A semi-supervised autoencoder framework for joint generation and classification of breathing. (September 2021)

• Record Type: Journal Article
• Authors: Pastor-Serrano, Oscar; Lathouwers, Danny; Perkó, Zoltán
• Is Part Of: Computer methods and programs in biomedicine. Volume 209(2021)
• Publication Date: 2021-09
• Subjects: Deep learning -- Respiratory motion -- Breathing signals -- Convolutional neural network -- Probabilistic autoencoder -- Semi-supervised learning; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2021.106312
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: Models of breathing motion using 1D convolutional neural networks and probabilistic autoencoders. A novel semi-supervised algorithm based on Adversarial Autoencoders that allows joint classification and generation of breathing. The models are trained with 4% and 12% of the labeled data and achieve a macro F1-score of 94.91% and 96.54% in a different test set. A pre-processing step compresses 3-dimensional breathing time series into vectors. Abstract: Background and objective: 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. Methods: 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. Results: 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. Conclusion: 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.