For currently available augmented reality workflows, 3D models need to be created with manual or semiautomatic segmentation, which is a time-consuming process. The authors created an automatic segmentation algorithm that generates 3D models of skin, brain, ventricles, and contrast-enhancing tumor from a single T1-weighted MR sequence and embedded this model into an automatic workflow for 3D evaluation of anatomical structures with augmented reality in a cloud environment. In this study, the authors validate the accuracy and efficiency of this automatic segmentation algorithm for brain tumors and compared it with a manually segmented ground truth set.

Fifty contrast-enhanced T1-weighted sequences of patients with contrast-enhancing lesions measuring at least 5 cm³ were included. All slices of the ground truth set were manually segmented. The same scans were subsequently run in the cloud environment for automatic segmentation. Segmentation times were recorded. The accuracy of the algorithm was compared with that of manual segmentation and evaluated in terms of Sørensen-Dice similarity coefficient (DSC), average symmetric surface distance (ASSD), and 95th percentile of Hausdorff distance (HD₉₅).

The mean ± SD computation time of the automatic segmentation algorithm was 753 ± 128 seconds. The mean ± SD DSC was 0.868 ± 0.07, ASSD was 1.31 ± 0.63 mm, and HD₉₅ was 4.80 ± 3.18 mm. Meningioma (mean 0.89 and median 0.92) showed greater DSC than metastasis (mean 0.84 and median 0.85). Automatic segmentation had greater accuracy for measuring DSC (mean 0.86 and median 0.87) and HD₉₅ (mean 3.62 mm and median 3.11 mm) of supratentorial metastasis than those of infratentorial metastasis (mean 0.82 and median 0.81 for DSC; mean 5.26 mm and median 4.72 mm for HD₉₅).

The automatic cloud-based segmentation algorithm is reliable, accurate, and fast enough to aid neurosurgeons in everyday clinical practice by providing 3D augmented reality visualization of contrast-enhancing intracranial lesions measuring at least 5 cm³. The next steps involve incorporation of other sequences and improving accuracy with 3D fine-tuning in order to expand the scope of augmented reality workflow.

对于当前可用的增强现实工作流程，需要使用手动或半自动分割来创建 3D 模型，这是一个耗时的过程。作者创建了一种自动分割算法，该算法可从单个 T1 加权 MR 序列生成皮肤、大脑、心室和对比度增强肿瘤的 3D 模型，并将该模型嵌入到自动工作流程中，以在云环境。在这项研究中，作者验证了这种脑肿瘤自动分割算法的准确性和效率，并将其与手动分割的地面实况集进行了比较。

包括测量至少 5 cm ^{3 的}对比增强病变患者的 50 个对比增强 T1 加权序列。地面实况集的所有切片都是手动分割的。随后在云环境中运行相同的扫描以进行自动分割。记录分割时间。将算法的准确性与手动分割的准确性进行比较，并根据 Sørensen-Dice 相似系数 (DSC)、平均对称表面距离 (ASSD) 和 Hausdorff 距离的第 95 个百分位数 (HD ₉₅ )进行评估。

自动分割算法的平均值 ± SD 计算时间为 753 ± 128 秒。平均值 ± SD DSC 为 0.868 ± 0.07，ASSD 为 1.31 ± 0.63 mm，HD ₉₅为 4.80 ± 3.18 mm。脑膜瘤（平均 0.89 和中位数 0.92）显示出比转移（平均 0.84 和中位数 0.85）更大的 DSC。自动分割在测量幕上转移的DSC（平均 0.86 和中位数 0.87）和 HD ₉₅（平均 3.62 毫米和中位数 3.11 毫米）方面比幕下转移（DSC 平均 0.82 和中位数 0.81；平均 5.26 毫米和中位数 4.72 ）具有更高的准确性毫米为 HD ₉₅）。

基于云的自动分割算法可靠、准确且足够快，通过提供测量至少 5 cm ³的增强对比的颅内病变的 3D 增强现实可视化，足以在日常临床实践中帮助神经外科医生。下一步包括合并其他序列并通过 3D 微调提高准确性，以扩大增强现实工作流程的范围。