文献速递中枢神经肿瘤放疗放疗物理与技术

MetNet:对比增强T1加权MRI中脑转移瘤的计算机辅助分割

MetNet: Computer-aided segmentation of brain metastases in post-contrast T1-weighted magnetic resonance imaging.
PubMed 文献 · Radiother Oncol · 2020-09-13

本研究回顾性分析934例接受立体定向放射外科(SRS)患者的对比增强3D T1加权MRI,构建两阶段深度学习集成模型MetNet用于脑转移瘤分割。结果显示,对于1-52 mm转移瘤,患者平均敏感度88%±19%、阳性预测值(PPV)58%±25%、Dice相似系数(DSC)85%±13%;仅考虑≥6 mm转移瘤时敏感度达99%±5%。MetNet可在对比增强T1加权MRI中以高敏感度、低假阳性和高分割精度分割脑转移瘤,可能辅助SRS治疗计划。

要点

  • MetNet为两阶段深度学习集成模型,用于对比增强T1加权MRI脑转移瘤分割。
  • 转移瘤≥6 mm时患者平均敏感度99%±5%、PPV 67%±28%、DSC 87%±13%。
  • 全部1-52 mm转移瘤患者平均敏感度88%±19%、PPV 58%±25%、DSC 85%±13%。

核心结论

  • MetNet可在对比增强T1加权MRI中对广泛大小范围的脑转移瘤实现高敏感度、低假阳性和高分割精度的分割,可能辅助SRS治疗计划。

研究设计与样本

  • 回顾性分析2009年8月至2018年8月接受SRS的934例患者的对比增强3D T1加权 spoiled gradient echo MRI。
  • 由神经放射学家手动识别脑转移瘤,由治疗放射肿瘤科医生或物理师勾画脑转移瘤。
  • 构建由检测模型和分割模型组成的两阶段深度学习集成模型MetNet,在MRI上分割脑转移瘤。
  • 934例患者(平均年龄59±13岁,474例女性)随机分为80%训练组和20%测试组(748:186)。
  • 通过计算敏感度、阳性预测值(PPV)和Dice相似系数(DSC)评估MetNet性能,并分析无响应受试者工作特征。

主要发现

  • 在转移瘤大小1-52 mm的患者(n=766)中,648例(85%)被检测并分割,平均分割DSC为81%±15%。
  • 患者平均敏感度为88%±19%,PPV为58%±25%,DSC为85%±13%,每例患者假阳性(FP)为3±3。
  • 仅考虑≥6 mm的转移瘤时,患者平均敏感度为99%±5%,PPV为67%±28%,DSC为87%±13%,每例患者FP为1±2。

临床怎么用

  • MetNet可能辅助SRS治疗计划中脑转移瘤的自动分割,减少手动勾画耗时和挑战。

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)。

原文

PURPOSE: Brain metastases are manually contoured during stereotactic radiosurgery (SRS) treatment planning, which is time-consuming, potentially challenging, and laborious. The purpose of this study was to develop and investigate a 2-stage deep learning (DL) approach (MetNet) for brain metastasis segmentation in pre-treatment magnetic resonance imaging (MRI). MATERIALS AND METHODS: We retrospectively analyzed postcontrast 3D T1-weighted spoiled gradient echo MRIs from 934 patients who underwent SRS between August 2009 and August 2018. Neuroradiologists manually identified brain metastases in the MRIs. The treating radiation oncologist or physicist contoured the brain metastases. We constructed a 2-stage DL ensemble consisting of detection and segmentation models to segment the brain metastases on the MRIs. We evaluated the performance of MetNet by computing sensitivity, positive predictive value (PPV), and Dice similarity coefficient (DSC) with respect to metastasis size, as well as free-response receiver operating characteristics. RESULTS: The 934 patients (mean [±standard deviation] age 59 ± 13 years, 474 women) were randomly split into 80% training and 20% testing groups (748:186). For patients with metastases 1-52 mm (n = 766), 648 (85%) were detected and segmented with a mean segmentation DSC of 81% ± 15%. Patient-averaged sensitivity was 88% ± 19%, PPV was 58% ± 25%, and DSC was 85% ± 13% with 3 ± 3 false positives (FPs) per patient. When considering only metastases ≥6 mm, patient-averaged sensitivity was 99% ± 5%, PPV was 67% ± 28%, and DSC was 87% ± 13% with 1 ± 2 FPs per patient. CONCLUSION: MetNet can segment brain metastases across a broad range of metastasis sizes with high sensitivity, low FPs, and high segmentation accuracy in postcontrast T1-weighted MRI, potentially aiding treatment planning for SRS.

来源:Radiother Oncol,查看原文。版权归原作者所有。

引用

  1. Zhou Z, Sanders JW, Johnson JM, et al. MetNet: Computer-aided segmentation of brain metastases in post-contrast T1-weighted magnetic resonance imaging. Radiother Oncol. 2020. PMID: 32937104. doi:10.1016/j.radonc.2020.09.016

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。