Radiomic features as a risk factor for early postoperative seizure in patients with meningioma

A PET-based radiomics nomogram for individualized predictions of seizure outcomes after temporal lobe epilepsy surgery

PURPOSE

To establish and validate a novel nomogram based on clinical characteristics and [18F]FDG PET radiomics for the prediction of postsurgical seizure freedom in patients with temporal lobe epilepsy (TLE).

PATIENTS AND METHODS

234 patients with drug-refractory TLE patients were included with a median follow-up time of 24 months after surgery. The correlation coefficient redundancy analysis and LASSO Cox regression were used to characterize risk factors. The Cox model was conducted to develop a Clinic-PET nomogram to predict the relapse status in the training set (n = 171). The nomogram's performance was estimated through discrimination, calibration, and clinical utility. The prognostic prediction model was validated in the test set (n = 63).

RESULTS

Eight radiomics features were selected to assess the radiomics score (radscore) of the operation side (Lat_radscore) and the asymmetric index (AI) of the radiomics score (AI_radscore). AI_radscor, Lat_radscor, secondarily generalized seizures (SGS), and duration between seizure onset and surgery (Durmon) were significant predictors of seizure-free outcomes. The final model had a C-index of 0.68 (95 %CI: 0.59-0.77) for complete freedom from seizures and time-dependent AUROC was 0.65 at 12 months, 0.65 at 36 months, and 0.59 at 60 months in the test set. A web application derived from the primary predictive model was displayed for economic and efficient use.

CONCLUSIONS

A PET-based radiomics nomogram is clinically promising for predicting seizure outcomes after temporal lobe epilepsy surgery.

Predictors of early and late postoperative seizures in meningioma patients: a systematic review and meta-analysis

Meningioma is the most common type of primary brain tumor which presents with a variety of neurological manifestations. Surgical resection tends to be the preferred treatment. The occurrence of seizures after resection is common, which occur either early, within seven days of operation, or late. Our meta-analysis investigated the possible predictors of early and late postoperative seizures. We assessed the relevant observational studies on predictors of postoperative seizures published in PubMed, Scopus, and Web of Science from January 2000 to September 2022, and those that met inclusion criteria were included. We calculated the association between potential predicting factors and postoperative seizures, odds ratios (ORs) with 95% confidence intervals (CIs) applying either random or fixed-effect models. The early and late postoperative seizures were evaluated individually. Thirteen observational studies involving 4176 patients were included. Seizures occurred in 250 (6%) and 584 (14%) patients, respectively, in the early and late postoperative phases. Shared predictors for early and late seizures included tumors involving the motor cortex (OR = 2.7; 95% CI: 1.67-4.38, OR = 2.46; 95% CI: 1.68-3.61), postoperative neurological deficit (OR = 4.68; 95% CI: 2.67-8.22, OR = 2.01; 95% CI: 1.39-2.92), and preoperative seizures (OR = 2.52; 95% CI: 1.82-3.49, OR = 4.35; 95% CI: 3.29-5.75). Peritumoral edema (OR = 1.99; 95% CI: 1.49-2.64) was a significant factor only among late postoperative seizure patients while surgical complications (OR = 3.77; 95% CI: 2.39-5.93) was a significant factor solely for early postoperative seizures. Meningioma patients commonly experience early and late postoperative seizures. Identifying predictors of postoperative seizures is essential to diagnose and manage them effectively.

Prediction of meningioma grade by constructing a clinical radiomics model nomogram based on magnetic resonance imaging

PURPOSE

To explore the clinical value of a clinical radiomics model nomogram based on magnetic resonance imaging (MRI) for preoperative meningioma grading.

MATERIALS AND METHODS

We collected retrospectively 544 patients with pathological diagnosis of meningiomas were categorized into training (n = 380) and validation (n = 164) groups at the ratio of 7∶ 3. There were 3,376 radiomics features extracted from T2WI and T1C by shukun technology platform after manual segmentation using an independent blind method by two radiologists. The Selectpercentile and Lasso are used to filter the most strongly correlated features. Random forest (RF) radiomics model and clinical radiomics model nomogram were constructed respectively. The calibration, discrimination, and clinical validity were evaluated by using the calibration curve and decision analysis curve (DCA).

