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

Asthmatic models (a), upper airway variation (b), and flow chart (c) of the proposed method methodology.The airway constriction level in the asthmatic models ranges from 0% (D0) to 75% (D3). The shape variations represent the potential uncertainties in the upper airway during breath tests. There is 5% oral expansion and 8% tracheal contraction relative to the control cases. Physiology-based modeling was undertaken to generate exhaled aerosol images; the images were characterized using fractal analysis to extract salient features; a SVM classifier was trained with extracted feature vectors and tested with extra samples. CFD: computational fluid dynamics; SVM: support vector machines.
© Copyright Policy
Related In: Results  -  Collection

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

pone.0139511.g001: Asthmatic models (a), upper airway variation (b), and flow chart (c) of the proposed method methodology.The airway constriction level in the asthmatic models ranges from 0% (D0) to 75% (D3). The shape variations represent the potential uncertainties in the upper airway during breath tests. There is 5% oral expansion and 8% tracheal contraction relative to the control cases. Physiology-based modeling was undertaken to generate exhaled aerosol images; the images were characterized using fractal analysis to extract salient features; a SVM classifier was trained with extracted feature vectors and tested with extra samples. CFD: computational fluid dynamics; SVM: support vector machines.

Mentions: This study will aim to address the remaining three questions, namely how to link exhaled aerosol patterns to internal lung diseases? Is the new method accurate? Is it robust? To this aim, we will introduce an image-CFD-fractal-SVM model and evaluate the feasibility of the proposed exhaled aerosol test using this model. This new model includes four steps: sample acquisition, fractal feature extraction, database quality evaluation, and SVM classification (flow chart in Fig 1). The performance of the proposed model will be assessed in four asthmatic models (Fig 1) using two datasets that represent ideal and more realistic testing conditions (Table 1). Specific aims of this study include: (1) database development of aerosol samples to train and test the classification model, (2) fractal feature extraction to quantitatively describe exhaled aerosol images, (3) SVM classification to correlate exhaled aerosol features to the asthmatic grade, and (4) analysis of data quality (before test) and misdiagnosed samples (after test) to minimize misclassifications. This new model will set the stage for developing a non-invasive, computer-aided diagnostic system that is capable of rapid detection and location of asthmatic bronchitis using exhaled aerosol tests.


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)

Asthmatic models (a), upper airway variation (b), and flow chart (c) of the proposed method methodology.The airway constriction level in the asthmatic models ranges from 0% (D0) to 75% (D3). The shape variations represent the potential uncertainties in the upper airway during breath tests. There is 5% oral expansion and 8% tracheal contraction relative to the control cases. Physiology-based modeling was undertaken to generate exhaled aerosol images; the images were characterized using fractal analysis to extract salient features; a SVM classifier was trained with extracted feature vectors and tested with extra samples. CFD: computational fluid dynamics; SVM: support vector machines.
© Copyright Policy
Related In: Results  -  Collection

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

pone.0139511.g001: Asthmatic models (a), upper airway variation (b), and flow chart (c) of the proposed method methodology.The airway constriction level in the asthmatic models ranges from 0% (D0) to 75% (D3). The shape variations represent the potential uncertainties in the upper airway during breath tests. There is 5% oral expansion and 8% tracheal contraction relative to the control cases. Physiology-based modeling was undertaken to generate exhaled aerosol images; the images were characterized using fractal analysis to extract salient features; a SVM classifier was trained with extracted feature vectors and tested with extra samples. CFD: computational fluid dynamics; SVM: support vector machines.
Mentions: This study will aim to address the remaining three questions, namely how to link exhaled aerosol patterns to internal lung diseases? Is the new method accurate? Is it robust? To this aim, we will introduce an image-CFD-fractal-SVM model and evaluate the feasibility of the proposed exhaled aerosol test using this model. This new model includes four steps: sample acquisition, fractal feature extraction, database quality evaluation, and SVM classification (flow chart in Fig 1). The performance of the proposed model will be assessed in four asthmatic models (Fig 1) using two datasets that represent ideal and more realistic testing conditions (Table 1). Specific aims of this study include: (1) database development of aerosol samples to train and test the classification model, (2) fractal feature extraction to quantitatively describe exhaled aerosol images, (3) SVM classification to correlate exhaled aerosol features to the asthmatic grade, and (4) analysis of data quality (before test) and misdiagnosed samples (after test) to minimize misclassifications. This new model will set the stage for developing a non-invasive, computer-aided diagnostic system that is capable of rapid detection and location of asthmatic bronchitis using exhaled aerosol tests.

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