文献速递心血管技术与安全US

所有深度学习架构在床旁超声中表现相同吗:来自心脏图像分类模型的证据提示并非如此

Are All Deep Learning Architectures Alike for Point-of-Care Ultrasound?: Evidence From a Cardiac Image Classification Model Suggests Otherwise.
PubMed 文献 · J Ultrasound Med · 2019-12-24

该研究比较了6种常用深度学习架构在床旁超声心脏图像分类中的表现,使用225个公开去标识化床旁超声心脏视频提取的750,018张图像训练,并在125张全新图像上测试。结果显示准确率从96%到85.6%不等,最老旧简单的VGG-16表现最佳(96%正确,训练232分钟),最新的DenseNet201表现最差(85.6%准确,训练429分钟),提示并非所有架构在床旁超声深度学习应用中都能最优表现,更现代更深的算法反而结果更差。

要点

  • 6种卷积神经网络在床旁超声心脏图像分类中准确率范围为96%至85.6%,训练时间差异明显。
  • VGG-16表现最佳:96%正确,训练232分钟(R=0.97;κ=0.95;P<.00001)。
  • DenseNet201表现最差:85.6%准确,训练429分钟(R=0.92;κ=0.82;P<.00001)。

诊断标准与关键数值

  • 6种卷积神经网络准确率范围为96%至85.6%正确。
  • VGG-16表现最佳:96%正确,训练232分钟(R=0.97;κ=0.95;P<.00001)。
  • DenseNet201表现最差:85.6%准确,训练429分钟(R=0.92;κ=0.82;P<.00001)。

局限性

  • 原文未报告局限性。

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: Little is known about optimal deep learning (DL) approaches for point-of-care ultrasound (POCUS) applications. We compared 6 popular DL architectures for POCUS cardiac image classification to determine whether an optimal DL architecture exists for future DL algorithm development in POCUS.

METHODS: We trained 6 convolutional neural networks (CNNs) with a range of complexities and ages (AlexNet, VGG-16, VGG-19, ResNet50, DenseNet201, and Inception-v4). Each CNN was trained by using images of 5 typical POCUS cardiac views. Images were extracted from 225 publicly available deidentified POCUS cardiac videos. A total of 750,018 individual images were extracted, with 90% used for model training and 10% for cross-validation. The training time and accuracy achieved were tracked. A real-world test of the algorithms was performed on a set of 125 completely new cardiac images. Descriptive statistics, Pearson R values, and κ values were calculated for each CNN.

RESULTS: Accuracy ranged from 96% to 85.6% correct for the 6 CNNs. VGG-16, one of the oldest and simplest CNNs, performed best at 96% correct with 232 minutes to train (R = 0.97; κ = 0.95; P < .00001). The worst-performing CNN was the newer DenseNet201, with 85.6% accuracy and 429 minutes to train (R = 0.92; κ = 0.82; P < .00001).

CONCLUSIONS: Six common image classification DL algorithms showed considerable variability in their accuracy and training time when trained and tested on identical data, suggesting that not all will perform optimally for POCUS DL applications. Contrary to well-established accuracies for CNNs, more modern and deeper algorithms yielded poorer results.

来源:J Ultrasound Med,查看原文。版权归原作者所有。

引用

  1. Blaivas M, Blaivas L. Are All Deep Learning Architectures Alike for Point-of-Care Ultrasound?: Evidence From a Cardiac Image Classification Model Suggests Otherwise. J Ultrasound Med. 2019. PMID: 31872477. doi:10.1002/jum.15206

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。