Machine learning models for predicting microvascular invasion in hepatocellular carcinoma with three-dimensional whole-lesion 18F-FDG PET radiomics.

Key Points

• The study aims to predict microvascular invasion in hepatocellular carcinoma using machine learning models and radiomics data from PET imaging.
• Developed machine learning models utilizing three-dimensional whole-lesion radiomics features.
• Evaluated the performance of these models in predicting microvascular invasion.
• The logistic regression model exhibited the best performance among the tested models.
• The model shows potential for noninvasive preoperative assessment of microvascular invasion.