Delft University of Technology, Department of Radiation Science and Technology, Mekelweg 15, Delft 2629JB, Netherlands.
Delft University of Technology, Department of Radiation Science and Technology, Mekelweg 15, Delft 2629JB, Netherlands.
Comput Methods Programs Biomed. 2021 Sep;209:106312. doi: 10.1016/j.cmpb.2021.106312. Epub 2021 Jul 31.
One of the main problems with biomedical signals is the limited amount of patient-specific data and the significant amount of time needed to record the sufficient number of samples needed for diagnostic and treatment purposes. In this study, we present a framework to simultaneously generate and classify biomedical time series based on a modified Adversarial Autoencoder (AAE) algorithm and one-dimensional convolutions. Our work is based on breathing time series, with specific motivation to capture breathing motion during radiotherapy lung cancer treatments.
First, we explore the potential in using the Variational Autoencoder (VAE) and AAE algorithms to model breathing signals from individual patients. We then extend the AAE algorithm to allow joint semi-supervised classification and generation of different types of signals within a single framework. To simplify the modeling task, we introduce a pre-processing and post-processing compressing algorithm that transforms the multi-dimensional time series into vectors containing time and position values, which are transformed back into time series through an additional neural network.
The resulting models are able to generate realistic and varied samples of breathing. By incorporating 4% and 12% of the labeled samples during training, our model outperforms other purely discriminative networks in classifying breathing baseline shift irregularities from a dataset completely different from the training set, achieving an average macro F1-score of 94.91% and 96.54%, respectively.
To our knowledge, the presented framework is the first approach that unifies generation and classification within a single model for this type of biomedical data, enabling both computer aided diagnosis and augmentation of labeled samples within a single framework.
生物医学信号的主要问题之一是患者特定数据的数量有限，并且为了诊断和治疗目的记录足够数量的样本需要大量时间。在这项研究中，我们提出了一个基于改进的对抗自动编码器（AAE）算法和一维卷积的同时生成和分类生物医学时间序列的框架。我们的工作基于呼吸时间序列，具体动机是在放射治疗肺癌治疗过程中捕获呼吸运动。
首先，我们探索了使用变分自动编码器（VAE）和 AAE 算法来对来自个体患者的呼吸信号进行建模的潜力。然后，我们将 AAE 算法扩展到允许在单个框架内联合半监督分类和生成不同类型的信号。为了简化建模任务，我们引入了预处理和后处理压缩算法，将多维时间序列转换为包含时间和位置值的向量，通过附加的神经网络将其转换回时间序列。
所得到的模型能够生成逼真且多样化的呼吸样本。通过在训练过程中纳入 4%和 12%的标记样本，我们的模型在对与训练集完全不同的数据集进行分类时，表现优于其他纯粹的判别网络，分别实现了平均宏观 F1 分数为 94.91%和 96.54%。
据我们所知，所提出的框架是第一种在单个模型中统一生成和分类的方法，用于这种类型的生物医学数据，能够在单个框架内实现计算机辅助诊断和标记样本的扩充。
