Preoperative prediction for pathological grade of hepatocellular carcinoma via machine learning–based radiomics

The purpose of this single-center retrospective study was to investigate the effectiveness of contrast-enhanced computed tomography (CECT)-based radiomic signatures for the preoperative prediction of pathological grades of hepatocellular carcinoma (HCC) via machine learning. The authors found that the radiomics signatures could non-invasively explore the underlying association between CECT images and pathological grades of HCC.

Key points

• The radiomics signatures may non-invasively explore the underlying association between CECT images and pathological grades of HCC via machine learning.
• The radiomics signatures of CECT images may enhance the prediction performance of pathological grading of HCC, and further validation is required.
• The features extracted from arterial phase CECT images may be more reliable than venous phase CECT images for predicting pathological grades of HCC.

Article: Preoperative prediction for pathological grade of hepatocellular carcinoma via machine learning–based radiomics

Authors: Bing Mao, Lianzhong Zhang, Peigang Ning, Feng Ding, Fatian Wu, Gary Lu, Yayuan Geng & Jingdong Ma