摘要
机器人与机器学习每日新闻-肿瘤学新研究-肝转移是一篇报道的主题。根据NewsRx记者从广州发回的新闻报道，研究表明：“肝脏是结直肠癌转移形成的最常见器官，结直肠癌肝脏转移的非侵入性预测(CRLM)可以更好地为临床医生提供决策依据。”我们的新闻编辑引用了消化道科的研究，“最后分析了180例CRLM病例的增强CT图像，用放射组学方法提取了包括形状、一阶、小波和纹理在内的放射组学特征。”采用弹性网(EN)和随机生存因子t(RSF)两种算法构建无病生存期(DFS)的放射组学特征,用Kaplan-Meier曲线和多因素Cox回归分析放射组学特征的预测潜力,选取11个放射组学特征作为EN算法的预测模型。EN算法的放射组学特征在训练数据集(L og-rank检验:P<0.01,危险比:1.45(1.07-1.96),P<0.01)和测试数据集(危险比:1.89(1.17-3.04)中成功分离出高危和低危病例的DFS。RSF算法在训练数据集（对数秩检验：P<0.001，危险系数：2.54（1.80-3.61），P<0.0001）和测试数据集（对数秩检验：P<0.05，危险比：1.84（1.15-2.96），P<0.05）中显示出对DFS更好的预测潜力。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News – New research on Oncology - Liver Metastasis is th e subject of a report. According to news reporting originating from Guangzhou, P eople’s Republic of China, by NewsRx correspondents, research stated, “The liver is the most common organ for the formation of colorectal cancer metastasis. Non -invasive prognostication of colorectal cancer liver metastasis (CRLM) may bette r inform clinicians for decision-making.” Our news editors obtained a quote from the research from the Department of Gastr oenterology, “Contrast-enhanced computed tomography images of 180 CRLM cases wer e included in the final analyses. Radiomics features, including shape, first-ord er, wavelet, and texture, were extracted with Pyradiomics, followed by feature e ngineering by penalized Cox regression. Radiomics signatures were constructed fo r disease-free survival (DFS) by both elastic net (EN) and random survival fores t (RSF) algorithms. The prognostic potential of the radiomics signatures was dem onstrated by Kaplan-Meier curves and multivariate Cox regression. 11 radiomics f eatures were selected for prognostic modelling for the EN algorithm, with 835 fe atures for the RSF algorithm. Survival heatmap indicates a negative correlation between EN or RSF risk scores and DFS. Radiomics signature by EN algorithm succe ssfully separates DFS of high-risk and lowrisk cases in the training dataset (l og-rank test: p<0.01, hazard ratio: 1.45 (1.07-1.96), p<0.01) and test dataset (hazard ratio: 1.89 (1.17-3.04), p<0.05). RSF algorithm shows a better prognostic implication potential for DFS in the training dataset (log-rank test: p<0.001, hazard rati o: 2.54 (1.80-3.61), p <0.0001) and test dataset (log-rank test: p<0.05, hazard ratio: 1.84 (1.15-2.96), p<0.05).”
NETL
NSTL