Department of Neurosurgery, Seoul National University Hospital, Seoul National University College of Medicine, Seoul, Korea.
Research and Science Division, Research and Development Center, MEDICALIP Co. Ltd, Seoul, Korea.
J Magn Reson Imaging. 2023 Mar;57(3):871-881. doi: 10.1002/jmri.28332. Epub 2022 Jul 1.
Accurate and rapid measurement of the MRI volume of meningiomas is essential in clinical practice to determine the growth rate of the tumor. Imperfect automation and disappointing performance for small meningiomas of previous automated volumetric tools limit their use in routine clinical practice.
To develop and validate a computational model for fully automated meningioma segmentation and volume measurement on contrast-enhanced MRI scans using deep learning.
Retrospective.
A total of 659 intracranial meningioma patients (median age, 59.0 years; interquartile range: 53.0-66.0 years) including 554 women and 105 men.
FIELD STRENGTH/SEQUENCE: The 1.0 T, 1.5 T, and 3.0 T; three-dimensional, T -weighted gradient-echo imaging with contrast enhancement.
The tumors were manually segmented by two neurosurgeons, H.K. and C.-K.P., with 10 and 26 years of clinical experience, respectively, for use as the ground truth. Deep learning models based on U-Net and nnU-Net were trained using 459 subjects and tested for 100 patients from a single institution (internal validation set [IVS]) and 100 patients from other 24 institutions (external validation set [EVS]), respectively. The performance of each model was evaluated with the Sørensen-Dice similarity coefficient (DSC) compared with the ground truth.
According to the normality of the data distribution verified by the Shapiro-Wilk test, variables with three or more categories were compared by the Kruskal-Wallis test with Dunn's post hoc analysis.
A two-dimensional (2D) nnU-Net showed the highest median DSCs of 0.922 and 0.893 for the IVS and EVS, respectively. The nnU-Nets achieved superior performance in meningioma segmentation than the U-Nets. The DSCs of the 2D nnU-Net for small meningiomas less than 1 cm were 0.769 and 0.780 with the IVS and EVS, respectively.
A fully automated and accurate volumetric measurement tool for meningioma with clinically applicable performance for small meningioma using nnU-Net was developed.
3 TECHNICAL EFFICACY: Stage 2.
在临床实践中，准确快速地测量脑膜瘤的 MRI 体积对于确定肿瘤的生长速度至关重要。以前的自动容积工具在测量小脑膜瘤时存在不完善的自动化和令人失望的性能，限制了它们在常规临床实践中的应用。
使用深度学习开发和验证一种用于增强对比度 MRI 扫描的全自动脑膜瘤分割和体积测量的计算模型。
回顾性。
共 659 例颅内脑膜瘤患者（中位年龄为 59.0 岁；四分位间距：53.0-66.0 岁），其中 554 例为女性，105 例为男性。
磁场强度/序列：1.0T、1.5T 和 3.0T；三维、T1 加权梯度回波成像，增强对比。
两名具有 10 年和 26 年临床经验的神经外科医生 H.K.和 C.-K.P.手动分割肿瘤，分别作为金标准。基于 U-Net 和 nnU-Net 的深度学习模型分别使用 459 例患者进行训练，并分别对来自单个机构的 100 例患者（内部验证集 [IVS]）和来自其他 24 个机构的 100 例患者（外部验证集 [EVS]）进行测试。通过与金标准相比，使用 Sørensen-Dice 相似系数（DSC）评估每个模型的性能。
根据 Shapiro-Wilk 检验验证的数据分布正态性，对于三个或更多类别的变量，使用 Kruskal-Wallis 检验和 Dunn 事后分析进行比较。
二维（2D）nnU-Net 的 IVS 和 EVS 的中位数 DSC 分别为 0.922 和 0.893，表现最佳。nnU-Nets 在脑膜瘤分割方面的表现优于 U-Nets。2D nnU-Net 对小于 1cm 的小脑膜瘤的 DSCs 分别为 IVS 和 EVS 的 0.769 和 0.780。
使用 nnU-Net 开发了一种全自动、准确的脑膜瘤容积测量工具，具有适用于小脑膜瘤的临床应用性能。
3 级技术功效：第 2 阶段。
