Magnetic resonance imaging indicators for neurological outcome after surgery in patients with intramedullary spinal ependymomas

This is a retrospective study. The aim of this study was to determine the indicators of neurological outcome after surgery in patients with intramedullary spinal ependymomas by using magnetic resonance imaging (MRI). A total of 106 consecutive patients (mean age: 42.4 +/- 1.3 years; 52.8% male) diagnosed with intramedullary spinal ependymomas were retrospectively recruited. All patients underwent spine MRI and subsequent surgical resection for the spinal tumors. Data regarding clinical symptoms and pathological grades of tumors were collected from clinical records. The McCormick score was used for grading patients' neurological status before and after surgery at 12 months. Good outcome was defined as stable McCormick score (McC) score (no change of McC score between preoperation and post-operation at 12 months) or improvement in McC score (post-operative McC score at 12 months < preoperative McC score). Poor outcome was determined when there was an increase in McC score at 12 months after surgery. The MRI characteristics of spinal ependymomas between patients with good and poor neurological outcomes were compared. Logistic regression was performed to assess the association between MRI characteristics of tumors and post-operative neurological outcomes. Patients with poor neurological outcomes had larger longitudinal length (4.7 +/- 0.5 vs 3.3 +/- 0.2, P = .004) and higher enhancement signal-to-noise-ratio (SNR) (102.4 +/- 12.3 vs 72.8 +/- 4.6, P = .022) than those with good neurological outcomes. After adjusting for confounding factors, longitudinal length (OR, 0.768; 95% CI, 0.604-0.976; P = .031) and enhancement SNR (OR, 0.988; 95% CI, 0.978-0.999; P = .026) of spinal ependymomas were significantly associated with poor neurological prognosis. The longitudinal length of tumor and enhancement SNR on T1-weighted images are independently associated with neurological outcome after surgery.