RESULTS

The RF radiomics model based on T1C and T2WI was the most effective to predict meningioma grade before surgery among the six different classifiers. The predictive ability of clinical radiomics model was slightly higher than that of RF model alone. The AUC, SEN, SPE, and ACC of the training set were 0.949, 0.976, 0.785, and 0.826, and the AUC, SEN, SPE, and ACC of the validation set were 0.838, 0.829, 0.783, and 0.793, respectively. The calibration curve and Hosmer-Lemeshow test showed the predictive probability of the fusion model was similar to the actual differentiated LGM and HGM. The analysis of the decision curve showed that the clinical radiomics model could obtain the best clinical net profit.

CONCLUSIONS

The clinical radiomics model nomogram based on T1C and T2WI has high accuracy and sensitivity for predicting meningioma grade.

Radiomics and machine learning for predicting the consistency of benign tumors of the central nervous system: A systematic review

PURPOSE

Predicting the consistency of benign central nervous system (CNS) tumors prior to surgery helps to improve surgical outcomes. This review summarizes and analyzes the literature on using radiomics and/or machine learning (ML) for consistency prediction.

METHOD

The Medical Literature Analysis and Retrieval System Online (MEDLINE) database was screened for studies published in English from January 1st 2000. Data was extracted according to the PRISMA guidelines and quality of the studies was assessed in compliance with the Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2).

RESULTS

Eight publications were included focusing on pituitary macroadenomas (n = 5), pituitary adenomas (n = 1), and meningiomas (n = 2) using a retrospective (n = 6), prospective (n = 1), and unknown (n = 1) study design with a total of 763 patients for the consistency prediction. The studies reported an area under the curve (AUC) of 0.71-0.99 for their respective best performing model regarding the consistency prediction. Of all studies, four articles validated their models internally whereas none validated their models externally. Two articles stated making data available on request with the remaining publications lacking information with regard to data availability.

CONCLUSIONS

The research on consistency prediction of CNS tumors is still at an early stage regarding the use of radiomics and different ML techniques. Best-practice procedures regarding radiomics and ML need to be followed more rigorously to facilitate the comparison between publications and, accordingly, the possible implementation into clinical practice in the future.

Preoperative MRI for postoperative seizure prediction: a radiomics study of dysembryoplastic neuroepithelial tumor and a systematic review

OBJECTIVE

In this systematic review the authors aimed to evaluate the effectiveness and superiority of radiomics in detecting tiny epilepsy lesions and to conduct original research in the use of radiomics for preliminary prediction of postoperative seizures in patients with dysembryoplastic neuroepithelial tumor (DNET).

METHODS

The PubMed and Web of Science databases were searched from the earliest record, January 1, 2018, to December 29, 2021, for reports of the detection of epilepsy using radiomics, and the resulting articles were carefully checked according to the PRISMA 2020 guidelines. The authors then conducted original research by evaluating MR images in 18 patients, who were then separated into two groups, the epilepsy recurrence group (ERG) and the epilepsy nonrecurrence group. The tumor region and the edema region were segmented manually by 3D Slicer. The radiomics data were extracted from MR images by using “Slicer Radiomics” running on Mac OS X. Tumor regions were observed with T1-weighted imaging, and edema with FLAIR imaging. Radiomics features with significant differences were selected through comparison according to epilepsy relapses performed with the Mann-Whitney U-test. The edema and tumor regions were also compared within groups to identify their distinctive features. Radiomics features were tested to verify their ability to predict recurrence epilepsy by receiver operating characteristic curve.

RESULTS

This systematic review located 9 original articles related to epilepsy and radiomics published from 2018 to 2021. The reported studies demonstrated that radiomics is useful for detecting tiny epilepsy lesions. Among the radiomics features used, the predictive ability of the area under the curve was more than 0.8. The heterogeneity of the peritumoral edema region was found to be higher in the ERG.

CONCLUSIONS

Satellite lesions in the peritumoral edema region of DNET patients may cause epilepsy recurrence, and radiomics is an emerging method to detect and evaluate these epilepsy-associated lesions.