Non-Invasive Radiomics Approach Predict Invasiveness of Adamantinomatous Craniopharyngioma Before Surgery

Abstract

Purpose: Craniopharyngiomas (CPs) are benign tumors, complete tumor resection is considered to be the optimal treatment. However, although histologically benign, the local invasiveness of CPs commonly contributes to incomplete resection and a poor prognosis. At present, some advocate less aggressive surgery combined with radiotherapy as a more reasonable and effective means of protecting hypothalamus function and preventing recurrence in patients with tight tumor adhesion to the hypothalamus. Hence, if a method can be developed to predict the invasiveness of CP preoperatively, it will help in the development of a more personalized surgical strategy. The aim of the study was to report a radiomics-clinical nomogram for the individualized preoperative prediction of the invasiveness of adamantinomatous CP (ACPs) before surgery.

Methods: In total, 1,874 radiomics features were extracted from whole tumors on contrast-enhanced T1-weighted images. A support vector machine trained a predictive model that was validated using receiver operating characteristic (ROC) analysis on an independent test set. Moreover, a nomogram was constructed incorporating clinical characteristics and the radiomics signature for individual prediction.

Results: Eleven features associated with the invasiveness of ACPs were selected by using the least absolute shrinkage and selection operator (LASSO) method. These features yielded area under the curve (AUC) values of 79.09 and 73.5% for the training and test sets, respectively. The nomogram incorporating peritumoral edema and the radiomics signature yielded good calibration in the training and test sets with the AUCs of 84.79 and 76.48%, respectively.

Conclusion: The developed model yields good performance, indicating that the invasiveness of APCs can be predicted using noninvasive radiological data. This reliable, noninvasive tool can help clinical decision making and improve patient prognosis.

Keywords: adamantinomatous; craniopharyngioma; invasiveness; machine learning; nomogram; radiomics.

Figure 1

Texture feature selection using LASSO logistic regression. (A) Selection of the tuning parameter (lambda). The dotted vertical lines are plotted at the optimal λ values based on the minimum criteria and 1 standard error of the minimum criteria. (B) LASSO coefficient profiles are shown for the 1874 texture features. A vertical line is drawn at the value where the optimal lambda results in 11 nonzero coefficients.

Figure 2

Receiver operating characteristic curves for the prediction of invasiveness of ACPs in the training and validation sets. (A) For the training set, the area under the curve (AUC) was 79.09% with a sensitivity, specificity and accuracy of 81.97, 66.74, and 75%, respectively. (B) For the validation set, the AUC was 73.5% with a sensitivity, specificity and accuracy of 69.53, 72.44, and 66.53%, respectively.

Figure 3

The radiomic-clinical nomogram and its performance are illustrated. (A) The radiomics-clinical nomogram developed to predict the invasiveness of ACPs is illustrated. (B) For the training set, the AUC was 84.79% with the sensitivity, specificity and accuracy of 83.27, 76.05, and 78.22%, respectively. (C) For the validation set, the AUC was 76.48% with a sensitivity, specificity and accuracy of 71.24, 72.33, and 72.58%, respectively.