Differential Diagnosis of Intrahepatic Mass-forming Cholangiocarcinoma and Solitary Hypovascular Hepatic Metastasis Using Whole-Tumor Texture Features Based on Apparent Diffusion Coefficient and Fractional Anisotropy Signal Intensity Maps

This work aimed for ADC and FA texture features based strategy to identify intrahepatic mass-forming cholangiocarcinoma (IMCC) and solitary hypovascular hepatic metastasis (SHHM) which may represent a diagnostic challenge due to many overlapping MRI features. The results showed that ADC and FA texture features can differentiate IMCC and SHHM. The Grey Level Non-uniformity (GLN) achieved the best result (AUC: 0.820; sensitivity: 79.2%; specificity: 86.2%) on ADC signal intensity map, forming a valuable strategy for clinical practice.