruan Hui Yan Ciyi Liu Jie Chen Wenhui Xie Wenhui Xie A Machine Learning Model Based on PET/CT Radiomics and Clinical Characteristics Predicts ALK Rearrangement Status in Lung Adenocarcinoma Frontiers in Oncology positron emission tomography/computed tomography (PET/CT) machine learning radiomics anaplastic lymphoma kinase (ALK) rearrangement lung adenocarcinoma |
| title | A Machine Learning Model Based on PET/CT Radiomics and Clinical Characteristics Predicts ALK Rearrangement Status in Lung Adenocarcinoma |
| title_full | A Machine Learning Model Based on PET/CT Radiomics and Clinical Characteristics Predicts ALK Rearrangement Status in Lung Adenocarcinoma |
| title_fullStr | A Machine Learning Model Based on PET/CT Radiomics and Clinical Characteristics Predicts ALK Rearrangement Status in Lung Adenocarcinoma |
| title_full_unstemmed | A Machine Learning Model Based on PET/CT Radiomics and Clinical Characteristics Predicts ALK Rearrangement Status in Lung Adenocarcinoma |
| title_short | A Machine Learning Model Based on PET/CT Radiomics and Clinical Characteristics Predicts ALK Rearrangement Status in Lung Adenocarcinoma |
| title_sort | machine learning model based on pet ct radiomics and clinical characteristics predicts alk rearrangement status in lung adenocarcinoma |
| topic | positron emission tomography/computed tomography (PET/CT) machine learning radiomics anaplastic lymphoma kinase (ALK) rearrangement lung adenocarcinoma |
| url | https://www.frontiersin.org/articles/10.3389/fonc.2021.603882/full |
| work_keys_str_mv | AT chengchang amachinelearningmodelbasedonpetctradiomicsandclinicalcharacteristicspredictsalkrearrangementstatusinlungadenocarcinoma AT chengchang amachinelearningmodelbasedonpetctradiomicsandclinicalcharacteristicspredictsalkrearrangementstatusinlungadenocarcinoma AT xiaoyansun amachinelearningmodelbasedonpetctradiomicsandclinicalcharacteristicspredictsalkrearrangementstatusinlungadenocarcinoma AT xiaoyansun amachinelearningmodelbasedonpetctradiomicsandclinicalcharacteristicspredictsalkrearrangementstatusinlungadenocarcinoma AT gangwang amachinelearningmodelbasedonpetctradiomicsandclinicalcharacteristicspredictsalkrearrangementstatusinlungadenocarcinoma AT hongyu amachinelearningmodelbasedonpetctradiomicsandclinicalcharacteristicspredictsalkrearrangementstatusinlungadenocarcinoma AT wenluzhao amachinelearningmodelbasedonpetctradiomicsandclinicalcharacteristicspredictsalkrearrangementstatusinlungadenocarcinoma AT yaqiongge amachinelearningmodelbasedonpetctradiomicsandclinicalcharacteristicspredictsalkrearrangementstatusinlungadenocarcinoma AT shaofengduan amachinelearningmodelbasedonpetctradiomicsandclinicalcharacteristicspredictsalkrearrangementstatusinlungadenocarcinoma AT xiaohuaqian amachinelearningmodelbasedonpetctradiomicsandclinicalcharacteristicspredictsalkrearrangementstatusinlungadenocarcinoma AT ruiwang amachinelearningmodelbasedonpetctradiomicsandclinicalcharacteristicspredictsalkrearrangementstatusinlungadenocarcinoma AT beilei amachinelearningmodelbasedonpetctradiomicsandclinicalcharacteristicspredictsalkrearrangementstatusinlungadenocarcinoma AT lihuawang amachinelearningmodelbasedonpetctradiomicsandclinicalcharacteristicspredictsalkrearrangementstatusinlungadenocarcinoma AT liuliu amachinelearningmodelbasedonpetctradiomicsandclinicalcharacteristicspredictsalkrearrangementstatusinlungadenocarcinoma AT liuliu amachinelearningmodelbasedonpetctradiomicsandclinicalcharacteristicspredictsalkrearrangementstatusinlungadenocarcinoma