Radiomic data mining and machine learning on preoperative pituitary adenoma MRI

Pituitary adenomas are among the most frequent intracranial tumors, accounting for the majority of sellar/suprasellar masses in adults. MRI is the preferred imaging modality for detecting pituitary adenomas. Radiomics represents the conversion of digital medical images into mineable high-dimensional data. This process is motivated by the concept that biomedical images contain information that reflects underlying pathophysiology and that these relationships can be revealed via quantitative image analyses. The aim of this thesis is to apply machine learning algorithms on parameters obtained by texture analysis on MRI images in order to distinguish functional from non-functional pituitary macroadenomas, to predict their ki-67 proliferation index class, and to predict pituitary macroadenoma surgical consistency prior to an endoscopic endonasal procedure