首页|Division of Radiology Reports Findings in Machine Learning (Machine learning and radiomics analysis by computed tomography in colorectal liver metastases patien ts for RAS mutational status prediction)
Division of Radiology Reports Findings in Machine Learning (Machine learning and radiomics analysis by computed tomography in colorectal liver metastases patien ts for RAS mutational status prediction)
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 Machine Learning is th e subject of a report. According to news reporting originating in Naples, Italy, by NewsRx journalists, research stated, “To assess the efficacy of machine lear ning and radiomics analysis by computed tomography (CT) in presurgical setting, to predict RAS mutational status in colorectal liver metastases. Patient selecti on in a retrospective study was carried out from January 2018 to May 2021 consid ering the following inclusion criteria: patients subjected to surgical resection for liver metastases; proven pathological liver metastases; patients subjected to enhanced CT examination in the presurgical setting with a good quality of ima ges; and RAS assessment as standard reference.” The news reporters obtained a quote from the research from the Division of Radio logy, “A total of 851 radiomics features were extracted using the PyRadiomics Py thon package from the Slicer 3D image computing platform after slice-by-slice se gmentation on CT portal phase by two expert radiologists of each individual live r metastasis performed first independently by the individual reader and then in consensus. Balancing technique was performed, and inter- and intraclass correlat ion coefficients were calculated to assess the between-observer and within-obser ver reproducibility of features. Receiver operating characteristics (ROC) analys is with the calculation of area under the ROC curve (AUC), sensitivity (SENS), s pecificity (SPEC), positive predictive value (PPV), negative predictive value (N PV) and accuracy (ACC) were assessed for each parameter. Linear and non-logistic regression model (LRM and NLRM) and different machine learning-based classifier s were considered. Moreover, features selection was performed before and after a normalized procedure using two different methods (3-sigma and z-score). Seventy -seven liver metastases in 28 patients with a mean age of 60 years (range 40-80 years) were analyzed. The best predictors, at univariate analysis for both norma lized procedures, were original_shape_Maximum2DDiamete r and wavelet_HLL_glcm_InverseVariance th at reached an accuracy of 80%, an AUC 0.75, a sensitivity 80% and a specificity 70% (p value <<0.01). However, a multivariate analysis significantly increased the accuracy in RAS prediction when a linear regression model (LRM) was used. The best performa nce was obtained using a LRM combining linearly 12 robust features after a z-sco re normalization procedure: AUC of 0.953, accuracy 98%, sensitivity 96%, specificity of 100%, PPV 100% and NPV 96% (p value <<0.01 ). No statistically significant increase was obtained considering the tested mac hine learning both without normalization and with normalization methods.”
NaplesItalyEuropeColorectal Resear chComputed TomographyCyborgsEmerging TechnologiesGastroenterologyHealt h and MedicineImaging TechnologyMachine LearningTechnology
NETL
NSTL
