期刊
JOURNAL OF CANCER RESEARCH AND CLINICAL ONCOLOGY
卷 147, 期 3, 页码 821-833出版社
SPRINGER
DOI: 10.1007/s00432-020-03366-9
关键词
Hepatocellular carcinoma; Micro-vascular invasion; Deep learning; Neural network models; Radiomics
类别
资金
- National Natural Science Foundation of China [81570593, 81770648]
- Natural Science Foundation of Guangdong Province [2015A030312013, 2015A030313038]
- Frontier and Key Technologies Innovation Foundation of Guangdong Province [2014B020228003]
- Science and Technology Program of Guangdong Province [2014B030301041, 2014A020211015]
- Major State Research Development Program [2017ZX10203205-006-001, 2017ZX10203205-001-003]
- Science and Technology Program of Guangzhou city [201604020001]
- Major Project of Cooperative Innovation of Health Care of Guangzhou City [158100076]
The study developed predictive models using XGBoost and deep learning to predict Microvascular invasion (MVI) status in hepatocellular carcinoma (HCC) patients. The models showed considerable efficacy in identifying MVI preoperatively, with the predicted MVI-negative group having significantly better recurrence-free survival compared to the predicted MVI-positive group.
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据