Yixian Guo1, Qiong Song2, Mengmeng Jiang3, Yinglong Guo4, Peng Xu5, Yiqian Zhang5, Chi-Cheng Fu5, Qu Fang5, Mengsu Zeng6, Xiuzhong Yao7. 1. Department of Radiology, Zhongshan Hospital of Fudan University, Fudan University, No 130, Dongan Rd, Xuhui District, Shanghai, 200032, P.R. of China. 2. Xuzhou Mining Group General Hospital, radiology department, Xuzhou, Jiangsu, 221000, P.R. of China; Shanghai Aitrox Technology Corporation Limited, Shanghai, 200032, P.R. of China. 3. Department of Radiology, Shanghai Institute of Medical Imaging, Zhongshan Hospital of Fudan University, Fudan University, No 130, Dongan Rd, Xuhui District, Shanghai, 200032, P.R. of China. 4. Department of Radiology, Zhongshan Hospital of Fudan University, Fudan University, No138, Fenglin Rd, Xuhui District, Shanghai, 200032, P.R. of China. 5. Shanghai Aitrox Technology Corporation Limited, Shanghai, 200032, P.R. of China. 6. Department of Radiology, Zhongshan Hospital of Fudan University, Fudan University. 7. Department of Radiology, Shanghai Institute of Medical Imaging, Zhongshan Hospital of Fudan University, Fudan University, No 130, Dongan Rd, Xuhui District, Shanghai, 200032, P.R. of China. Electronic address: zsyyyxz@163.com.
Abstract
RATIONALE AND OBJECTIVES: Histological subtypes of lung cancers are critical for clinical treatment decision. In this study, we attempt to use 3D deep learning and radiomics methods to automatically distinguish lung adenocarcinomas (ADC), squamous cell carcinomas (SCC), and small cell lung cancers (SCLC) respectively on Computed Tomography images, and then compare their performance. MATERIALS AND METHODS: 920 patients (mean age 61.2, range, 17-87; 340 Female and 580 Male) with lung cancer, including 554 patients with ADC, 175 patients with lung SCC and 191 patients with SCLC, were included in this retrospective study from January 2013 to August 2018. Histopathologic analysis was available for every patient. The classification models based on 3D deep learning (named the ProNet) and radiomics (named com_radNet) were designed to classify lung cancers into the three types mentioned above according to histopathologic results. The training, validation and testing cohorts counted 0.70, 0.15, and 0.15 of the whole datasets respectively. RESULTS: The ProNet model used to classify the three types of lung cancers achieved the F1-scores of 90.0%, 72.4%, 83.7% in SCC, ADC, and SCLC respectively, and the weighted average F1-score of 73.2%. For com_radNet, the F1-scores achieved 83.1%, 75.4%, 85.1% in SCC, ADC, and SCLC, and the weighted average F1-score was 72.2%. The area under the receiver operating characteristic curve of the ProNet model and com_radNet were 0.840 and 0.789, and the accuracy were 71.6% and 74.7% respectively. CONCLUSION: The ProNet and com_radNet models we developed can achieve high performance in distinguishing ADC, SCC, and SCLC and may be promising approaches for non-invasive predicting histological subtypes of lung cancers.
RATIONALE AND OBJECTIVES: Histological subtypes of lung cancers are critical for clinical treatment decision. In this study, we attempt to use 3D deep learning and radiomics methods to automatically distinguish lung adenocarcinomas (ADC), squamous cell carcinomas (SCC), and small cell lung cancers (SCLC) respectively on Computed Tomography images, and then compare their performance. MATERIALS AND METHODS: 920 patients (mean age 61.2, range, 17-87; 340 Female and 580 Male) with lung cancer, including 554 patients with ADC, 175 patients with lung SCC and 191 patients with SCLC, were included in this retrospective study from January 2013 to August 2018. Histopathologic analysis was available for every patient. The classification models based on 3D deep learning (named the ProNet) and radiomics (named com_radNet) were designed to classify lung cancers into the three types mentioned above according to histopathologic results. The training, validation and testing cohorts counted 0.70, 0.15, and 0.15 of the whole datasets respectively. RESULTS: The ProNet model used to classify the three types of lung cancers achieved the F1-scores of 90.0%, 72.4%, 83.7% in SCC, ADC, and SCLC respectively, and the weighted average F1-score of 73.2%. For com_radNet, the F1-scores achieved 83.1%, 75.4%, 85.1% in SCC, ADC, and SCLC, and the weighted average F1-score was 72.2%. The area under the receiver operating characteristic curve of the ProNet model and com_radNet were 0.840 and 0.789, and the accuracy were 71.6% and 74.7% respectively. CONCLUSION: The ProNet and com_radNet models we developed can achieve high performance in distinguishing ADC, SCC, and SCLC and may be promising approaches for non-invasive predicting histological subtypes of lung cancers.