Limits...
Detecting Lung Diseases from Exhaled Aerosols: Non-Invasive Lung Diagnosis Using Fractal Analysis and SVM Classification.

Xi J, Zhao W, Yuan JE, Kim J, Si X, Xu X - PLoS ONE (2015)

Bottom Line: By employing the 10-fold cross-validation method, we achieved 100% classification accuracy among four asthmatic models using an ideal 108-sample dataset and 99.1% accuracy using a more realistic 324-sample dataset.The fractal-SVM classifier has been shown to be robust, highly sensitive to structural variations, and inherently suitable for investigating aerosol-disease correlations.For the first time, this study quantitatively linked the exhaled aerosol patterns with their underlying diseases and set the stage for the development of a computer-aided diagnostic system for non-invasive detection of obstructive respiratory diseases.

View Article: PubMed Central - PubMed

Affiliation: School of Engineering and Technology, Central Michigan University, Mount Pleasant, Michigan, United States of America.

ABSTRACT

Background: Each lung structure exhales a unique pattern of aerosols, which can be used to detect and monitor lung diseases non-invasively. The challenges are accurately interpreting the exhaled aerosol fingerprints and quantitatively correlating them to the lung diseases.

Objective and methods: In this study, we presented a paradigm of an exhaled aerosol test that addresses the above two challenges and is promising to detect the site and severity of lung diseases. This paradigm consists of two steps: image feature extraction using sub-regional fractal analysis and data classification using a support vector machine (SVM). Numerical experiments were conducted to evaluate the feasibility of the breath test in four asthmatic lung models. A high-fidelity image-CFD approach was employed to compute the exhaled aerosol patterns under different disease conditions.

Findings: By employing the 10-fold cross-validation method, we achieved 100% classification accuracy among four asthmatic models using an ideal 108-sample dataset and 99.1% accuracy using a more realistic 324-sample dataset. The fractal-SVM classifier has been shown to be robust, highly sensitive to structural variations, and inherently suitable for investigating aerosol-disease correlations.

Conclusion: For the first time, this study quantitatively linked the exhaled aerosol patterns with their underlying diseases and set the stage for the development of a computer-aided diagnostic system for non-invasive detection of obstructive respiratory diseases.

No MeSH data available.


Related in: MedlinePlus

Principle component analysis (PCA) of a database containing 324 sample vectors in a 36-dimensional space.Each vector was transformed via PCA into three mutually orthogonal principle components, which was plotted according to different categories: (a) bronchial constriction level, (b) inhalation flow rate, (c) particle size, and (d) upper airway variation. Varying degrees of data clustering exist among the four categories, with the particle sizes showing nearly no separation.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4589383&req=5

pone.0139511.g005: Principle component analysis (PCA) of a database containing 324 sample vectors in a 36-dimensional space.Each vector was transformed via PCA into three mutually orthogonal principle components, which was plotted according to different categories: (a) bronchial constriction level, (b) inhalation flow rate, (c) particle size, and (d) upper airway variation. Varying degrees of data clustering exist among the four categories, with the particle sizes showing nearly no separation.

Mentions: There were two datasets generated via physiological modeling. The first dataset contained 108 samples and represented ideal test conditions with small respiration fluctuations (±10%) and no upper airway variation. The second dataset contained 324 samples and allowed for more realistic scenarios such as large variations in both respirations (±33%) and upper airway geometries (5% oral cavity expansion, and 8% tracheal contraction). Principal component analysis (PCA) was performed to assess the quality of the 324-sample dataset. PCA projected the feature variables (36 in this study) into three mutually orthogonal eigenvectors (PC1, PC2, and PC3), and thus reduced the number of feature variables for better visual inspection (Fig 5). In other words, PCA reduced 36 dimensions into 3 dimensions that better present the data variance. Varying degrees of clustering were noted among the four categories. The most apparent data separation was observed in flow rate (Q = 20, 30, 40 L/min), followed by the airway constriction level (D0–3) and upper airway variation (Fig 5A, 5B and 5D). Considering the effects of upper airway variations, oral expansions were found to separate themselves more clearly from the control cases than tracheal contractions (Fig 5D). No clear separation was noted when varying the particle size (Fig 5C).


