首页|Jiangxi Cancer Hospital Reports Findings in Liver Cancer (MRIbased clinical-rad iomics nomogram model for predicting microvascular invasion in hepatocellular ca rcinoma)
Jiangxi Cancer Hospital Reports Findings in Liver Cancer (MRIbased clinical-rad iomics nomogram model for predicting microvascular invasion in hepatocellular ca rcinoma)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Oncology - Liver Cance r is the subject of a report. According to news reporting originating in Nanchan g, People’s Republic of China, by NewsRx journalists, research stated, “Preopera tive microvascular invasion (MVI) of liver cancer is an effective method to redu ce the recurrence rate of liver cancer. Hepatectomy with extended resection and additional adjuvant or targeted therapy can significantly improve the survival r ate of MVI+ patients by eradicating micrometastasis.” The news reporters obtained a quote from the research from Jiangxi Cancer Hospit al, “Preoperative prediction of MVI status is of great clinical significance for surgical decision-making and the selection of other adjuvant therapy strategies to improve the prognosis of patients. Established a radiomics machine learning model based on multimodal MRI and clinical data, and analyzed the preoperative p rediction value of this model for microvascular invasion (MVI) of hepatocellular carcinoma (HCC). The preoperative liver MRI data and clinical information of 13 0 HCC patients who were pathologically confirmed to be pathologically confirmed were retrospectively studied. These patients were divided into MVI-positive grou p (MVI+) and MVI-negative group (MVI-) based on postoperative pathology. After a series of dimensionality reduction analysis, six radiomic features were finally selected. Then, linear support vector machine (linear SVM), support vector mach ine with rbf kernel function (rbf-SVM), logistic regression (LR), Random forest (RF) and XGBoost (XGB) algorithms were used to establish the MVI prediction mode l for preoperative HCC patients. Then, rbf-SVM with the best predictive performa nce was selected to construct the radiomics score (R-score). Finally, we combine d R-score and clinical-pathology-image independent predictors to establish a com bined nomogram model and corresponding individual models. The predictive perform ance of individual models and combined nomogram was evaluated and compared by re ceiver operating characteristic curve (ROC). Alpha-fetoprotein concentration, pe ritumor enhancement, maximum tumor diameter, smooth tumor margins, tumor growth pattern, presence of intratumor hemorrhage, and RVI were independent predictors of MVI. Compared with individual models, the final combined nomogram model (AUC: 0.968, 95% CI: 0.920-1.000) constructed by radiometry score (R-sc ore) combined with clinicopathological parameters and apparent imaging features showed the optimal predictive performance.”
NanchangPeople’s Republic of ChinaAs iaCancerCarcinomasEmerging TechnologiesHealth and MedicineLiver CancerMachine LearningOncologySupport Vector MachinesVector Machines
NETL
NSTL
