Virtual Library
Start Your Search
X.A. Si
Author of
-
+
P2.06 - Poster Session/ Screening and Early Detection (ID 219)
- Event: WCLC 2015
- Type: Poster
- Track: Screening and Early Detection
- Presentations: 1
- Moderators:
- Coordinates: 9/08/2015, 09:30 - 17:00, Exhibit Hall (Hall B+C)
-
+
P2.06-015 - Detecting Obstructive Lung Diseases with Aerosol Breath Test: A Non-Invasive Diagnostic Method Using Fractal Analysis and SVM Classification (ID 1548)
09:30 - 09:30 | Author(s): X.A. Si
- Abstract
Background:
Each lung structure has a unique pattern of exhaled aerosols (aerosol fingerprint), whose deviation from the normal pattern may indicate an anomaly inside the airway. Therefore, an exhaled aerosol test can be used to detect and monitor lung diseases non-invasively. The key challenge is accurately interpreting the exhaled aerosol fingerprints and quantitatively correlating them to lung diseases.
Methods:
In this study, a novel integrated algorithm was developed to evaluate the feasibility of the exhaled aerosol tests. This algorithm has four steps: data generation via physiology-based modeling, image feature extraction using sub-regional fractal analysis, data classification using a support vector machine (SVM), and data quality assessment using principle component analysis.
Results:
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 links the exhaled aerosol patterns with their underlying diseases and sets the stage for the development of a computer-aided diagnostic system for non-invasive detection of obstructive respiratory diseases. The proposed aerosol breath test is especially suitable for the use of screening to detect lung tumors at early stages, and to monitor tumor growth or therapeutic outcome of medical interventions.
