Table 1.

Radiomics for predictive use

Author	Aims	Imaging modality	Number (training and validation sets, where available)	Conclusion
Lewis et al. [9]	To distinguish hepatocellular carcinoma (HCC) from other primary liver cancers (intrahepatic cholangiocarcinoma [ICC] and combined HCC-ICC) through volumetric quantitative apparent diffusion coefficient (ADC) histogram parameters and LI-RADS categorization	MRI	63	Combination of quantitative ADC histogram parameters and LI-RADS categorization yielded the best prediction accuracy for distinction of HCC compared to ICC and combined HCC-ICC
Wu et al. [10]	To evaluate the feasibility of using radiomics with precontrast MRI for classifying HCC and hepatic haemangioma (HH)	MRI	369	Radiomics-based assessments could be used to distinguish between HCC and HH on precontrast images, thereby allowing noninvasively efficient identification and minimizing errors from visual inspection
Oyama et al. [11]	To evaluate the accuracy for classification of hepatic tumours	MRI	37 HCCs, 23 metastatic tumours, and 33 HHs	Using texture analysis or topological data analysis allows for classification of the three hepatic tumours with considerable accuracy
Wu et al. [12]	To predict histopathological grading for HCC cases	MRI	170	A computed radiomics signature itself or combined with clinical factors could help to classify the patients into high-grade or low-grade HCC

The columns Aims and Conclusion are directly based on the original work as cited in the column Author (wording partly adapted).

CECT contrast-enhanced computed tomography, ER early recurrence, HCC hepatocellular carcinoma, LI-RADS Liver Imaging Reporting and Data System, MRI magnetic resonance imaging, MVI microvascular invasion