Correlating exhaled aerosol images to small airway obstructive diseases: A study with dynamic mode decomposition and machine learning

• Published in: PloS one 2019-01, Vol.14 (1), p.e0211413-e0211413
• Main Authors: Xi, Jinxiang, Zhao, Weizhong
• Format: Article
• Language: English
• Subjects: Aerosols; Aerosols - analysis; Airway obstruction; Algorithms; Analysis; Artificial intelligence; Asthma; Bioinformatics; Biology and Life Sciences; Breath Tests; Chronic obstructive pulmonary disease; Classification; Computer and Information Sciences; Computer simulation; Decomposition; Diseases; Exhalation; Explicit knowledge; Feature extraction; Fractals; Gene expression; Health aspects; Humans; Image Processing, Computer-Assisted - methods; Learning algorithms; Lung diseases; Lung Diseases, Obstructive - diagnosis; Lung Diseases, Obstructive - diagnostic imaging; Lungs; Machine Learning; Male; Medical imaging; Medical research; Medicine and Health Sciences; Middle Aged; Neural networks; Obstructive lung disease; Physical Sciences; Physiology; Principal Component Analysis; Principal components analysis; Prognosis; Proper Orthogonal Decomposition; Research and Analysis Methods; Respiration; Respiratory tract diseases; Risk factors; Studies; Support Vector Machine; Support vector machines; Tomography, X-Ray Computed - methods; Turbulence models
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0211413

Exhaled aerosols from lungs have unique patterns, and their variation can be correlated to the underlying lung structure and associated abnormities. However, it is challenging to characterize such aerosol patterns and differentiate their difference because of their complexity. This challenge is even greater for small airway diseases, where the disturbance signals are weak. The objective of this study is exploiting different feature extraction algorithms to develop a practical classifier to diagnose obstructive lung diseases using exhaled aerosol images. These include proper orthogonal decomposition (POD), principal component analysis (PCA), dynamic mode decomposition (DMD), and DMD with control (DMDC). Aerosol images were generated via physiology-based simulations in one normal and four diseased airway models in G7-9 bronchioles. The image data were classified using both the support vector machine (SVM) and random forest (RF) algorithms. The effectiveness of different features was evaluated by classification accuracy and misclassification rate. Results show a significantly higher performance using dynamic feature extractions (DMD and DMDC) than static algorithms (POD and PCA). Adding the control variables to DMD further improved classification accuracy. Comparing the classification methods, RF persistently outperformed SVM for all types of features considered. While the performance of RF constantly increased with the number of features retained, the performance of SVM peaked at 50 and decreased thereafter. The 5-class classification accuracy was 94.8% using the DMDC-RF model and 93.0% using the DMD-RF model, both of which were higher than 87.0% in the previous study that used fractal dimension features. Considering that disease progression is inherently a dynamic process, DMD(C)-based feature extraction preserves temporal information and is preferred over POD and PCA. Compared with hand-crafted features like fractals, feature extraction by DMD and DMDC is automatic and more accurate.