Prognostic factors for progression-free survival of the filum terminale ependymomas in adults

Convolutional neural network-based magnetic resonance image differentiation of filum terminale ependymomas from schwannomas

PURPOSE

Preoperative diagnosis of filum terminale ependymomas (FTEs) versus schwannomas is difficult but essential for surgical planning and prognostic assessment. With the advancement of deep-learning approaches based on convolutional neural networks (CNNs), the aim of this study was to determine whether CNN-based interpretation of magnetic resonance (MR) images of these two tumours could be achieved.

METHODS

Contrast-enhanced MRI data from 50 patients with primary FTE and 50 schwannomas in the lumbosacral spinal canal were retrospectively collected and used as training and internal validation datasets. The diagnostic accuracy of MRI was determined by consistency with postoperative histopathological examination. T1-weighted (T1-WI), T2-weighted (T2-WI) and contrast-enhanced T1-weighted (CE-T1) MR images of the sagittal plane containing the tumour mass were selected for analysis. For each sequence, patient MRI data were randomly allocated to 5 groups that further underwent fivefold cross-validation to evaluate the diagnostic efficacy of the CNN models. An additional 34 pairs of cases were used as an external test dataset to validate the CNN classifiers.

RESULTS

After comparing multiple backbone CNN models, we developed a diagnostic system using Inception-v3. In the external test dataset, the per-examination combined sensitivities were 0.78 (0.71-0.84, 95% CI) based on T1-weighted images, 0.79 (0.72-0.84, 95% CI) for T2-weighted images, 0.88 (0.83-0.92, 95% CI) for CE-T1 images, and 0.88 (0.83-0.92, 95% CI) for all weighted images. The combined specificities were 0.72 based on T1-WI (0.66-0.78, 95% CI), 0.84 (0.78-0.89, 95% CI) based on T2-WI, 0.74 (0.67-0.80, 95% CI) for CE-T1, and 0.81 (0.76-0.86, 95% CI) for all weighted images. After all three MRI modalities were merged, the receiver operating characteristic (ROC) curve was calculated, and the area under the curve (AUC) was 0.93, with an accuracy of 0.87.

CONCLUSIONS

CNN based MRI analysis has the potential to accurately differentiate ependymomas from schwannomas in the lumbar segment.

Predictors of functional outcome after spinal cord surgery: Relevance of intraoperative neurophysiological monitoring combined with preoperative neurophysiological and MRI assessments

OBJECTIVES

To assess the accuracy of intraoperative neurophysiological monitoring (IONM) in predicting immediate and 3-month postoperative neurological new deficit (or deterioration) in patients benefiting from spinal cord (SC) surgery; and to identify factors associated with a higher risk of postoperative clinical worsening.

METHODS

Consecutive patients who underwent SC surgery with IONM were included. Pre and postoperative clinical (modified McCormick scale), radiological (lesion-occupying area ratio), and electrophysiological features were collected.

RESULTS

A total of 99 patients were included: 14 (14.1%) underwent extradural surgery, 50 (50.5%) intradural extramedullary surgery, and 35 (35.4%) intramedullary surgery. Cumulatively, multimodal IONM (motor and somatosensory evoked potentials, D-wave whenever possible) significantly predicted postoperative deficits (p<0.001), with a sensitivity, specificity, positive predictive value, and negative predictive value of 0.81, 0.93, 0.83, and 0.92, respectively. Sixty (60.6%) patients displayed no IONM change, whereas 39 (39.4%) displayed IONM worsening. In multivariate analysis, predictors for postoperative clinical worsening were: abnormal preoperative electrophysiological assessment (p=0.03), intramedullary tumor (p<0.001), lesion-occupying area ratio ≥0.7 (p<0.001), and IONM alterations (p<0.001). Three months after the surgical procedure, in patients presenting at least one of the risk factors described above, 45/81 (55.6%) and 19/81 (23.5%) were clinically and electrophysiologically improved, respectively; while 13/81 (16.0%) and 10/81 (12.3%) were clinically and electrophysiologically worsened.

CONCLUSION

Multimodal IONM is an essential tool to guide SC surgery, and enables the accurate prediction of postoperative neurological outcome. Specific attention should be given to patients presenting with preoperative electrophysiological abnormalities, large tumor volume, and intramedullary tumor location.