首页|Quzhou Affiliated Hospital of Wenzhou Medical University Reports Findings in Car cinomas (Development and validation of a CT based radiomics nomogram for preoper ative prediction of ISUP/WHO grading in renal clear cell carcinoma)
Quzhou Affiliated Hospital of Wenzhou Medical University Reports Findings in Car cinomas (Development and validation of a CT based radiomics nomogram for preoper ative prediction of ISUP/WHO grading in renal clear cell carcinoma)
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-Carcinomas is the subject of a report. According to news reporting out of Quzhou, People's Republic of China, by NewsRx editors, research stated, "Nuclear grading of clear cell renal cell carcinoma (ccRCC) is crucial for its diagnosis and treatment. T o develop and validate a machine learning model for preoperative assessment of c cRCC nuclear grading using CT radiomics." Our news journalists obtained a quote from the research from the Quzhou Affiliat ed Hospital of Wenzhou Medical University, "This retrospective study analyzed 14 6 ccRCC patients who underwent surgery between June 2016 and January 2022 at two hospitals (the Quzhou Affiliated Hospital of Wenzhou Medical University with 11 7 cases and the Affiliated Cancer Hospital of University of Chinese Academy of S ciences with 29 cases). Radiomic features were extracted from preoperative abdom inal CT images. Features reduction and selection were carried out using intracla ss correlation efficient (ICCs), Spearman rank correlation coefficientsand and t he Least Absolute Shrinkage and Selection Operator (LASSO) regression method. Ra diomics and clinical models were developed utilizing Support Vector Machine (SVM ), Extremely Randomized Trees (Extra Trees), Light Gradient Boosting Machine (Li ghtGBM), Random Forest (RF) and K-Nearest Neighbors (KNN) algorithms. Subsequent ly, the radiomics nomogramwas developed incorporating independent clinical predi ctors and Rad_signature. Model performance was evaluated using the area under the curve (AUC), accuracy, sensitivity, and specificity, with decisio n curve analysis (DCA) assessing its clinical utility. We extracted 1834 radiomi c features from each CT sequence, with 1320 features passing through the ICCs sc reening process. 480 radiomics features were screened by Spearson correlation co efficient. Then, 15 radiomic features with non-zero coefficient values were dete rmined by Lasso dimensionality reduction technique. The five machine learning me thods effectively distinguished nuclear grades. The radiomics nomogram outperfor med clinical radiological models and radiomics feature models in predictive perf ormance, with an AUC of 0.936 (95% CI 0.885-0.986) for the trainin g set and 0.896 (95% CI 0.716-1.000) for the external verification set. DCA indicated potential clinical applicability of the nomogram. The radiom ics nomogram, developed by integrating clinically independent risk factors and a nd Rad_signature, demonstrated robust performance in preoperative c cRCC grading."
QuzhouPeople's Republic of ChinaAsiaCancerCarcinomasCyborgsEmerging TechnologiesHealth and MedicineHospi talsKidneyMachine LearningNephrologyOncologyRisk and Prevention
NETL
NSTL
