Detection of COVID-19 features in lung ultrasound images using deep neural networks.
Detection of COVID-19 features in lung ultrasound images using deep neural networks.
复制标题
使用深度神经网络检测肺部超声图像中的 COVID-19 特征。
DOI：
10.1038/s43856-024-00463-5
复制
发表时间：
2024
期刊：
影响因子：
--
通讯作者：
Bell,MuyinatuALediju
中科院分区：
文献类型：
--
作者：
Zhao,Lingyi;Fong,TiffanyClair;Bell,MuyinatuALediju
用于检测肺部超声B模式图像中COVID-19特征的深度神经网络（DNN）主要依赖于体内或模拟图像作为训练数据。然而，体内图像受到对数千个训练图像示例的所需手动标记的有限访问的影响，并且由于域差异，模拟图像可能受到体内图像的较差概括性的影响。我们解决了这些局限性，并确定最佳的训练strategy.MethodsWe研究了体内COVID-19特征检测与DNN训练我们仔细模拟的数据集（40，000图像），公开的体内数据集（174图像），体内数据集由我们的团队策划（958图像），以及模拟和内部或外部的体内数据集的组合。在COVID-19患者的体内B模式图像上测试了七种DNN训练策略。ResultsHere，我们表明，当模拟数据与外部体内数据混合并在内部体内数据（即，0.482 ± 0.211），与仅使用模拟的B模式图像训练数据（即，0.464 ± 0.230）或仅外部体内B模式训练数据（即，0.407 ± 0.177）。当内部体内B模式图像的单独子集被包括在训练数据集中时，实现了额外的最大化，其中在训练期间将模拟数据与内部和外部体内数据混合之后获得DSC的最大化（以及所需训练时间或时期的最小化），然后在内部体内数据集的保留子集上进行测试（即，结论当分割体内COVID-19肺部超声特征时，用模拟和体内数据训练的DNN是仅用真实的或仅用模拟数据训练的有希望的替代方案。
BackgroundDeep neural networks (DNNs) to detect COVID-19 features in lung ultrasound B-mode images have primarily relied on either in vivo or simulated images as training data. However, in vivo images suffer from limited access to required manual labeling of thousands of training image examples, and simulated images can suffer from poor generalizability to in vivo images due to domain differences. We address these limitations and identify the best training strategy.MethodsWe investigated in vivo COVID-19 feature detection with DNNs trained on our carefully simulated datasets (40,000 images), publicly available in vivo datasets (174 images), in vivo datasets curated by our team (958 images), and a combination of simulated and internal or external in vivo datasets. Seven DNN training strategies were tested on in vivo B-mode images from COVID-19 patients.ResultsHere, we show that Dice similarity coefficients (DSCs) between ground truth and DNN predictions are maximized when simulated data are mixed with external in vivo data and tested on internal in vivo data (i.e., 0.482 ± 0.211), compared with using only simulated B-mode image training data (i.e., 0.464 ± 0.230) or only external in vivo B-mode training data (i.e., 0.407 ± 0.177). Additional maximization is achieved when a separate subset of the internal in vivo B-mode images are included in the training dataset, with the greatest maximization of DSC (and minimization of required training time, or epochs) obtained after mixing simulated data with internal and external in vivo data during training, then testing on the held-out subset of the internal in vivo dataset (i.e., 0.735 ± 0.187).ConclusionsDNNs trained with simulated and in vivo data are promising alternatives to training with only real or only simulated data when segmenting in vivo COVID-19 lung ultrasound features.
使用基于胸部放射图像的深度学习开发用于早期检测 COVID-19 的临床决策支持系统
DOI：
10.1109/iscv49265.2020.9204282
发表时间：
2020
期刊：
2020 International Conference on Intelligent Systems and Computer Vision (ISCV)
影响因子：
--
作者：
M. Qjidaa;A. Ben;Y. Mechbal;H. Amakdouf;M. Maaroufi;B. Alami;H. Qjidaa
通讯作者：
H. Qjidaa