Clinical radiomics-based machine learning versus three-dimension convolutional neural network analysis for differentiation of thymic epithelial tumors from other prevascular mediastinal tumors on chest computed tomography scan

Frontiers in Oncology

Oncology

Chia-Ying Lin¹  Yi-Sheng Liu¹  Fu-Zong Wu²  Ming-Ting Wu³  Mi-Chia Ma⁴  En-Kuei Tang⁵  Yau-Lin Tseng⁶  Chao-Chun Chang⁶  Yi-Ting Yen⁷  Yu-Feng Wei⁸ 

[1] Department of Medical Imaging, National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University, Tainan, Taiwan;Department of Radiology, Kaohsiung Veterans General Hospital, Kaohsiung, Taiwan;Faculty of Clinical Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan;Institute of Education, National Sun Yat-sen University, Kaohsiung, Taiwan;Department of Radiology, Kaohsiung Veterans General Hospital, Kaohsiung, Taiwan;School of Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan;Institute of Clinical Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan;Department of Statistics and Institute of Data Science, National Cheng Kung University, Tainan, Taiwan;Division of Thoracic Surgery, Department of Surgery, Kaohsiung Veterans General Hospital, Kaohsiung, Taiwan;Division of Thoracic Surgery, Department of Surgery, National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University, Tainan, Taiwan;Division of Thoracic Surgery, Department of Surgery, National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University, Tainan, Taiwan;Division of Trauma and Acute Care Surgery, Department of Surgery, National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University, Tainan, Taiwan;School of Medicine for International Students, College of Medicine, I-Shou University, Kaohsiung, Taiwan;Division of Chest Medicine, Department of Internal Medicine, E-Da Cancer Hospital, Kaohsiung, Taiwan;

关键词: radiomics;    convolutional neural networks;    deep learning;    machine learning;    prevascular mediastinal tumor;   

DOI  :  10.3389/fonc.2023.1105100

 received in 2022-11-22, accepted in 2023-03-27,  发布年份 2023

来源: Frontiers

【 摘 要 】

PurposeTo compare the diagnostic performance of radiomic analysis with machine learning (ML) model with a convolutional neural network (CNN) in differentiating thymic epithelial tumors (TETs) from other prevascular mediastinal tumors (PMTs).MethodsA retrospective study was performed in patients with PMTs and undergoing surgical resection or biopsy in National Cheng Kung University Hospital, Tainan, Taiwan, E-Da Hospital, Kaohsiung, Taiwan, and Kaohsiung Veterans General Hospital, Kaohsiung, Taiwan between January 2010 and December 2019. Clinical data including age, sex, myasthenia gravis (MG) symptoms and pathologic diagnosis were collected. The datasets were divided into UECT (unenhanced computed tomography) and CECT (enhanced computed tomography) for analysis and modelling. Radiomics model and 3D CNN model were used to differentiate TETs from non-TET PMTs (including cyst, malignant germ cell tumor, lymphoma and teratoma). The macro F1-score and receiver operating characteristic (ROC) analysis were performed to evaluate the prediction models.ResultIn the UECT dataset, there were 297 patients with TETs and 79 patients with other PMTs. The performance of radiomic analysis with machine learning model using LightGBM with Extra Tree (macro F1-Score = 83.95%, ROC-AUC = 0.9117) had better performance than the 3D CNN model (macro F1-score = 75.54%, ROC-AUC = 0.9015). In the CECT dataset, there were 296 patients with TETs and 77 patients with other PMTs. The performance of radiomic analysis with machine learning model using LightGBM with Extra Tree (macro F1-Score = 85.65%, ROC-AUC = 0.9464) had better performance than the 3D CNN model (macro F1-score = 81.01%, ROC-AUC = 0.9275).ConclusionOur study revealed that the individualized prediction model integrating clinical information and radiomic features using machine learning demonstrated better predictive performance in the differentiation of TETs from other PMTs at chest CT scan than 3D CNN model.

【 授权许可】

Unknown   
Copyright © 2023 Chang, Tang, Wei, Lin, Wu, Wu, Liu, Yen, Ma and Tseng