首页|Chongqing University Cancer Hospital Reports Findings in Gastric Cancer (Preoper ative Prediction of Her-2 and Ki-67 Status in Gastric Cancer Using 18F-FDG PET/C T Radiomics Features of Visceral Adipose Tissue)
Chongqing University Cancer Hospital Reports Findings in Gastric Cancer (Preoper ative Prediction of Her-2 and Ki-67 Status in Gastric Cancer Using 18F-FDG PET/C T Radiomics Features of Visceral Adipose Tissue)
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 - Gastric Can cer is the subject of a report. According to news reporting from Chongqing, Peop le’s Republic of China, by NewsRx journalists, research stated, “Immunohistochem istry (IHC) is the main method to detect human epidermal growth factor receptor 2 (Her-2) and Ki-67 expression levels. However, IHC is invasive and cannot refle ct their expression status in real-time.” The news correspondents obtained a quote from the research from Chongqing Univer sity Cancer Hospital, “This study aimed to build radiomics models based on visce ral adipose tissue (VAT)’s Ffluorodeoxyglucose (F-FDG) positron emission tomogr aphy/computed tomography (PET/CT) imaging, and to evaluate the relationship betw een radiomics features of VAT and positive expression of Her-2 and Ki-67 in gast ric cancer (GC). Ninety patients with GC were enrolled in this study. F-FDG PET/ CT radiomics features were calculated using the PyRadiomics package. Two methods were employed to reduce radiomics features. The machine learning models, logist ic regression (LR), and support vector machine (SVM), were constructed and estim ated by the receiver operator characteristic (ROC) curve. The correlation of out standing features with Ki-67 and Her-2 expression status was evaluated. For the Ki-67 set, the area under of the receiver operator characteristic curve (AUC) an d accuracy were 0.86 and 0.79 for the LR model and 0.83 and 0.69 for the SVM mod el. For the Her-2 set, the AUC and accuracy were 0.84 and 0.86 for the LR model and 0.65 and 0.85 for the SVM model. The LR model for Ki-67 exhibited outstandin g prediction performance. Three wavelet transform features were correlated with Her-2 expression status ( all <0.001), and one wavelet tra nsform feature was correlated with the expression status of Ki-67 ( = 0.042). F- FDG PET/CT-based radiomics models of VAT demonstrate good performance in predict ing Her-2 and Ki-67 expression status in patients with GC.”
ChongqingPeople’s Republic of ChinaA siaCancerGastric CancerGastroenterologyHealth and MedicineMachine Lear ningOncologySupport Vector Machines
NETL
NSTL
