The apparent diffusion coefficient (ADC) derived from Diffusion-weighted imaging (DWI) has been widely used for lesion characterization. However, ADC is calculated from image intensities with different b values, which is a low-level image feature that might be insufficient to represent heterogeneous of neoplasm. Furthermore, ADC measurements are subject to the influence of motion and image artifacts. The deep feature based on the emerging deep learning technique has been considered to be superior to traditional low-level features. The purpose of this study is to effectively characterize the malignancy of HCC based on deep feature derived from DWI data using deep learning.