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

中文翻译：

---

基于卷积神经网络的磁共振图像区分终丝室管膜瘤和神经鞘瘤

终末室管膜瘤 (FTE) 与神经鞘瘤的术前诊断很困难，但对于手术计划和预后评估至关重要。随着基于卷积神经网络（CNN）的深度学习方法的进步，本研究的目的是确定是否可以实现基于 CNN 的这两种肿瘤的磁共振（MR）图像的解释。回顾性收集 50 名原发性 FTE 患者和 50 名腰骶椎管神经鞘瘤患者的对比增强 MRI 数据，并将其用作训练和内部验证数据集。MRI诊断的准确性取决于与术后组织病理学检查的一致性。选择包含肿瘤块的矢状面的T1加权（T1-WI）、T2加权（T2-WI）和对比增强T1加权（CE-T1）MR图像进行分析。对于每个序列，患者 MRI 数据被随机分配到 5 组，这些组进一步进行五倍交叉验证，以评估 CNN 模型的诊断功效。另外 34 对案例被用作外部测试数据集来验证 CNN 分类器。在比较多个骨干 CNN 模型后，我们使用 Inception-v3 开发了一个诊断系统。在外部测试数据集中，基于 T1 加权图像的每次检查组合灵敏度为 0.78（0.71-0.84，95% CI），T2 加权图像为 0.79（0.72-0.84，95% CI），T2 加权图像为 0.88（0.83- CE-T1 图像为 0.92，95% CI），所有加权图像为 0.88（0.83–0.92，95% CI）。基于 T1-WI 的组合特异性为 0.72（0.66–0.78，95% CI），基于 T2-WI 的组合特异性为 0.84（0.78–0.89，95% CI），CE-T1 的组合特异性为 0.74（0.67–0.80，95% CI）对于所有加权图像，为 0.81（0.76–0.86，95% CI）。合并所有三种MRI模式后，计算受试者工作特征（ROC）曲线，曲线下面积（AUC）为0.93，准确度为0.87。基于 CNN 的 MRI 分析有可能准确区分腰段的室管膜瘤和神经鞘瘤。