MRI radiomics for the prediction of recurrence in patients with clinically non-functioning pituitary macroadenomas

Abstract

Twelve to 66% of patients with clinically non-functioning pituitary adenoma (NFPA) experience tumor recurrence 1–5 years after the first surgery. Nevertheless, there is still no recurrence prediction factor concisely established and reproduced in the literature for NFPA management. The present study evaluates the prognostic value of MRI Radiomics features combined with machine learning models to assess recurrence after the first surgery in patients with clinically non-functioning pituitary adenomas (NFPA). We carried out a retrospective study on 27 patients with NFPA, 10 patients having experienced tumor recurrence after the first surgery and 17 who did not. Preoperative 3D T1 contrast-enhanced MR images of patients were used to extract up to 255 Radiomics features from two and three-dimensional segmented regions. Additionally, gender, age at first surgery, and the presence of remnant tumor tissue were investigated to find the correlation with NFPA recurrence. Conventional statistics tests were used to evaluate whether the outcome patient groups (stable and recurrent) were different considering each feature individually. Additionally, five well-known machine-learning algorithms were used in combination with Radiomic features to classify recurrent and stable lesions. We found statistical evidence (p < 0.02) for 6 two-dimensional and 13 three-dimensional radiomic features. We achieved accuracies of up to 96.3% for 3D-feature based models and up to 92.6% accuracies for 2D-feature based models. 3D-feature based models achieved better performances using considerably fewer features when compared to 2D-feature based models. We concluded that Radiomics have the potential of NFPA recurrence prediction after the first surgery. Three-dimensional Radiomics have superior discrimination power to predict NFPA recurrence than two-dimensional radiomic features. Finally, the combination of Radiomics with machine-learning algorithms can offer computational models capable of non-invasive, unbiased, and quick assessment that might improve the prediction of NFPA recurrence.