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

Abstract

PurposeCraniopharyngiomas (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.MethodsIn 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.ResultsEleven 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.ConclusionThe 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.

Clinical Outcomes of Transcranial and Endoscopic Endonasal Surgery for Craniopharyngiomas: A Single-Institution Experience

“…Typically, the surgical outcome is closely associated with the extent of resection (3,7,22). Reports showed that the extent of resection is an independent predictor of tumor recurrence (7,16,17,(23)(24)(25). However, the close association of these tumors with critical neurovascular structures and locally aggressive characteristics make GTR difficult and lead to controversies surrounding the extent of resection in patients with craniopharyngiomas (10,11,26).…”

“…Furthermore, radiosurgery has been proven to have the potential for better outcomes and decreasing mortality (3,(27)(28)(29). Subtotal resection surgery combined with radiotherapy has been advocated to protect hypothalamus-pituitary function and prevent tumor recurrence (23). In addition, neurosurgical expertise has an important impact on the extent of resection (24,(30)(31)(32), and tumor size may be a predictor of the postoperative functional outcome.…”

Nomograms to Predict Endocrinological Deficiency in Patients With Surgically Treated Craniopharyngioma

“…Further, a nomogram based on independent risk factors can provide more individual and accurate prognosis data for treating clinicians and patients or their relatives. In the last two decades, neurosurgical clinical prediction models have increased exponentially, for a variety of clinical outcomes ( 23 , 45 ). This is the first study to construct models to predict postoperative endocrinological prognosis in patients with CP.…”

Application of Artificial Intelligence in Diagnosis of Craniopharyngioma

“…Therefore, preoperative evaluation of the tissue invasion of craniopharyngioma is helpful to formulate a more individualized surgical scheme. Ma et al ( 31 ) used a machine learning algorithm combined with radiological characteristics to predict preoperative craniopharyngioma invasiveness. The study cohort consisted of 325 patients in a single institution.…”

“…Zhang et al ( 28 ) verified five feature selection methods including distance correlation, random forest, Lasso, extreme gradient boosting and gradient boosting decision tree, of which Lasso achieved the best performance. And Ma et al ( 31 ) also adopted Lasso for feature selection. Gutta et al ( 41 ) used the importance score in the gradient boosting algorithm to select the features.…”