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

Numerically predicted expiratory flows for the four asthmatic models with varying airway constriction levels.(a) Streamlines, (b) cross-sectional velocity contours, and (c) horizontal velocity profiles.
© Copyright Policy
Related In: Results  -  Collection

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

pone.0139511.g002: Numerically predicted expiratory flows for the four asthmatic models with varying airway constriction levels.(a) Streamlines, (b) cross-sectional velocity contours, and (c) horizontal velocity profiles.

Mentions: The predicted expiratory airflows among the four asthmatic cases are compared in Fig 2 in the form of streamlines, cross-sectional contours, and 2-D velocity plots. The asthmatic airway constriction noticeably distorts the streamlines and airflow field (Fig 2A and 2B). In contrast to the two peaks in the velocity contour at Slice 1–1’ for the normal case (D0-1 in Fig 2B), one of the peaks diminishes with increasing constriction level and becomes invisible for D2 and D3. At the same time, a low-speed zone forms near the bifurcation ridge that is next to the constricted bronchioles, which is most obvious in D3 (D3-1 in Fig 2B). These flow disturbances will be conveyed further downstream by the expiratory flow. Due to reduced flow areas from asthmatic constrictions, higher flow resistances are expected; under the same breathing efforts, the respiratory flow rate will be lower. The airway loss prevents aerosols from being inhaled and exhaled smoothly and is expected to noticeably alter the exhaled aerosol profiles. Fig 2C shows the velocity profiles at Slice 1–1’ among the four models in two different directions (a-a’ and b-b’). As expected, flow velocity progressively decreases as the airway constriction level increases. The differences in airflows diminish progressively towards the mouth. It is noted that particle profiles depend on both local flows and particle histories. Although the downstream airflows may appear similar, the particle profiles can still be different because of their time-integrative natures.


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)

Numerically predicted expiratory flows for the four asthmatic models with varying airway constriction levels.(a) Streamlines, (b) cross-sectional velocity contours, and (c) horizontal velocity profiles.
© Copyright Policy
Related In: Results  -  Collection

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

pone.0139511.g002: Numerically predicted expiratory flows for the four asthmatic models with varying airway constriction levels.(a) Streamlines, (b) cross-sectional velocity contours, and (c) horizontal velocity profiles.
Mentions: The predicted expiratory airflows among the four asthmatic cases are compared in Fig 2 in the form of streamlines, cross-sectional contours, and 2-D velocity plots. The asthmatic airway constriction noticeably distorts the streamlines and airflow field (Fig 2A and 2B). In contrast to the two peaks in the velocity contour at Slice 1–1’ for the normal case (D0-1 in Fig 2B), one of the peaks diminishes with increasing constriction level and becomes invisible for D2 and D3. At the same time, a low-speed zone forms near the bifurcation ridge that is next to the constricted bronchioles, which is most obvious in D3 (D3-1 in Fig 2B). These flow disturbances will be conveyed further downstream by the expiratory flow. Due to reduced flow areas from asthmatic constrictions, higher flow resistances are expected; under the same breathing efforts, the respiratory flow rate will be lower. The airway loss prevents aerosols from being inhaled and exhaled smoothly and is expected to noticeably alter the exhaled aerosol profiles. Fig 2C shows the velocity profiles at Slice 1–1’ among the four models in two different directions (a-a’ and b-b’). As expected, flow velocity progressively decreases as the airway constriction level increases. The differences in airflows diminish progressively towards the mouth. It is noted that particle profiles depend on both local flows and particle histories. Although the downstream airflows may appear similar, the particle profiles can still be different because of their time-integrative natures.

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