A Preoperative MRI-Based Radiomics-Clinicopathological Classifier to Predict the Recurrence of Pituitary Macroadenoma Within 5 Years

Abstract

Objective: To investigate the ability of a MRI-based radiomics-clinicopathological model to predict pituitary macroadenoma (PMA) recurrence within 5 years. Materials and Methods: We recruited 74 recurrent and 94 non-recurrent subjects, following first surgery with 5-year follow-up data. Univariate and multivariate analyses were conducted to identify independent clinicopathological risk factors. Two independent and blinded neuroradiologists used 3D-Slicer software to manually delineate whole tumors using preoperative axial contrast-enhanced T1WI (CE-T1WI) images. 3D-Slicer was then used to extract radiomics features from segmented tumors. Dimensionality reduction was carried out by the least absolute shrinkage and selection operator (LASSO). Two multilayer perceptron (MLP) models were established, including independent clinicopathological risk factors (Model 1) and a combination of screened radiomics features and independent clinicopathological markers (Model 2). The predictive performance of these models was evaluated by receiver operator characteristic (ROC) curve analysis. Results: In total, 1,130 features were identified, and 4 of these were selected by LASSO. In the test set, the area under the curve (AUC) of Model 2 was superior to Model 1 {0.783, [95% confidence interval (CI): 0.718-.860] vs. 0.739, (95% CI: 0.665-0.818)}. Model 2 also yielded the higher accuracy (0.808 vs. 0.692), sensitivity (0.826 vs. 0.652), and specificity (0.793 vs. 0.724) than Model 1. Conclusions: The integrated classifier was superior to a clinical classifier and may facilitate the prediction of individualized prognosis and therapy.

Keywords: deep learning; multilayer perceptron; pituitary macroadenoma; predictive model; recurrence.

Figure 1

The process used for the analysis of radiomics. Radiomics features were extracted from the preoperative axial CE-T1WI images by 3D slicer. Dimension reductions were performed two times by ICC and LASSO. The MLP was used to build two predictive models. Model 1 included independent clinicopathological risk factors. Model 2 included the combination of radiomics features and independent risk factors.

Figure 2

Violin plots showing the differences of 4 selected radiomics features, Shape_Sphericity (A), LOG_GLDM_LDHGLE (B), Wavelet_GLSZM_GLNU (C), and Wavelet_GLSZM_ZE (D) between groups of recurrence and non-recurrence in the training set by Mann—Whitney U-test. GLDM, gray-level dependence matrix; GLNU, gray-level non-uniformity; GLSZM, gray-level size zone matrix; LDHGLE, large dependence high-gray-level emphasis; LOG, laplacian of gaussian; ZE, zone entropy.

Figure 3

The receiver-operating characteristic (ROC) curve for Models 1 and 2 in the training (A) and test sets (B), respectively. Model 1 included independent clinicopathological risk factors and Model 2 included both radiomics features and independent clinicopathological risk factors.