Kang Wang1, Yanjun Xiang1, Jiangpeng Yan2,3, Yuyao Zhu4, Hanbo Chen2, Jianhua Yao5, Shuqun Cheng6,7,8, Hongming Yu1, Yuqiang Cheng1, Xiu Li3, Wei Dong4, Yan Ji2, Jingjing Li9, Dong Xie9, Wan Yee Lau1,10. 1. Department of Hepatic Surgery VI, Eastern Hepatobiliary Surgery Hospital, Shanghai, China. 2. Tencent AI Lab, Building A 12#, Shenzhenwan Science and Technology Ecological Garden, Nanshan District Shenzhen, Guangdong, China. 3. Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China. 4. Department of Pathology, Eastern Hepatobiliary Surgery Hospital, Shanghai, China. 5. Tencent AI Lab, Building A 12#, Shenzhenwan Science and Technology Ecological Garden, Nanshan District Shenzhen, Guangdong, China. jianhuayao@tencent.com. 6. Department of Hepatic Surgery VI, Eastern Hepatobiliary Surgery Hospital, Shanghai, China. chengshuqun@aliyun.com. 7. Department of Cell Biology, College of Medicine, Jiaxing University, Jiaxing, China. chengshuqun@aliyun.com. 8. School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai, China. chengshuqun@aliyun.com. 9. CAS Key Laboratory of Nutrition, Metabolism and Food Safety, Shanghai Institute of Nutrition and Health, University of Chinese Academy of Sciences, Chinese Academy of Sciences, Shanghai, China. 10. Faculty of Medicine, The Chinese University of Hong Kong, Hong Kong, China.
Abstract
INTRODUCTION: Microvascular invasion (MVI) is a known risk factor for prognosis after R0 liver resection for hepatocellular carcinoma (HCC). The aim of this study was to develop a deep learning prognostic prediction model by incorporating a new factor of MVI area to the other independent risk factors. METHODS: Consecutive patients with HCC who underwent R0 liver resection from January to December 2016 at the Eastern Hepatobiliary Surgery Hospital were included in this retrospective study. For patients with MVI detected on resected specimens, they were divided into two groups according to the size of the maximal MVI area: the small-MVI group and the large-MVI group. RESULTS: Of 193 patients who had MVI in the 337 HCC patients, 130 patients formed the training cohort and 63 patients formed the validation cohort. The large-MVI group of patients had worse overall survival (OS) when compared with the small-MVI group (p = 0.009). A deep learning model was developed based on the following independent risk factors found in this study: MVI stage, maximal MVI area, presence/absence of cirrhosis, and maximal tumor diameter. The areas under the receiver operating characteristic of the deep learning model for the 1-, 3-, and 5-year predictions of OS were 80.65, 74.04, and 79.44, respectively, which outperformed the traditional COX proportional hazards model. CONCLUSION: The deep learning model, by incorporating the maximal MVI area as an additional prognostic factor to the other previously known independent risk factors, predicted more accurately postoperative long-term OS for HCC patients with MVI after R0 liver resection.
INTRODUCTION: Microvascular invasion (MVI) is a known risk factor for prognosis after R0 liver resection for hepatocellular carcinoma (HCC). The aim of this study was to develop a deep learning prognostic prediction model by incorporating a new factor of MVI area to the other independent risk factors. METHODS: Consecutive patients with HCC who underwent R0 liver resection from January to December 2016 at the Eastern Hepatobiliary Surgery Hospital were included in this retrospective study. For patients with MVI detected on resected specimens, they were divided into two groups according to the size of the maximal MVI area: the small-MVI group and the large-MVI group. RESULTS: Of 193 patients who had MVI in the 337 HCC patients, 130 patients formed the training cohort and 63 patients formed the validation cohort. The large-MVI group of patients had worse overall survival (OS) when compared with the small-MVI group (p = 0.009). A deep learning model was developed based on the following independent risk factors found in this study: MVI stage, maximal MVI area, presence/absence of cirrhosis, and maximal tumor diameter. The areas under the receiver operating characteristic of the deep learning model for the 1-, 3-, and 5-year predictions of OS were 80.65, 74.04, and 79.44, respectively, which outperformed the traditional COX proportional hazards model. CONCLUSION: The deep learning model, by incorporating the maximal MVI area as an additional prognostic factor to the other previously known independent risk factors, predicted more accurately postoperative long-term OS for HCC patients with MVI after R0 liver resection.
Authors: Jorge A Marrero; Laura M Kulik; Claude B Sirlin; Andrew X Zhu; Richard S Finn; Michael M Abecassis; Lewis R Roberts; Julie K Heimbach Journal: Hepatology Date: 2018-08 Impact factor: 17.425
Authors: Kheng-Choon Lim; Pierce Kah-Hoe Chow; John C Allen; Ghim-Song Chia; Miaoshan Lim; Peng-Chung Cheow; Alexander Y F Chung; London L P Ooi; Say-Beng Tan Journal: Ann Surg Date: 2011-07 Impact factor: 12.969
Authors: Sasan Roayaie; Iris N Blume; Swan N Thung; Maria Guido; Maria-Isabel Fiel; Spiros Hiotis; Daniel M Labow; Josep M Llovet; Myron E Schwartz Journal: Gastroenterology Date: 2009-06-12 Impact factor: 22.682