The accurate non-invasive staging of liver fibrosis using deep learning radiomics based on transfer learning of shear wave elastography

摘要

Background: We developed the deep learning Radiomics of elastography (DLRE) which adopted Convolutional NeuralNetwork (CNN) based on transfer learning as a noninvasive method to assess liver fibrosis stages, which is essential forprognosis, surveillance of chronic hepatitis B (CHB) patients. Methods: 297 patients were prospectively enrolled from 4hospitals, and finally 1485 images were included into analysis randomly. DLRE adopted the Convolutional NeuralNetwork (CNN) based on transfer learning, one of the deep learning radiomic techniques, for the automatic analysis of2D-SWE images. This study was conducted to assess the accuracy of DLRE in comparison with 2D-SWE, transientelastography (TE), transaminase-to-platelet ratio index (APRI), and fibrosis index based on the four factors (FIB-4), byusing liver biopsy as the gold standard. Results: AUCs of DLRE were both 0.98 for cirrhosis (95% confidence interval[CI]: 0.95-0.99) and advanced fibrosis (95% CI: 0.94-0.99), which were significantly better than other methods, as wellas 0.76 (95% CI: 0.72-0.81) for significance fibrosis (significantly better than APRI and FIB-4). Conclusions: DLREshows the best overall performance in predicting liver fibrosis stages comparing with 2D-SWE, TE, and serologicalexaminations.