AT maomeiruan amachinelearningmodelbasedonpetctradiomicsandclinicalcharacteristicspredictsalkrearrangementstatusinlungadenocarcinoma AT huiyan amachinelearningmodelbasedonpetctradiomicsandclinicalcharacteristicspredictsalkrearrangementstatusinlungadenocarcinoma AT ciyiliu amachinelearningmodelbasedonpetctradiomicsandclinicalcharacteristicspredictsalkrearrangementstatusinlungadenocarcinoma AT jiechen amachinelearningmodelbasedonpetctradiomicsandclinicalcharacteristicspredictsalkrearrangementstatusinlungadenocarcinoma AT wenhuixie amachinelearningmodelbasedonpetctradiomicsandclinicalcharacteristicspredictsalkrearrangementstatusinlungadenocarcinoma AT wenhuixie amachinelearningmodelbasedonpetctradiomicsandclinicalcharacteristicspredictsalkrearrangementstatusinlungadenocarcinoma AT chengchang machinelearningmodelbasedonpetctradiomicsandclinicalcharacteristicspredictsalkrearrangementstatusinlungadenocarcinoma AT chengchang machinelearningmodelbasedonpetctradiomicsandclinicalcharacteristicspredictsalkrearrangementstatusinlungadenocarcinoma AT xiaoyansun machinelearningmodelbasedonpetctradiomicsandclinicalcharacteristicspredictsalkrearrangementstatusinlungadenocarcinoma AT xiaoyansun machinelearningmodelbasedonpetctradiomicsandclinicalcharacteristicspredictsalkrearrangementstatusinlungadenocarcinoma AT gangwang machinelearningmodelbasedonpetctradiomicsandclinicalcharacteristicspredictsalkrearrangementstatusinlungadenocarcinoma AT hongyu machinelearningmodelbasedonpetctradiomicsandclinicalcharacteristicspredictsalkrearrangementstatusinlungadenocarcinoma AT wenluzhao machinelearningmodelbasedonpetctradiomicsandclinicalcharacteristicspredictsalkrearrangementstatusinlungadenocarcinoma AT yaqiongge machinelearningmodelbasedonpetctradiomicsandclinicalcharacteristicspredictsalkrearrangementstatusinlungadenocarcinoma AT shaofengduan machinelearningmodelbasedonpetctradiomicsandclinicalcharacteristicspredictsalkrearrangementstatusinlungadenocarcinoma AT xiaohuaqian machinelearningmodelbasedonpetctradiomicsandclinicalcharacteristicspredictsalkrearrangementstatusinlungadenocarcinoma AT ruiwang machinelearningmodelbasedonpetctradiomicsandclinicalcharacteristicspredictsalkrearrangementstatusinlungadenocarcinoma AT beilei machinelearningmodelbasedonpetctradiomicsandclinicalcharacteristicspredictsalkrearrangementstatusinlungadenocarcinoma AT lihuawang machinelearningmodelbasedonpetctradiomicsandclinicalcharacteristicspredictsalkrearrangementstatusinlungadenocarcinoma AT liuliu machinelearningmodelbasedonpetctradiomicsandclinicalcharacteristicspredictsalkrearrangementstatusinlungadenocarcinoma AT liuliu machinelearningmodelbasedonpetctradiomicsandclinicalcharacteristicspredictsalkrearrangementstatusinlungadenocarcinoma AT maomeiruan machinelearningmodelbasedonpetctradiomicsandclinicalcharacteristicspredictsalkrearrangementstatusinlungadenocarcinoma AT huiyan machinelearningmodelbasedonpetctradiomicsandclinicalcharacteristicspredictsalkrearrangementstatusinlungadenocarcinoma AT ciyiliu machinelearningmodelbasedonpetctradiomicsandclinicalcharacteristicspredictsalkrearrangementstatusinlungadenocarcinoma AT jiechen machinelearningmodelbasedonpetctradiomicsandclinicalcharacteristicspredictsalkrearrangementstatusinlungadenocarcinoma AT wenhuixie machinelearningmodelbasedonpetctradiomicsandclinicalcharacteristicspredictsalkrearrangementstatusinlungadenocarcinoma AT wenhuixie machinelearningmodelbasedonpetctradiomicsandclinicalcharacteristicspredictsalkrearrangementstatusinlungadenocarcinoma |