Yong Han1,2, Yuan Ma1,2, Zhiyuan Wu1,2, Feng Zhang1,2, Deqiang Zheng1,2, Xiangtong Liu1,2, Lixin Tao1,2, Zhigang Liang3, Zhi Yang4, Xia Li5, Jian Huang6, Xiuhua Guo7,8. 1. Department of Epidemiology and Health Statistics, School of Public Health, Capital Medical University, Beijing, China. 2. Beijing Municipal Key Laboratory of Clinical Epidemiology, Capital Medical University, Beijing, China. 3. Department of Nuclear Medicine, Xuanwu Hospital Capital Medical University, Beijing, China. 4. Key Laboratory of Carcinogenesis and Translational Research, Department of Nuclear Medicine, Peking University Cancer Hospital, Beijing, China. 5. Department of Mathematics and Statistics, La Trobe University, Melbourne, Victoria, Australia. 6. School of Mathematical Sciences, University College Cork, Cork, Ireland. 7. Department of Epidemiology and Health Statistics, School of Public Health, Capital Medical University, Beijing, China. statguo@ccmu.edu.cn. 8. Beijing Municipal Key Laboratory of Clinical Epidemiology, Capital Medical University, Beijing, China. statguo@ccmu.edu.cn.
Abstract
PURPOSES: To evaluate the capability of PET/CT images for differentiating the histologic subtypes of non-small cell lung cancer (NSCLC) and to identify the optimal model from radiomics-based machine learning/deep learning algorithms. METHODS: In this study, 867 patients with adenocarcinoma (ADC) and 552 patients with squamous cell carcinoma (SCC) were retrospectively analysed. A stratified random sample of 283 patients (20%) was used as the testing set (173 ADC and 110 SCC); the remaining data were used as the training set. A total of 688 features were extracted from each outlined tumour region. Ten feature selection techniques, ten machine learning (ML) models and the VGG16 deep learning (DL) algorithm were evaluated to construct an optimal classification model for the differential diagnosis of ADC and SCC. Tenfold cross-validation and grid search technique were employed to evaluate and optimize the model hyperparameters on the training dataset. The area under the receiver operating characteristic curve (AUROC), accuracy, precision, sensitivity and specificity was used to evaluate the performance of the models on the test dataset. RESULTS: Fifty top-ranked subset features were selected by each feature selection technique for classification. The linear discriminant analysis (LDA) (AUROC, 0.863; accuracy, 0.794) and support vector machine (SVM) (AUROC, 0.863; accuracy, 0.792) classifiers, both of which coupled with the ℓ2,1NR feature selection method, achieved optimal performance. The random forest (RF) classifier (AUROC, 0.824; accuracy, 0.775) and ℓ2,1NR feature selection method (AUROC, 0.815; accuracy, 0.764) showed excellent average performance among the classifiers and feature selection methods employed in our study, respectively. Furthermore, the VGG16 DL algorithm (AUROC, 0.903; accuracy, 0.841) outperformed all conventional machine learning methods in combination with radiomics. CONCLUSION: Employing radiomic machine learning/deep learning algorithms could help radiologists to differentiate the histologic subtypes of NSCLC via PET/CT images.
PURPOSES: To evaluate the capability of PET/CT images for differentiating the histologic subtypes of non-small cell lung cancer (NSCLC) and to identify the optimal model from radiomics-based machine learning/deep learning algorithms. METHODS: In this study, 867 patients with adenocarcinoma (ADC) and 552 patients with squamous cell carcinoma (SCC) were retrospectively analysed. A stratified random sample of 283 patients (20%) was used as the testing set (173 ADC and 110 SCC); the remaining data were used as the training set. A total of 688 features were extracted from each outlined tumour region. Ten feature selection techniques, ten machine learning (ML) models and the VGG16 deep learning (DL) algorithm were evaluated to construct an optimal classification model for the differential diagnosis of ADC and SCC. Tenfold cross-validation and grid search technique were employed to evaluate and optimize the model hyperparameters on the training dataset. The area under the receiver operating characteristic curve (AUROC), accuracy, precision, sensitivity and specificity was used to evaluate the performance of the models on the test dataset. RESULTS: Fifty top-ranked subset features were selected by each feature selection technique for classification. The linear discriminant analysis (LDA) (AUROC, 0.863; accuracy, 0.794) and support vector machine (SVM) (AUROC, 0.863; accuracy, 0.792) classifiers, both of which coupled with the ℓ2,1NR feature selection method, achieved optimal performance. The random forest (RF) classifier (AUROC, 0.824; accuracy, 0.775) and ℓ2,1NR feature selection method (AUROC, 0.815; accuracy, 0.764) showed excellent average performance among the classifiers and feature selection methods employed in our study, respectively. Furthermore, the VGG16 DL algorithm (AUROC, 0.903; accuracy, 0.841) outperformed all conventional machine learning methods in combination with radiomics. CONCLUSION: Employing radiomic machine learning/deep learning algorithms could help radiologists to differentiate the histologic subtypes of NSCLC via PET/CT images.
Authors: Weimiao Wu; Chintan Parmar; Patrick Grossmann; John Quackenbush; Philippe Lambin; Johan Bussink; Raymond Mak; Hugo J W L Aerts Journal: Front Oncol Date: 2016-03-30 Impact factor: 6.244
Authors: Philippe Thuillier; Virginia Liberini; Osvaldo Rampado; Elena Gallio; Bruno De Santi; Francesco Ceci; Jasna Metovic; Mauro Papotti; Marco Volante; Filippo Molinari; Désirée Deandreis Journal: Biomedicines Date: 2021-03-10