Conditional GAN based augmentation for predictive modeling of respiratory signals

• Published in: Computers in biology and medicine 2021-11, Vol.138, p.104930-104930, Article 104930
• Main Authors: Jayalakshmy, S., Sudha, Gnanou Florence
• Format: Article
• Language: English
• Subjects: Accuracy; Acoustics; Algorithms; Artificial intelligence; Auscultation; Chronic obstructive pulmonary disease; Classification; Conditional generative adversarial networks; Coronaviruses; Correlation metrics; COVID-19; Data augmentation; Datasets; Deep convolutional neural networks; Deep learning; Diagnosis; Electrocardiography; Generative adversarial networks; Life span; Lung diseases; Machine learning; Methods; Neural networks; Pandemics; Patients; Physiology; Prediction models; Respiration; Respiratory diseases; Respiratory signals; Signal classification; Signal generation; Signal processing; Sound; Spirometry
• ISSN: 0010-4825; 1879-0534
• DOI: 10.1016/j.compbiomed.2021.104930

Respiratory illness is the primary cause of mortality and impairment in the life span of an individual in the current COVID–19 pandemic scenario. The inability to inhale and exhale is one of the difficult conditions for a person suffering from respiratory disorders. Unfortunately, the diagnosis of respiratory disorders with the presently available imaging and auditory screening modalities are sub-optimal and the accuracy of diagnosis varies with different medical experts. At present, deep neural nets demand a massive amount of data suitable for precise models. In reality, the respiratory data set is quite limited, and therefore, data augmentation (DA) is employed to enlarge the data set. In this study, conditional generative adversarial networks (cGAN) based DA is utilized for synthetic generation of signals. The publicly available repository such as ICBHI 2017 challenge, RALE and Think Labs Lung Sounds Library are considered for classifying the respiratory signals. To assess the efficacy of the artificially created signals by the DA approach, similarity measures are calculated between original and augmented signals. After that, to quantify the performance of augmentation in classification, scalogram representation of generated signals are fed as input to different pre-trained deep learning architectures viz Alexnet, GoogLeNet and ResNet-50. The experimental results are computed and performance results are compared with existing classical approaches of augmentation. The research findings conclude that the proposed cGAN method of augmentation provides better accuracy of 92.50% and 92.68%, respectively for both the two data sets using ResNet 50 model. •Conditional GAN based Data Augmentation approach is employed and examined for predictive modeling of respiratory signals.•Similarity and Coherence between original and augmented signals are assessed using linear and non-linear metrics.•Augmented signals in the form of scalogram images are classified using Alexnet, GoogLenet and ResNet- 50.•Enhancement in accuracy compared to existing approaches without and with augmentation is achieved.