摘要
一位新闻记者-机器人与机器学习的工作人员新闻编辑每日新闻-肿瘤学的新研究-神经内分泌癌是一篇报道的主题。本研究旨在探讨基于多参数MRI的机器学习和放射组学在术前预测垂体神经内分泌瘤(PitNETs)组织学亚型的可行性，并对201年1月6日至2022年5月4家医疗中心收治的垂体神经内分泌瘤患者进行回顾性研究。我们的新闻记者引用了山东省医院的一篇研究报道:“利用cfVBNet网络自动分割PitNET多参数MRI,从MRI中提取放射组学特征,计算每个患者的放射组学score(Radiomics score),以预测组织学亚型。”采用基于放射组学特征的高斯过程(GP)机器学习分类器,构建了多分类(六类组织学亚型)和Bina Ry分类(PRL vs non-PRL)GP模型。应用多因素Logistic回归分析建立了一个结合临床因素和RAD评分的临床-R放射组学列线图，用受试者操作特征(ROC)曲线评价模型的性能，PitNET Aut Osegments模型最终在1206例患者(平均年龄49.3±SD岁，女性52%)中获得了0.888的平均Dice相似系数。T2WI的GP在ROC曲线(AUC)下的面积最大，训练集、验证集和外部测试集分别为0.791、0.801和0.711，在二元分类模型中，T2WI结合CE T1WI的GP表现良好，训练集、验证集和外部测试集的AUC分别为0.936、0.882和0.791."radscore和Hardy分级是PRL表达的p指标."
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Oncology - Neuroendocr ine Cancer is the subject of a report. According to news originating from Jinan, People's Republic of China, by NewsRx correspondents, research stated, "This st udy aims to investigate the feasibility of preoperatively predicting histologica l subtypes of pituitary neuroendocrine tumors (PitNETs) using machine learning a nd radiomics based on multiparameter MRI. Patients with PitNETs from January 201 6 to May 2022 were retrospectively enrolled from four medical centers." Our news journalists obtained a quote from the research from Shandong Provincial Hospital, "A cfVBNet network was used to automatically segment PitNET multipar ameter MRI. Radiomics features were extracted from the MRI, and the radiomics sc ore (Radscore) of each patient was calculated. To predict histological subtypes, the Gaussian process (GP) machine learning classifier based on radiomics featur es was performed. Multi-classification (six-class histological subtype) and bina ry classification (PRL vs. non-PRL) GP model was constructed. Then, a clinical-r adiomics nomogram combining clinical factors and Radscores was constructed using the multivariate logistic regression analysis. The performance of the models wa s evaluated using receiver operating characteristic (ROC) curves. The PitNET aut osegmentation model eventually achieved the mean Dice similarity coefficient of 0.888 in 1206 patients (mean age 49.3 ± SD years, 52% female). In the multi-classification model, the GP of T2WI got the best area under the ROC curve (AUC), with 0.791, 0.801, and 0.711 in the training, validation, and exter nal testing set, respectively. In the binary classification model, the GP of T2W I combined with CE T1WI demonstrated good performance, with AUC of 0.936, 0.882, and 0.791 in training, validation, and external testing sets, respectively. In the clinical-radiomics nomogram, Radscores and Hardy' grade were identified as p redictors for PRL expression."
NETL
NSTL