Clinical Applications Research, Philips Research, Aachen.
Department of Neurosurgery, University Hospital Cologne, Cologne, Germany.
Invest Radiol. 2018 Nov;53(11):647-654. doi: 10.1097/RLI.0000000000000484.
The aims of this study were, first, to evaluate a deep learning-based, automatic glioblastoma (GB) tumor segmentation algorithm on clinical routine data from multiple centers and compare the results to a ground truth, manual expert segmentation, and second, to evaluate the quality of the segmentation results across heterogeneous acquisition protocols of routinely acquired clinical magnetic resonance imaging (MRI) examinations from multiple centers.
The data consisted of preoperative MRI scans (T1, T2, FLAIR, and contrast-enhanced [CE] T1) of 64 patients with an initial diagnosis of primary GB, which were acquired in 15 institutions with varying protocols. All images underwent preprocessing (coregistration, skull stripping, resampling to isotropic resolution, normalization) and were fed into an independently trained deep learning model based on DeepMedic, a multilayer, multiscale convolutional neural network for detection and segmentation of tumor compartments. Automatic segmentation results for the whole tumor, necrosis, and CE tumor were compared with manual segmentations.
Whole tumor and CE tumor compartments were correctly detected in 100% of the cases; necrosis was correctly detected in 91% of the cases. A high segmentation accuracy comparable to interrater variability was achieved for the whole tumor (mean dice similarity coefficient [DSC], 0.86 ± 0.09) and CE tumor (DSC, 0.78 ± 0.15). The DSC for tumor necrosis was 0.62 ± 0.30. We have observed robust segmentation quality over heterogeneous image acquisition protocols, for example, there were no correlations between resolution and segmentation accuracy of the single tumor compartments. Furthermore, no relevant correlation was found between quality of automatic segmentation and volume of interest properties (surface-to-volume ratio and volume).
The proposed approach for automatic segmentation of GB proved to be robust on routine clinical data and showed on all tumor compartments a high automatic detection rate and a high accuracy, comparable to interrater variability. Further work on improvements of the segmentation accuracy for the necrosis compartments should be guided by the evaluation of the clinical relevance.Therefore, we propose this approach as a suitable building block for automatic tumor segmentation to support radiologists or neurosurgeons in the preoperative reading of GB MRI images and characterization of primary GB.
本研究的目的首先是评估一种基于深度学习的胶质母细胞瘤（GB）肿瘤自动分割算法在来自多个中心的临床常规数据上的表现，并将结果与真实情况、手动专家分割进行比较；其次，评估该算法在来自多个中心的常规临床磁共振成像（MRI）检查的异质采集协议下的分割质量。
该研究的数据来自 64 名初诊为原发性 GB 患者的术前 MRI 扫描（T1、T2、FLAIR 和对比增强 [CE] T1），这些扫描分别来自 15 个不同协议的机构。所有图像均经过预处理（配准、颅骨剥离、各向同性分辨率重采样、归一化），并输入到一个基于 DeepMedic 的独立训练深度学习模型中，DeepMedic 是一种用于肿瘤区检测和分割的多层、多尺度卷积神经网络。自动分割结果与手动分割结果进行比较，包括全肿瘤、坏死和 CE 肿瘤。
全肿瘤和 CE 肿瘤在 100%的病例中被正确检测到；坏死在 91%的病例中被正确检测到。全肿瘤（平均骰子相似系数 [DSC]，0.86±0.09）和 CE 肿瘤（DSC，0.78±0.15）的分割精度与组内差异相当高。肿瘤坏死的 DSC 为 0.62±0.30。我们观察到，在异质图像采集协议下，分割质量具有很强的稳健性，例如，单个肿瘤区的分辨率与分割精度之间没有相关性。此外，自动分割质量与感兴趣区（体积表面比和体积）的性质之间也没有发现相关性。
该方法用于胶质母细胞瘤的自动分割，在常规临床数据上表现稳健，在所有肿瘤区都具有较高的自动检测率和较高的准确性，与组内差异相当。为了提高坏死区的分割精度，应根据对临床相关性的评估来进一步改进该方法。因此，我们提出该方法作为自动肿瘤分割的合适构建块，以支持放射科医生或神经外科医生在术前阅读胶质母细胞瘤 MRI 图像和对原发性胶质母细胞瘤进行特征描述。
