Yi-Quan Jiang1, Su-E Cao2, Shilei Cao3, Jian-Ning Chen4, Guo-Ying Wang1, Wen-Qi Shi2, Yi-Nan Deng1, Na Cheng4, Kai Ma3, Kai-Ning Zeng1, Xi-Jing Yan1, Hao-Zhen Yang5, Wen-Jing Huan5, Wei-Min Tang5, Yefeng Zheng3, Chun-Kui Shao4, Jin Wang2, Yang Yang6, Gui-Hua Chen7,8. 1. Department of Hepatic Surgery and Liver Transplantation Center, The Third Affiliated Hospital, Organ Transplantation Institute, Sun Yat-Sen University, 600 Tianhe Road, Guangzhou, 510630, Guangdong, China. 2. Department of Radiology, The Third Affiliated Hospital, Sun Yat-Sen University, 600 Tianhe Road, Guangzhou, 510630, China. 3. Tencent Youtu Lab, Malata Building, Kejizhongyi Road, Nanshan District, Shenzhen, 518075, China. 4. Department of Pathology, The Third Affiliated Hospital, Sun Yat-Sen University, 600 Tianhe Road, Guangzhou, 510630, China. 5. Tencent Healthcare, Tengxun Building, Kejizhongyi Road, Nanshan District, Shenzhen, 518075, China. 6. Department of Hepatic Surgery and Liver Transplantation Center, The Third Affiliated Hospital, Organ Transplantation Institute, Sun Yat-Sen University, 600 Tianhe Road, Guangzhou, 510630, Guangdong, China. yysysu@163.com. 7. Organ Transplantation Research Center of Guangdong Province, Guangzhou, 510630, Guangdong, China. chghua@mail.sysu.edu.cn. 8. Guangdong Key Laboratory of Liver Disease Research, The Third Affiliated Hospital, Sun Yat-Sen University, 600 Tianhe Road, Guangzhou, 510630, Guangdong, China. chghua@mail.sysu.edu.cn.
Abstract
PURPOSE: Microvascular invasion (MVI) is a valuable predictor of survival in hepatocellular carcinoma (HCC) patients. This study developed predictive models using eXtreme Gradient Boosting (XGBoost) and deep learning based on CT images to predict MVI preoperatively. METHODS: In total, 405 patients were included. A total of 7302 radiomic features and 17 radiological features were extracted by a radiomics feature extraction package and radiologists, respectively. We developed a XGBoost model based on radiomics features, radiological features and clinical variables and a three-dimensional convolutional neural network (3D-CNN) to predict MVI status. Next, we compared the efficacy of the two models. RESULTS: Of the 405 patients, 220 (54.3%) were MVI positive, and 185 (45.7%) were MVI negative. The areas under the receiver operating characteristic curves (AUROCs) of the Radiomics-Radiological-Clinical (RRC) Model and 3D-CNN Model in the training set were 0.952 (95% confidence interval (CI) 0.923-0.973) and 0.980 (95% CI 0.959-0.993), respectively (p = 0.14). The AUROCs of the RRC Model and 3D-CNN Model in the validation set were 0.887 (95% CI 0.797-0.947) and 0.906 (95% CI 0.821-0.960), respectively (p = 0.83). Based on the MVI status predicted by the RRC and 3D-CNN Models, the mean recurrence-free survival (RFS) was significantly better in the predicted MVI-negative group than that in the predicted MVI-positive group (RRC Model: 69.95 vs. 24.80 months, p < 0.001; 3D-CNN Model: 64.06 vs. 31.05 months, p = 0.027). CONCLUSION: The RRC Model and 3D-CNN models showed considerable efficacy in identifying MVI preoperatively. These machine learning models may facilitate decision-making in HCC treatment but requires further validation.
PURPOSE: Microvascular invasion (MVI) is a valuable predictor of survival in hepatocellular carcinoma (HCC) patients. This study developed predictive models using eXtreme Gradient Boosting (XGBoost) and deep learning based on CT images to predict MVI preoperatively. METHODS: In total, 405 patients were included. A total of 7302 radiomic features and 17 radiological features were extracted by a radiomics feature extraction package and radiologists, respectively. We developed a XGBoost model based on radiomics features, radiological features and clinical variables and a three-dimensional convolutional neural network (3D-CNN) to predict MVI status. Next, we compared the efficacy of the two models. RESULTS: Of the 405 patients, 220 (54.3%) were MVI positive, and 185 (45.7%) were MVI negative. The areas under the receiver operating characteristic curves (AUROCs) of the Radiomics-Radiological-Clinical (RRC) Model and 3D-CNN Model in the training set were 0.952 (95% confidence interval (CI) 0.923-0.973) and 0.980 (95% CI 0.959-0.993), respectively (p = 0.14). The AUROCs of the RRC Model and 3D-CNN Model in the validation set were 0.887 (95% CI 0.797-0.947) and 0.906 (95% CI 0.821-0.960), respectively (p = 0.83). Based on the MVI status predicted by the RRC and 3D-CNN Models, the mean recurrence-free survival (RFS) was significantly better in the predicted MVI-negative group than that in the predicted MVI-positive group (RRC Model: 69.95 vs. 24.80 months, p < 0.001; 3D-CNN Model: 64.06 vs. 31.05 months, p = 0.027). CONCLUSION: The RRC Model and 3D-CNN models showed considerable efficacy in identifying MVI preoperatively. These machine learning models may facilitate decision-making in HCC treatment but requires further validation.
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: Wenya Linda Bi; Ahmed Hosny; Matthew B Schabath; Maryellen L Giger; Nicolai J Birkbak; Alireza Mehrtash; Tavis Allison; Omar Arnaout; Christopher Abbosh; Ian F Dunn; Raymond H Mak; Rulla M Tamimi; Clare M Tempany; Charles Swanton; Udo Hoffmann; Lawrence H Schwartz; Robert J Gillies; Raymond Y Huang; Hugo J W L Aerts Journal: CA Cancer J Clin Date: 2019-02-05 Impact factor: 508.702