深度学习用于FAST检查质量评估
本研究探讨使用深度学习算法评估创伤重点超声评估(FAST)检查质量的可行性。数据集包含441次FAST检查、共3161段视频,分为高质量或低质量。采用自编码器压缩FAST图像后接两层分类器网络,在留出测试集上视频级敏感度和特异度分别为99%和98%。作者结论认为自编码器压缩FAST图像是获取预测检查质量特征的有效方法,优于在Imagenet上预训练的卷积神经网络特征。
要点
- 自编码器压缩FAST图像后分类,视频级敏感度99%、特异度98%。
- 在Imagenet上预训练的CNN迁移学习效果明显差于自编码器方案。
- 推理时半数帧判为低质量则视频判低质量,半数视频判低质量则检查判低质量。
核心结论
- 使用自编码器压缩FAST图像是获取可用于预测检查质量特征的有效方法,这些特征比在Imagenet上预训练的CNN所获特征更合适。
研究设计与样本
- 研究数据集包含441次FAST检查、共3161段视频,检查被分类为高质量或低质量;采用在Imagenet数据集上预训练并在FAST数据集上微调的卷积神经网络,以及以20:1压缩比压缩FAST图像的自编码器加两层分类器网络,每个视频标注检查质量、每帧标注视频质量。
诊断标准与关键数值
- 推理时若半数帧被网络判为低质量则该视频判为低质量,若半数视频被判为低质量则该检查判为低质量;编码器-分类器网络在留出测试集上的视频敏感度为99%、特异度为98%。
临床应用与阅片要点
- 原文未据此给出临床阅片或报告建议。
局限性
- Imagenet数据集与超声质量评估问题不匹配,导致CNN迁移学习结果明显差于编码器-分类器网络。
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 determine the feasibility of using a deep learning (DL) algorithm to assess the quality of focused assessment with sonography in trauma (FAST) exams.
METHODS: Our dataset consists of 441 FAST exams, classified as good-quality or poor-quality, with 3161 videos. We first used convolutional neural networks (CNNs), pretrained on the Imagenet dataset and fine-tuned on the FAST dataset. Second, we trained a CNN autoencoder to compress FAST images, with a 20-1 compression ratio. The compressed codes were input to a two-layer classifier network. To train the networks, each video was labeled with the quality of the exam, and the frames were labeled with the quality of the video. For inference, a video was classified as poor-quality if half the frames were classified as poor-quality by the network, and an exam was classified as poor-quality if half the videos were classified as poor-quality.
RESULTS: The results with the encoder-classifier networks were much better than the transfer learning results with CNNs. This was primarily because the Imagenet dataset is not a good match for the ultrasound quality assessment problem. The DL models produced video sensitivities and specificities of 99% and 98% on held-out test sets.
CONCLUSIONS: Using an autoencoder to compress FAST images is a very effective way to obtain features that can be used to predict exam quality. These features are more suitable than those obtained from CNNs pretrained on Imagenet.
引用
- Taye, Morrow, Cull, et al. Deep Learning for FAST Quality Assessment. J Ultrasound Med. 2022. PMID: 35770928. doi:10.1002/jum.16045
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。