Study of Texture Segmentation and Classification for Grading Small Hepatocellular Carcinoma Based on CT Images

To grade Small Hepatocellular CarCinoma (SHCC) using texture analysis of CT images, we retrospectively analysed 68 cases of Grade II (medium-differentiation) and 37 cases of Grades III and IV (high-differentiation). The grading scheme follows 4 stages: (1) training a Super Resolution Generative Adversarial Network (SRGAN) migration learning model on the Lung Nodule Analysis 2016 Dataset, and employing this model to reconstruct Super Resolution Images of the SHCC Dataset (SR-SHCC) images; (2) designing a texture clustering method based on Gray-Level Co-occurrence Matrix (GLCM) to segment tumour regions, which are Regions Of Interest (ROIs), from the original and SR-SHCC images, respectively; (3) extracting texture features on the ROIs; (4) performing statistical analysis and classifications. The segmentation achieved accuracies of 0.9049 and 0.8590 in the original SHCC images and the SR-SHCC images, respectively. The classification achived an accuracy of 0.838 and an Area Under the ROC Curve (AUC) of 0.84. The grading scheme can effectively reduce poor impacts on the texture analysis of SHCC ROIs. It may play a guiding role for physicians in early diagnoses of medium-differentiation and high-differentiation in SHCC.

Automated summary

This study explored the grading of Small Hepatocellular CarCinoma using texture analysis of CT images. Through training models, designing texture clustering methods, extracting features, and conducting statistical analysis and classification, the research successfully achieved the grading and diagnosis of SHCC. The results showed that the grading scheme effectively reduced errors in texture analysis and may assist physicians in early diagnosis in clinical practice.