Dan Bao1, Yanfeng Zhao1, Zhou Liu2, Hongxia Zhong1, Yayuan Geng3, Meng Lin1, Lin Li1, Xinming Zhao1, Dehong Luo4. 1. Department of Radiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100021, China. 2. Department of Radiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital & Shenzhen Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Shenzhen, 518116, China. 3. Huiying Medical Technology (Beijing) Co., Ltd, HaiDian District, B-2 Building, Dongsheng Science Park, Beijing City, 100192, People's Republic of China. 4. Department of Radiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100021, China. pumccancer@163.com.
Abstract
PURPOSE: To explore the value of MRI-based radiomics features in predicting risk in disease progression for nasopharyngeal carcinoma (NPC). METHODS: 199 patients confirmed with NPC were retrospectively included and then divided into training and validation set using a hold-out validation (159: 40). Discriminative radiomic features were selected with a Wilcoxon signed-rank test from tumors and normal masticatory muscles of 37 NPC patients. LASSO Cox regression and Pearson correlation analysis were applied to further confirm the differential expression of the radiomic features in the training set. Using the multiple Cox regression model, we built a radiomic feature-based classifier, Rad-Score. The prognostic and predictive performance of Rad-Score was validated in the validation cohort and illustrated in all included 199 patients. RESULTS: We identified 1832 differentially expressed radiomic features between tumors and normal tissue. Rad-Score was built based on one radiomic feature: CET1-w_wavelet.LLH_GLDM_Dependence-Entropy. Rad-Score showed a satisfactory performance to predict disease progression in NPC with an area under the curve (AUC) of 0.604, 0.732, 0.626 in the training, validation, and the combined cohort (all 199 patients included) respectively. Rad-Score improved risk stratification, and disease progression-free survival was significantly different between these groups in every cohort of patients (p = 0.044 or p < 0.01). Combining radiomics and clinical features, higher AUC was achieved of the prediction of 3-year disease progression-free survival (PFS) (AUC, 0.78) and 5-year disease PFS (AUC, 0.73), although there was no statistical difference. CONCLUSION: The radiomics classifier, Rad-Score, was proven useful for pretreatment prognosis prediction and showed potential in risk stratification for NPC.
PURPOSE: To explore the value of MRI-based radiomics features in predicting risk in disease progression for nasopharyngeal carcinoma (NPC). METHODS: 199 patients confirmed with NPC were retrospectively included and then divided into training and validation set using a hold-out validation (159: 40). Discriminative radiomic features were selected with a Wilcoxon signed-rank test from tumors and normal masticatory muscles of 37 NPC patients. LASSO Cox regression and Pearson correlation analysis were applied to further confirm the differential expression of the radiomic features in the training set. Using the multiple Cox regression model, we built a radiomic feature-based classifier, Rad-Score. The prognostic and predictive performance of Rad-Score was validated in the validation cohort and illustrated in all included 199 patients. RESULTS: We identified 1832 differentially expressed radiomic features between tumors and normal tissue. Rad-Score was built based on one radiomic feature: CET1-w_wavelet.LLH_GLDM_Dependence-Entropy. Rad-Score showed a satisfactory performance to predict disease progression in NPC with an area under the curve (AUC) of 0.604, 0.732, 0.626 in the training, validation, and the combined cohort (all 199 patients included) respectively. Rad-Score improved risk stratification, and disease progression-free survival was significantly different between these groups in every cohort of patients (p = 0.044 or p < 0.01). Combining radiomics and clinical features, higher AUC was achieved of the prediction of 3-year disease progression-free survival (PFS) (AUC, 0.78) and 5-year disease PFS (AUC, 0.73), although there was no statistical difference. CONCLUSION: The radiomics classifier, Rad-Score, was proven useful for pretreatment prognosis prediction and showed potential in risk stratification for NPC.
Authors: Jian Ji Pan; Wai Tong Ng; Jing Feng Zong; Lucy L K Chan; Brian O'Sullivan; Shao Jun Lin; Henry C K Sze; Yun Bin Chen; Horace C W Choi; Qiao Juan Guo; Wai Kuen Kan; You Ping Xiao; Xu Wei; Quynh Thu Le; Christine M Glastonbury; A Dimitrios Colevas; Randal S Weber; Jatin P Shah; Anne W M Lee Journal: Cancer Date: 2015-11-20 Impact factor: 6.860
Authors: Richard Du; Victor H Lee; Hui Yuan; Ka-On Lam; Herbert H Pang; Yu Chen; Edmund Y Lam; Pek-Lan Khong; Anne W Lee; Dora L Kwong; Varut Vardhanabhuti Journal: Radiol Artif Intell Date: 2019-07-10
Authors: Marius E Mayerhoefer; Andrzej Materka; Georg Langs; Ida Häggström; Piotr Szczypiński; Peter Gibbs; Gary Cook Journal: J Nucl Med Date: 2020-02-14 Impact factor: 11.082
Authors: Frances Duane; Marianne C Aznar; Freddie Bartlett; David J Cutter; Sarah C Darby; Reshma Jagsi; Ebbe L Lorenzen; Orla McArdle; Paul McGale; Saul Myerson; Kazem Rahimi; Sindu Vivekanandan; Samantha Warren; Carolyn W Taylor Journal: Radiother Oncol Date: 2017-02-21 Impact factor: 6.280