文献速递神经MR

复发性胶质母细胞瘤中BraTumIA自动分割的可重复性

Repeatability of Automated Image Segmentation with BraTumIA in Patients with Recurrent Glioblastoma.
PubMed 文献 · AJNR Am J Neuroradiol · 2021-03-18

该研究在20例复发性胶质母细胞瘤患者中,对间隔约2天的重复MRI扫描使用BraTumIA 1.2和2.0版自动分割肿瘤各成分,评估可重复性。结果显示增强肿瘤和水肿的Dice系数较高(>0.7),非增强肿瘤和坏死较低;增强肿瘤体积在 later 扫描中较大,作者认为可能与钆对比剂洗脱不完全有关。

要点

  • BraTumIA分割增强肿瘤和水肿的可重复性较好,Dice系数>0.7。
  • 非增强肿瘤和坏死的可重复性较差,重复性系数达87%~116%。
  • 后期扫描增强肿瘤体积大于早期扫描,可能受对比剂残留影响。

关键影像表现/征象

  • BraTumIA 1.2后期扫描增强肿瘤平均体积26.3 mL vs 早期24.2 mL(P<.05);BraTumIA 2.0后期24.9 mL vs 早期22.9 mL(P<.01)。
  • 增强肿瘤和水肿的Dice系数最高(>0.7),坏死居中,非增强肿瘤最低,且两个软件版本间无差异。
  • BraTumIA 2.0较1.2版分割的增强肿瘤和水肿更小,坏死肿瘤更大。

诊断标准与关键数值

  • 增强肿瘤和水肿的重复性系数范围为31%~46%,非增强肿瘤和坏死为87%~116%。
  • Dice系数:增强肿瘤和水肿>0.7,坏死居中,非增强肿瘤最低。

临床应用与阅片要点

  • 使用BraTumIA分割时,增强肿瘤和水肿的测量较可靠,非增强肿瘤和坏死需谨慎解读。
  • 重复扫描时间间隔较短时,增强肿瘤体积可能因对比剂残留而偏大,报告时需考虑此因素。
  • 不同软件版本间增强肿瘤和水肿体积存在差异,纵向比较时应使用同一版本。

局限性

  • 作者指出钆对比剂洗脱不完全可能解释后期扫描增强肿瘤体积增大。

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

BACKGROUND AND PURPOSE: Despite high interest in machine-learning algorithms for automated segmentation of MRIs of patients with brain tumors, there are few reports on the variability of segmentation results. The purpose of this study was to obtain benchmark measures of repeatability for a widely accessible software program, BraTumIA (Versions 1.2 and 2.0), which uses a machine-learning algorithm to segment tumor features on contrast-enhanced brain MR imaging.

MATERIALS AND METHODS: Automatic segmentation of enhancing tumor, tumor edema, nonenhancing tumor, and necrosis was performed on repeat MR imaging scans obtained approximately 2 days apart in 20 patients with recurrent glioblastoma. Measures of repeatability and spatial overlap, including repeatability and Dice coefficients, are reported.

RESULTS: Larger volumes of enhancing tumor were obtained on later compared with earlier scans (mean, 26.3 versus 24.2 mL for BraTumIA 1.2; P < .05; and 24.9 versus 22.9 mL for BraTumIA 2.0, P < .01). In terms of percentage change, repeatability coefficients ranged from 31% to 46% for enhancing tumor and edema components and from 87% to 116% for nonenhancing tumor and necrosis. Dice coefficients were highest (>0.7) for enhancing tumor and edema components, intermediate for necrosis, and lowest for nonenhancing tumor and did not differ between software versions. Enhancing tumor and tumor edema were smaller, and necrotic tumor larger using BraTumIA 2.0 rather than 1.2.

CONCLUSIONS: Repeatability and overlap metrics varied by segmentation type, with better performance for segmentations of enhancing tumor and tumor edema compared with other components. Incomplete washout of gadolinium contrast agents could account for increasing enhancing tumor volumes on later scans.

来源:AJNR Am J Neuroradiol,查看原文。版权归原作者所有。

引用

  1. Abu Khalaf N, Desjardins A, Vredenburgh JJ, et al. Repeatability of Automated Image Segmentation with BraTumIA in Patients with Recurrent Glioblastoma. AJNR Am J Neuroradiol. 2021. PMID: 33737270. doi:10.3174/ajnr.A7071

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。