文献速递神经MR

多参数深度学习模型在临床常规异质性磁共振数据中对胶质母细胞瘤分割的临床评估

Clinical Evaluation of a Multiparametric Deep Learning Model for Glioblastoma Segmentation Using Heterogeneous Magnetic Resonance Imaging Data From Clinical Routine.
PubMed 文献 · Invest Radiol · 2018-01-01

本研究在15家机构64例原发性胶质母细胞瘤患者的术前MRI上评估基于DeepMedic的深度学习自动分割模型,并与专家手动分割比较。全肿瘤和强化肿瘤100%正确检出,坏死91%正确检出;全肿瘤DSC为0.86±0.09,强化肿瘤0.78±0.15,坏死0.62±0.30。分割质量在不同采集方案间稳健,分辨率及感兴趣区属性与分割准确度无相关。

要点

  • 全肿瘤和强化肿瘤自动检出率达100%,坏死检出率为91%。
  • 全肿瘤分割DSC为0.86±0.09,强化肿瘤0.78±0.15,坏死0.62±0.30。
  • 不同采集方案间分割质量稳健,分辨率与各肿瘤分区分割准确度无相关。

核心结论

  • 该自动分割方法在常规临床数据上表现稳健,对所有肿瘤分区具有高自动检出率和高准确度,与观察者间变异相当;作者提出该方法可作为自动肿瘤分割的合适组成部分,以辅助放射科或神经外科医生术前阅读胶质母细胞瘤MRI图像并表征原发性胶质母细胞瘤。

研究设计与样本

  • 研究纳入15家机构不同采集方案的64例初诊原发性胶质母细胞瘤患者术前MRI(T1、T2、FLAIR和增强T1),经预处理后输入基于DeepMedic的多层多尺度卷积神经网络进行肿瘤分区检测与分割,并与手动专家分割比较。

关键影像表现/征象

  • 全肿瘤和强化肿瘤分区在100%的病例中正确检出,坏死在91%的病例中正确检出。
  • 全肿瘤分割平均DSC为0.86±0.09,强化肿瘤为0.78±0.15,坏死为0.62±0.30。
  • 在不同异质性图像采集方案间观察到稳健的分割质量,例如分辨率与单个肿瘤分区的分割准确度之间无相关性。
  • 自动分割质量与感兴趣区属性(表面积体积比和体积)之间未发现相关。

诊断标准与关键数值

  • 全肿瘤分割准确度以平均DSC 0.86±0.09评估,与观察者间变异相当。
  • 强化肿瘤分割准确度以DSC 0.78±0.15评估。
  • 肿瘤坏死分割准确度以DSC 0.62±0.30评估。
  • 全肿瘤和强化肿瘤正确检出率为100%,坏死正确检出率为91%。

临床应用与阅片要点

  • 作者提出该方法可作为自动肿瘤分割的合适组成部分,以辅助放射科或神经外科医生术前阅读胶质母细胞瘤MRI图像并表征原发性胶质母细胞瘤。
  • 坏死分区的分割准确度改进工作应由临床相关性评估来引导。

局限性

  • 坏死分区的分割准确度有待改进,进一步工作应由临床相关性评估来引导。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

OBJECTIVES: 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.

MATERIALS AND METHODS: 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.

RESULTS: 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).

CONCLUSIONS: 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.

来源:Invest Radiol,查看原文。版权归原作者所有。

引用

  1. Perkuhn M, Stavrinou P, Thiele F, et al. Clinical Evaluation of a Multiparametric Deep Learning Model for Glioblastoma Segmentation Using Heterogeneous Magnetic Resonance Imaging Data From Clinical Routine. Invest Radiol. 2018. PMID: 29863600. doi:10.1097/RLI.0000000000000484

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。