Mengyun Qiang1, Chaofeng Li2, Yuyao Sun3, Ying Sun4, Liangru Ke5, Chuanmiao Xie5, Tao Zhang6, Yujian Zou7, Wenze Qiu8, Mingyong Gao9, Yingxue Li3, Xiang Li3, Zejiang Zhan8, Kuiyuan Liu1, Xi Chen1, Chixiong Liang1, Qiuyan Chen1, Haiqiang Mai1, Guotong Xie3,10,11, Xiang Guo1, Xing Lv1. 1. Department of Nasopharyngeal Carcinoma, Sun Yat-sen University Cancer Center, Guangzhou, Guangdong, China. 2. Department of Artificial Intelligence Laboratory, Sun Yat-sen University Cancer Center, Guangzhou, Guangdong, China. 3. Ping An Healthcare Technology, Beijing, China. 4. Department of Radiotherapy, Sun Yat-sen University Cancer Center, Guangzhou, Guangdong, China. 5. Department of Radiology, Sun Yat-sen University Cancer Center, Guangzhou, Guangdong, China. 6. Department of Information, The Affiliated Nanfang Hospital of Southern Medical University, Guangzhou, Guangdong, China. 7. Department of Radiology, The People's Hospital of Dongguan, Dongguan, Guangdong, China. 8. Department of Radiotherapy, The Affiliated Cancer Hospital of Guangzhou Medical University, Guangzhou, Guangdong, China. 9. Department of Radiology, The First People's Hospital of Foshan, Foshan, Guangdong, China. 10. Ping An Health Cloud Company Limited, Beijing, China. 11. Ping An International Smart City Technology Co., Ltd., Beijing, China.
Abstract
BACKGROUND: Images from magnetic resonance imaging (MRI) are crucial unstructured data for prognostic evaluation in nasopharyngeal carcinoma (NPC). We developed and validated a prognostic system based on the MRI features and clinical data of locoregionally advanced NPC (LA-NPC) patients to distinguish low-risk patients with LA-NPC for whom concurrent chemoradiotherapy (CCRT) is sufficient. METHODS: This multicenter, retrospective study included 3444 patients with LA-NPC from January 1, 2010, to January 31, 2017. A 3-dimensional convolutional neural network was used to learn the image features from pretreatment MRI images. An eXtreme Gradient Boosting model was trained with the MRI features and clinical data to assign an overall score to each patient. Comprehensive evaluations were implemented to assess the performance of the predictive system. We applied the overall score to distinguish high-risk patients from low-risk patients. The clinical benefit of induction chemotherapy (IC) was analyzed in each risk group by survival curves. RESULTS: We constructed a prognostic system displaying a concordance index of 0.776 (95% confidence interval [CI] = 0.746 to 0.806) for the internal validation cohort and 0.757 (95% CI = 0.695 to 0.819), 0.719 (95% CI = 0.650 to 0.789), and 0.746 (95% CI = 0.699 to 0.793) for the 3 external validation cohorts, which presented a statistically significant improvement compared with the conventional TNM staging system. In the high-risk group, patients who received induction chemotherapy plus CCRT had better outcomes than patients who received CCRT alone, whereas there was no statistically significant difference in the low-risk group. CONCLUSIONS: The proposed framework can capture more complex and heterogeneous information to predict the prognosis of patients with LA-NPC and potentially contribute to clinical decision making.
BACKGROUND: Images from magnetic resonance imaging (MRI) are crucial unstructured data for prognostic evaluation in nasopharyngeal carcinoma (NPC). We developed and validated a prognostic system based on the MRI features and clinical data of locoregionally advanced NPC (LA-NPC) patients to distinguish low-risk patients with LA-NPC for whom concurrent chemoradiotherapy (CCRT) is sufficient. METHODS: This multicenter, retrospective study included 3444 patients with LA-NPC from January 1, 2010, to January 31, 2017. A 3-dimensional convolutional neural network was used to learn the image features from pretreatment MRI images. An eXtreme Gradient Boosting model was trained with the MRI features and clinical data to assign an overall score to each patient. Comprehensive evaluations were implemented to assess the performance of the predictive system. We applied the overall score to distinguish high-risk patients from low-risk patients. The clinical benefit of induction chemotherapy (IC) was analyzed in each risk group by survival curves. RESULTS: We constructed a prognostic system displaying a concordance index of 0.776 (95% confidence interval [CI] = 0.746 to 0.806) for the internal validation cohort and 0.757 (95% CI = 0.695 to 0.819), 0.719 (95% CI = 0.650 to 0.789), and 0.746 (95% CI = 0.699 to 0.793) for the 3 external validation cohorts, which presented a statistically significant improvement compared with the conventional TNM staging system. In the high-risk group, patients who received induction chemotherapy plus CCRT had better outcomes than patients who received CCRT alone, whereas there was no statistically significant difference in the low-risk group. CONCLUSIONS: The proposed framework can capture more complex and heterogeneous information to predict the prognosis of patients with LA-NPC and potentially contribute to clinical decision making.
Authors: Jian Ji Pan; Wai Tong Ng; Jing Feng Zong; Sarah W M Lee; Horace C W Choi; Lucy L K Chan; Shao Jun Lin; Qiao Juan Guo; Henry C K Sze; Yun Bin Chen; You Ping Xiao; Wai Kuen Kan; Brian O'Sullivan; Wei Xu; Quynh Thu Le; Christine M Glastonbury; A Dimitrios Colevas; Randal S Weber; William Lydiatt; Jatin P Shah; Anne W M Lee Journal: Cancer Date: 2016-07-19 Impact factor: 6.860