Jian Liu1,2,3, Jingjing Cui1,2,3, Fei Liu4, Yixuan Yuan5, Feng Guo6, Guanglei Zhang2,3. 1. School of Computer and Information Technology, Beijing Jiaotong University, Beijing, 100044, China. 2. Beijing Advanced Innovation Center for Biomedical Engineering, Beihang University, Beijing, 100083, China. 3. School of Biological Science and Medical Engineering, Beihang University, Beijing, 100083, China. 4. Key Laboratory of the Ministry of Education for Optoelectronic Measurement Technology and Instrument, Beijing Information Science and Technology University, Beijing, 100192, China. 5. School of Computer and Information Technology, City University of Hong Kong, Hong Kong, SAR, China. 6. Department of Thoracic Surgery, Peking Union Medical College Hospital, Peking Union Medical College, Chinese Academy of Medical Science, Beijing, 100730, China.
Abstract
PURPOSE: Histological subtypes of non-small cell lung cancer (NSCLC) are crucial for systematic treatment decisions. However, the current studies which used noninvasive radiomic methods to classify NSCLC histology subtypes mainly focused on two main subtypes: squamous cell carcinoma (SCC) and adenocarcinoma (ADC), while multi-subtype classifications that included the other two subtypes of NSCLC: large cell carcinoma (LCC) and not otherwise specified (NOS), were very few in the previous studies. The aim of this work was to establish a multi-subtype classification model for the four main subtypes of NSCLC and improve the classification performance and generalization ability compared with previous studies. METHODS: In this work, we extracted 1029 features from regions of interest in computed tomography (CT) images of 349 patients from two different datasets using radiomic methods. Based on "three-in-one" concept, we proposed a model called SLS wrapping three algorithms, synthetic minority oversampling technique, ℓ2,1-norm minimization, and support vector machines, into one hybrid technique to classify the four main subtypes of NSCLC: SCC, ADC, LCC, and NOS, which could cover the whole range of NSCLC. RESULTS: We analyzed the 247 features obtained by dimension reduction, and found that the extracted features from three methods: first order statistics, gray level co-occurrence matrix, and gray level size zone matrix, were more conducive to the classification of NSCLC subtypes. The proposed SLS model achieved an average classification accuracy of 0.89 on the training set (95% confidence interval [CI]: 0.846 to 0.912) and a classification accuracy of 0.86 on the test set (95% CI: 0.779 to 0.941). CONCLUSIONS: The experiment results showed that the subtypes of NSCLC could be well classified by radiomic method. Our SLS model can accurately classify and diagnose the four subtypes of NSCLC based on CT images, and thus it has the potential to be used in the clinical practice to provide valuable information for lung cancer treatment and further promote the personalized medicine.
PURPOSE: Histological subtypes of non-small cell lung cancer (NSCLC) are crucial for systematic treatment decisions. However, the current studies which used noninvasive radiomic methods to classify NSCLC histology subtypes mainly focused on two main subtypes: squamous cell carcinoma (SCC) and adenocarcinoma (ADC), while multi-subtype classifications that included the other two subtypes of NSCLC: large cell carcinoma (LCC) and not otherwise specified (NOS), were very few in the previous studies. The aim of this work was to establish a multi-subtype classification model for the four main subtypes of NSCLC and improve the classification performance and generalization ability compared with previous studies. METHODS: In this work, we extracted 1029 features from regions of interest in computed tomography (CT) images of 349 patients from two different datasets using radiomic methods. Based on "three-in-one" concept, we proposed a model called SLS wrapping three algorithms, synthetic minority oversampling technique, ℓ2,1-norm minimization, and support vector machines, into one hybrid technique to classify the four main subtypes of NSCLC: SCC, ADC, LCC, and NOS, which could cover the whole range of NSCLC. RESULTS: We analyzed the 247 features obtained by dimension reduction, and found that the extracted features from three methods: first order statistics, gray level co-occurrence matrix, and gray level size zone matrix, were more conducive to the classification of NSCLC subtypes. The proposed SLS model achieved an average classification accuracy of 0.89 on the training set (95% confidence interval [CI]: 0.846 to 0.912) and a classification accuracy of 0.86 on the test set (95% CI: 0.779 to 0.941). CONCLUSIONS: The experiment results showed that the subtypes of NSCLC could be well classified by radiomic method. Our SLS model can accurately classify and diagnose the four subtypes of NSCLC based on CT images, and thus it has the potential to be used in the clinical practice to provide valuable information for lung cancer treatment and further promote the personalized medicine.