Machine Learning: Applications and Advanced Progresses of Radiomics in Endocrine Neoplasms

Table 1

Different clinical applications of radiomic models (features) in PAs.

References	Case numbers	Radiomic method	Results
[20]	133	MRI	Radiomic features had promising and practical values in distinguishing pituitary adenoma from Rathke cleft cyst
[21]	235	MRI	MRI-based radiomic model could be used to predict immunohistochemical results of pituitary adenoma preoperatively
[22]	112	MRI	MRI-based radiomic features had a great potential to differentiate between nonfunctional subtypes and other subtypes pituitary adenomas preoperatively
[24]	89	MRI	Radiomics could indirectly predict tumor aggressiveness by predicting high proliferative index Ki-67 in pituitary macroadenomas
[25]	194	MRI	MRI-based radiomic method was proved to be an effective method for predicting the cavernous sinus invasion preoperatively
[28]	163	MRI	Radiomics models may help neurosurgeons predict the treatment response preoperatively and make personalized treatment strategies
[26]	400	MRI	The result indicated that early postoperative outcomes of PAs could be assessed by a radiomic approach