Background: The purpose of this study is to explore the potential of phase contrast\nimaging to detect fibrotic progress in its early stage; to investigate the feasibility of texture\nfeatures for quantified diagnosis of liver fibrosis; and to evaluate the performance\nof back propagation (BP) neural net classifier for characterization and classification of\nliver fibrosis.\nMethods: Fibrous mouse liver samples were imaged by X-ray phase contrast imaging,\nnine texture measures based on gray-level co-occurrence matrix were calculated\nand the feasibility of texture features in the characterization and discrimination of liver\nfibrosis at early stages was investigated. Furthermore, 36 or 18 features were applied to\nthe input of BP classifier; the classification performance was evaluated using receiver\noperating characteristic curve.\nResults: The phase contrast images displayed a vary degree of texture pattern from\nnormal to severe fibrosis stages. The BP classifier could distinguish liver fibrosis among\nnormal, mild, moderate and severe stages; the average accuracy was 95.1% for 36\nfeatures, and 91.1% for 18 features.\nConclusion: The study shows that early stages of liver fibrosis can be discriminated by\nthe morphological features on the phase contrast images. BP network model based on\ncombination of texture features is demonstrated effective for staging liver fibrosis.
Loading....