文献速递心血管MR

卷积神经网络用于重型地中海贫血患者心肌铁过载的自动MR分类

Convolutional neural networks for automatic MR classification of myocardial iron overload in thalassemia major patients.
PubMed 文献 · Eur Radiol · 2024-12-10

本研究基于496例重型地中海贫血患者的823幅心脏T2*多回波MR图像,训练两种2D卷积神经网络(多层面MS-HippoNet与单层面SS-HippoNet)对心肌铁过载进行三级分类,测试集多分类准确率分别为0.885与0.836,外部测试集为0.827与0.793,自动分类与金标准的一致性(MS:κ=0.771;SS:κ=0.614)与观察者间一致性(MS:κ=0.872,SS:κ=0.907)相当。

要点

  • MS-HippoNet在测试集多分类准确率0.885,SS-HippoNet为0.836。
  • 外部测试集多分类准确率MS为0.827、SS为0.793(29例来自CHMMOTv1数据库)。
  • 自动分类与金标准一致性MS的κ=0.771、SS的κ=0.614,与观察者间一致性相当。

核心结论

  • 所开发的网络能从多回波亮血T2*图像对心肌铁过载水平进行分类,表现良好。

研究设计与样本

  • 回顾性研究,纳入496例重型地中海贫血患者(285例女性,57%)的823幅心脏T2*多层面多回波MR图像,按心肌铁过载水平标注(正常:T2*>20 ms,中度:10≤T2*≤20 ms,重度:T2*<10 ms),采用5折交叉验证训练多层面MS-HippoNet与单层面SS-HippoNet两种2D卷积神经网络。

诊断标准与关键数值

  • 心肌铁过载分级标准:正常为T2*>20 ms,中度为10≤T2*≤20 ms,重度为T2*<10 ms。

临床应用与阅片要点

  • 作者认为卷积神经网络可基于多回波MR序列对心脏铁过载进行自动分级,促进血液系统疾病患者的无创评估。

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 a deep-learning model for supervised classification of myocardial iron overload (MIO) from magnitude T2* multi-echo MR images.

MATERIALS AND METHODS: Eight hundred twenty-three cardiac magnitude T2* multi-slice, multi-echo MR images from 496 thalassemia major patients (285 females, 57%), labeled for MIO level (normal: T2* > 20 ms, moderate: 10 ≤ T2* ≤ 20 ms, severe: T2* < 10 ms), were retrospectively studied. Two 2D convolutional neural networks (CNN) developed for multi-slice (MS-HippoNet) and single-slice (SS-HippoNet) analysis were trained using 5-fold cross-validation. Performance was assessed using micro-average, multi-class accuracy, and single-class accuracy, sensitivity, and specificity. CNN performance was compared with inter-observer agreement between radiologists on 20% of the patients. The agreement between patients' classifications was assessed by the inter-agreement Kappa test.

RESULTS: Among the 165 images in the test set, a multi-class accuracy of 0.885 and 0.836 was obtained for MS- and SS-Hippo-Net, respectively. Network performances were confirmed on external test set analysis (0.827 and 0.793 multi-class accuracy, 29 patients from the CHMMOTv1 database). The agreement between automatic and ground truth classification was good (MS: κ = 0.771; SS: κ = 0.614), comparable with the inter-observer agreement (MS: κ = 0.872, SS: κ = 0.907) evaluated on the test set.

CONCLUSION: The developed networks performed classification of MIO level from multiecho, bright-blood, and T2* images with good performances.

KEY POINTS: Question MRI T2* represents the established clinical tool for MIO assessment. Quality control of the image analysis is a problem in small centers. Findings Deep learning models can perform MIO staging with good accuracy, comparable to inter-observer variability of the standard procedure. Clinical relevance CNN can perform automated staging of cardiac iron overload from multiecho MR sequences facilitating non-invasive evaluation of patients with various hematologic disorders.

来源:Eur Radiol,查看原文。版权归原作者所有。

引用

  1. Positano V, Meloni A, De Santi LA, et al. Convolutional neural networks for automatic MR classification of myocardial iron overload in thalassemia major patients. Eur Radiol. 2024. PMID: 39658686. doi:10.1007/s00330-024-11245-x

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。