Development and validation of a radiomics-visual evoked potential nomogram for preoperative prediction of visual outcome after endoscopic craniopharyngioma resection.

Abstract

Objective: Craniopharyngiomas are rare, benign brain tumors that are primarily treated with surgery. Although the extended endoscopic endonasal approach (EEEA) has evolved as a more reliable surgical alternative and yields better visual outcomes than traditional craniotomy, postoperative visual deterioration remains one of the most common complications, and relevant risk factors are still poorly defined. Hence, identifying risk factors and developing a predictive model for postoperative visual deterioration is indeed necessary. However, there is still a lack of research on these topics. Therefore, the authors used the largest known case series of EEEA for craniopharyngioma to determine pertinent risk factors and develop a nomogram for the noninvasive preoperative prediction of visual outcome.

Methods: A total of 483 cases of craniopharyngioma (338 in the training cohort, 145 in the validation cohort) between January 2019 and March 2023 were retrospectively reviewed, and related risk factors were identified. In total, 851 radiomic features from the MR images of each case were extracted. The least absolute shrinkage and selection operator algorithm was used to select features and construct the radiomic score (Rad-score). A support vector machine (SVM) classifier was adopted to construct a radiomic model. Moreover, a clinical-radiomic nomogram was built by multivariable logistic regression. The performance of the nomogram was assessed by its discrimination, calibration, and clinical utility.

Results: The overall incidence of postoperative visual deterioration was 9.1%. A lack of intraoperative visual evoked potential (VEP) monitoring (OR 0.221, p = 0.001), larger maximum tumor diameter (OR 1.052, p = 0.014), and tight adherence (OR 2.963, p = 0.044) were demonstrated as independent risk factors for postoperative visual deterioration. The radiomic model using the SVM based on 8 selected features exhibited good discrimination in predicting adhesion strength in the training and validation cohorts (area under the receiver operating characteristic curve [AUC] 0.85 vs 0.80). Moreover, the nomogram incorporating the Rad-score and clinical factors showed AUCs of 0.827 and 0.808 in the training and validation sets, respectively, fitting well in calibration curves. Decision curve analysis further confirmed the clinical usefulness of the nomogram.

Conclusions: Intraoperative VEP monitoring was proven to help reduce postoperative visual deterioration, while tight adherence and larger maximum tumor diameter were confirmed as independent risk factors. The radiomic model allowed a noninvasive prediction of the adherence strength between the optic nerves and craniopharyngioma. The nomogram showed a promising performance for noninvasively predicting postoperative visual deterioration and may serve as a useful tool for clinical decision-making and patient counseling.