Detecting Lung Diseases from Exhaled Aerosols: Non-Invasive Lung Diagnosis Using Fractal Analysis and SVM Classification.

Xi J, Zhao W, Yuan JE, Kim J, Si X, Xu X - PLoS ONE (2015)

Principle component analysis (PCA) of a database containing 324 sample vectors in a 36-dimensional space.Each vector was transformed via PCA into three mutually orthogonal principle components, which was plotted according to different categories: (a) bronchial constriction level, (b) inhalation flow rate, (c) particle size, and (d) upper airway variation. Varying degrees of data clustering exist among the four categories, with the particle sizes showing nearly no separation.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4589383&req=5

pone.0139511.g005: Principle component analysis (PCA) of a database containing 324 sample vectors in a 36-dimensional space.Each vector was transformed via PCA into three mutually orthogonal principle components, which was plotted according to different categories: (a) bronchial constriction level, (b) inhalation flow rate, (c) particle size, and (d) upper airway variation. Varying degrees of data clustering exist among the four categories, with the particle sizes showing nearly no separation.
Mentions: There were two datasets generated via physiological modeling. The first dataset contained 108 samples and represented ideal test conditions with small respiration fluctuations (±10%) and no upper airway variation. The second dataset contained 324 samples and allowed for more realistic scenarios such as large variations in both respirations (±33%) and upper airway geometries (5% oral cavity expansion, and 8% tracheal contraction). Principal component analysis (PCA) was performed to assess the quality of the 324-sample dataset. PCA projected the feature variables (36 in this study) into three mutually orthogonal eigenvectors (PC1, PC2, and PC3), and thus reduced the number of feature variables for better visual inspection (Fig 5). In other words, PCA reduced 36 dimensions into 3 dimensions that better present the data variance. Varying degrees of clustering were noted among the four categories. The most apparent data separation was observed in flow rate (Q = 20, 30, 40 L/min), followed by the airway constriction level (D0–3) and upper airway variation (Fig 5A, 5B and 5D). Considering the effects of upper airway variations, oral expansions were found to separate themselves more clearly from the control cases than tracheal contractions (Fig 5D). No clear separation was noted when varying the particle size (Fig 5C).

Bottom Line: By employing the 10-fold cross-validation method, we achieved 100% classification accuracy among four asthmatic models using an ideal 108-sample dataset and 99.1% accuracy using a more realistic 324-sample dataset.The fractal-SVM classifier has been shown to be robust, highly sensitive to structural variations, and inherently suitable for investigating aerosol-disease correlations.For the first time, this study quantitatively linked the exhaled aerosol patterns with their underlying diseases and set the stage for the development of a computer-aided diagnostic system for non-invasive detection of obstructive respiratory diseases.

View Article: PubMed Central - PubMed

Affiliation: School of Engineering and Technology, Central Michigan University, Mount Pleasant, Michigan, United States of America.

ABSTRACT

Background: Each lung structure exhales a unique pattern of aerosols, which can be used to detect and monitor lung diseases non-invasively. The challenges are accurately interpreting the exhaled aerosol fingerprints and quantitatively correlating them to the lung diseases.

Objective and methods: In this study, we presented a paradigm of an exhaled aerosol test that addresses the above two challenges and is promising to detect the site and severity of lung diseases. This paradigm consists of two steps: image feature extraction using sub-regional fractal analysis and data classification using a support vector machine (SVM). Numerical experiments were conducted to evaluate the feasibility of the breath test in four asthmatic lung models. A high-fidelity image-CFD approach was employed to compute the exhaled aerosol patterns under different disease conditions.

Findings: By employing the 10-fold cross-validation method, we achieved 100% classification accuracy among four asthmatic models using an ideal 108-sample dataset and 99.1% accuracy using a more realistic 324-sample dataset. The fractal-SVM classifier has been shown to be robust, highly sensitive to structural variations, and inherently suitable for investigating aerosol-disease correlations.

Conclusion: For the first time, this study quantitatively linked the exhaled aerosol patterns with their underlying diseases and set the stage for the development of a computer-aided diagnostic system for non-invasive detection of obstructive respiratory diseases.

No MeSH data available.


Related in: MedlinePlus