OBJECTIVES Patients with multiple sclerosis (MS) regularly undergo MRI for assessment of disease burden. However, interpretation may be time consuming and prone to intra- and interobserver variability. Here, we evaluate the potential of artificial neural networks (ANN) for automated volumetric assessment of MS disease burden and activity on MRI. METHODS A single-institutional dataset with 334 MS patients (334 MRI exams) was used to develop and train an ANN for automated identification and volumetric segmentation of T2/FLAIR-hyperintense and contrast-enhancing (CE) lesions. Independent testing was performed in a single-institutional longitudinal dataset with 82 patients (266 MRI exams). We evaluated lesion detection performance (F1 scores), lesion segmentation agreement (DICE coefficients), and lesion volume agreement (concordance correlation coefficients [CCC]). Independent evaluation was performed on the public ISBI-2015 challenge dataset. RESULTS The F1 score was maximized in the training set at a detection threshold of 7 mm3 for T2/FLAIR lesions and 14 mm3 for CE lesions. In the training set, mean F1 scores were 0.867 for T2/FLAIR lesions and 0.636 for CE lesions, as compared to 0.878 for T2/FLAIR lesions and 0.715 for CE lesions in the test set. Using these thresholds, the ANN yielded mean DICE coefficients of 0.834 and 0.878 for segmentation of T2/FLAIR and CE lesions in the training set (fivefold cross-validation). Corresponding DICE coefficients in the test set were 0.846 for T2/FLAIR lesions and 0.908 for CE lesions, and the CCC was ≥ 0.960 in each dataset. CONCLUSIONS Our results highlight the capability of ANN for quantitative state-of-the-art assessment of volumetric lesion load on MRI and potentially enable a more accurate assessment of disease burden in patients with MS. KEY POINTS • Artificial neural networks (ANN) can accurately detect and segment both T2/FLAIR and contrast-enhancing MS lesions in MRI data. • Performance of the ANN was consistent in a clinically derived dataset, with patients presenting all possible disease stages in MRI scans acquired from standard clinical routine rather than with high-quality research sequences. • Computer-aided evaluation of MS with ANN could streamline both clinical and research procedures in the volumetric assessment of MS disease burden as well as in lesion detection.

中文翻译：

---

使用人工神经网络进行的自动体积评估可以更准确地评估多发性硬化症患者的疾病负担。

目标 多发性硬化症 (MS) 患者定期接受 MRI 以评估疾病负担。然而，解释可能非常耗时，并且容易出现观察者内部和观察者间的差异。在这里，我们评估了人工神经网络 (ANN) 在 MRI 上对 MS 疾病负担和活动进行自动体积评估的潜力。方法 使用包含 334 名 MS 患者（334 次 MRI 检查）的单一机构数据集来开发和训练人工神经网络，以自动识别和体积分割 T2/FLAIR 高信号和对比增强 (CE) 病变。在包含 82 名患者（266 次 MRI 检查）的单一机构纵向数据集中进行了独立测试。我们评估了病变检测性能（F1 分数）、病变分割一致性（DICE 系数）、和病变体积一致性（一致性相关系数 [CCC]）。对公共 ISBI-2015 挑战数据集进行了独立评估。结果 在 T2/FLAIR 病变的检测阈值为 7 mm3 和 CE 病变的检测阈值为 14 mm3 时，训练集中的 F1 分数最大化。在训练集中，T2/FLAIR 病变的平均 F1 分数为 0.867，CE 病变为 0.636，而测试集中的 T2/FLAIR 病变为 0.878，CE 病变为 0.715。使用这些阈值，ANN 产生了 0.834 和 0.878 的平均 DICE 系数，用于分割训练集中的 T2/FLAIR 和 CE 病变（五重交叉验证）。测试集中相应的 DICE 系数对于 T2/FLAIR 病变为 0.846，对于 CE 病变为 0.908，并且每个数据集中的 CCC ≥ 0.960。结论 我们的结果强调了 ANN 对 MRI 体积病变负荷进行定量最新评估的能力，并有可能更准确地评估 MS 患者的疾病负担。要点 • 人工神经网络 (ANN) 可以准确地检测和分割 MRI 数据中的 T2/FLAIR 和对比增强 MS 病变。• ANN 的性能在临床衍生的数据集中是一致的，患者在从标准临床常规而不是高质量研究序列获得的 MRI 扫描中呈现所有可能的疾病阶段。• 使用 ANN 对 MS 进行计算机辅助评估可以简化 MS 疾病负担体积评估以及病变检测中的临床和研究程序。