文献速递神经MR

基于MRI的两阶段深度学习模型自动检测与分割脑转移瘤

MRI-based two-stage deep learning model for automatic detection and segmentation of brain metastases.
PubMed 文献 · Eur Radiol · 2023-01-25

本研究回顾性纳入649例接受放疗患者的T1和T1ce MRI图像,手动标注5163个转移灶,开发两阶段深度学习模型(轻量分割网络生成候选+多尺度分类网络抑制假阳性),在测试集上达到90%敏感度和56%精确率,对<5mm病灶敏感度66%,分割平均Dice 81%、RVD 20%。

要点

  • 两阶段模型检测脑转移瘤敏感度90%、精确率56%,优于单阶段方法。
  • 对<5mm微小转移灶敏感度66%,显著高于单阶段模型的21%–53%。
  • 分割性能平均Dice 81%、相对体积差20%,体积误差较低。

核心结论

  • 两阶段深度学习模型可高敏感度检测和分割脑转移瘤,且体积误差较低。

研究设计与样本

  • 回顾性研究,纳入2019年8月至2022年1月接受放疗的649例患者,使用T1和T1ce MRI图像。
  • 由神经放射学家手动标注5163个转移灶,随机分为训练集295例、验证集99例、测试集255例。
  • 模型由轻量分割网络生成转移灶候选和多尺度分类网络抑制假阳性组成,参考标准为手动标注。

关键影像表现/征象

  • 原文未涉及具体影像征象描述,仅基于T1和T1ce MRI图像进行检测和分割。

诊断标准与关键数值

  • 测试集检测敏感度90%(1463/1632)、精确率56%(1463/2629)。
  • 对<5mm转移灶敏感度66%(116/177)、精确率22%。
  • 分割性能平均Dice 81%、平均相对体积差(RVD)20%。
  • 对比单阶段方法:单发检测器敏感度78%(1276/1632)、精确率40%(1276/3222);3D U-Net敏感度79%(1290/1632)、精确率51%(1290/2507);nnU-Net敏感度87%(1426/1632)、精确率53%(1426/2688)。
  • 对<5mm病灶,单阶段方法敏感度分别为21%(37/177)、36%(64/177)、53%(93/177)。

临床应用与阅片要点

  • 该模型可辅助放射科医生自动检测和分割脑转移瘤,提高阅片效率。
  • 对<5mm微小转移灶的敏感度仍有限(66%),阅片时需结合人工仔细排查。
  • 精确率56%提示存在假阳性,需人工复核模型输出结果。

局限性

  • 回顾性研究设计。
  • 单中心数据,外部泛化性未验证。
  • 仅纳入接受放疗的患者,可能存在选择偏倚。

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: To develop and validate a two-stage deep learning model for automatic detection and segmentation of brain metastases (BMs) in MRI images.

METHODS: In this retrospective study, T1-weighted (T1) and T1-weighted contrast-enhanced (T1ce) MRI images of 649 patients who underwent radiotherapy from August 2019 to January 2022 were included. A total of 5163 metastases were manually annotated by neuroradiologists. A two-stage deep learning model was developed for automatic detection and segmentation of BMs, which consisted of a lightweight segmentation network for generating metastases proposals and a multi-scale classification network for false-positive suppression. Its performance was evaluated by sensitivity, precision, F1-score, dice, and relative volume difference (RVD).

RESULTS: Six hundred forty-nine patients were randomly divided into training (n = 295), validation (n = 99), and testing (n = 255) sets. The proposed two-stage model achieved a sensitivity of 90% (1463/1632) and a precision of 56% (1463/2629) on the testing set, outperforming one-stage methods based on a single-shot detector, 3D U-Net, and nnU-Net, whose sensitivities were 78% (1276/1632), 79% (1290/1632), and 87% (1426/1632), and the precisions were 40% (1276/3222), 51% (1290/2507), and 53% (1426/2688), respectively. Particularly for BMs smaller than 5 mm, the proposed model achieved a sensitivity of 66% (116/177), far superior to one-stage models (21% (37/177), 36% (64/177), and 53% (93/177)). Furthermore, it also achieved high segmentation performance with an average dice of 81% and an average RVD of 20%.

CONCLUSION: A two-stage deep learning model can detect and segment BMs with high sensitivity and low volume error.

KEY POINTS: • A two-stage deep learning model based on triple-channel MRI images identified brain metastases with 90% sensitivity and 56% precision. • For brain metastases smaller than 5 mm, the proposed two-stage model achieved 66% sensitivity and 22% precision. • For segmentation of brain metastases, the proposed two-stage model achieved a dice of 81% and a relative volume difference (RVD) of 20%.

来源:Eur Radiol,查看原文。版权归原作者所有。

引用

  1. Li, Guo, Zhao, et al. MRI-based two-stage deep learning model for automatic detection and segmentation of brain metastases. Eur Radiol. 2023. PMID: 36695903. doi:10.1007/s00330-023-09420-7

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。