An automatic method improving the reliability of shear wave elastography in the diagnosis of chronic liver disease

Abstract

Introduction Chronic Liver Disease (CLD) is considered as one of the leading causes of death worldwide today. Shear Wave Elastography (SWE) is a recently introduced technique which offers real-time elasticity imaging as well as stiffness quantification over a 2D region-of-interest (ROI). The major challenge for clinicians nowadays is the accurate and on-time estimation of liver fibrosis progress toward an efficient treatment to avoid unnecessary and costly invasive procedures. Purpose Classify CLD from SWE imaging by means of an optimized ROI selection procedure and a computer aided diagnosis system. Materials and methods The proposed algorithm employs a ROI selection technique (areas with no stiffness variation across-time) to quantify 32 SWE images (16 healthy and 16 with CLD). The selection procedure employs four SWE images from the same area of liver parenchyma having 5 s time distance acquired from each patient. Subsequently, the mean stiffness value of pixels having Stiffness Standard Deviation Results Highest classification accuracy from the SVM-model was 94.3% with sensitivity and specificity values of 93.8% and 94.6%, respectively. Best feature combination for the SVM model comprised the Standard Deviation, Sum-Variance and Contrast features. Conclusion A new automatic SWE reliability algorithm for CLD diagnosis has been developed that could prove to be of value to physicians improving the diagnostic accuracy of CLD. Disclosure No disclosure.