首页|Capital Medical University Reports Findings in Pituitary Adenoma (Concomitant Pr ediction of the Ki67 and PIT-1 Expression in Pituitary Adenoma Using Different R adiomics Models)
Capital Medical University Reports Findings in Pituitary Adenoma (Concomitant Pr ediction of the Ki67 and PIT-1 Expression in Pituitary Adenoma Using Different R adiomics Models)
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 - Pituitary A denoma is the subject of a report. According to news originating from Beijing, P eople's Republic of China, by NewsRx correspondents, research stated, "To preope ratively predict the high expression of Ki67 and positive pituitary transcriptio n factor 1 (PIT-1) simultaneously in pituitary adenoma (PA) using three differen t radiomics models. A total of 247 patients with PA (training set: n = 198; test set: n = 49) were included in this retrospective study." Our news journalists obtained a quote from the research from Capital Medical Uni versity, "The imaging features were extracted from preoperative contrast-enhance d T1WI (T1CE), T1-weighted imaging (T1WI), and T2-weighted imaging (T2WI). Featu re selection was performed using Spearman's rank correlation coefficient and lea st absolute shrinkage and selection operator (LASSO). The classic machine learni ng (CML), deep learning (DL), and deep learning radiomics (DLR) models were cons tructed using logistic regression (LR), support vector machine (SVM), and multi- layer perceptron (MLP) algorithms. The area under the receiver operating charact eristic (ROC) curve (AUC), sensitivity, specificity, accuracy, negative predicti ve value (NPV) and positive predictive value (PPV) were calculated for the train ing and test sets. In addition, combined with clinical characteristics, the best CML and the best DL models (SVM classifier), the DL radiomics nomogram (DLRN) w as constructed to aid clinical decision-making. Seven CML features, 96 DL featur es, and 107 DLR features were selected to construct CML, DL and DLR models. Comp ared to CML and DL model, the DLR model had the best performance. The AUC, sensi tivity, specificity, accuracy, NPV and PPV were 0.827, 0.792, 0.800, 0.796, 0.80 0 and 0.792 in the test set, respectively."
BeijingPeople's Republic of ChinaAsi aAdenomasHealth and MedicineOncologyPituitary Adenoma
NETL
NSTL
