Table 4.

Radiomics for monitoring/follow-up

Author	Aims	Imaging modality	Number, (training (T) and validation (V) set, where available)	Conclusion
Reimer et al. [105]	To determine whether post-treatment MRI-based texture analysis of liver metastases may be suitable for predicting therapy response to transarterial radioembolization (TARE) during follow-up	CEMRI	37	The model indicates the potential of MRI-based texture analysis at arterial- and venous-phase MRI for the early prediction of progressive disease after TARE
Cozzi et al. [106]	To predict overall survival and local control	Non-contrast CT	138	Survival could be predicted using a radiomics signature made by a single shape-based feature
Kim et al. [107]	To predict survival (overall and progression-free survival)	CECT	88	A combination of clinical and radiomic features better predicted survival
Mokrane et al. [108]	To enhance clinicians’ decision-making by diagnosing HCC in cirrhotic patients with indeterminate liver nodules using quantitative imaging features	CECT	178 T: 142 V: 36	Radiomics can be used to non-invasively diagnose HCC in cirrhotic patients with indeterminate liver nodules, which could be used to optimize patient management
Donghui et al. [13]	To identify aggressive behaviour and predict recurrence of HCC after liver transplantation (LT)	CECT	133 T: 93 V: 40	Radiomics signature extracted from CT images may be a potential imaging biomarker for liver cancer invasion and enable accurate prediction of HCC recurrence after LT
Zhao et al. [109]	To investigate the combined predictive performance of qualitative and quantitative MRI features and prognostic immunohistochemical markers for the ER of intrahepatic mass-forming cholangiocarcinoma (IMCC)	CEMRI	47	The combined model was the superior predictive model of ER

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, MRI magnetic resonance imaging, MVI microvascular invasion