Abstract
Background/purpose
Optical and parametric skin imaging methods which can efficiently identify invisible sub‐skin features or subtle changes in skin layers are very important for accurate optical skin modelling. In this study, a hybrid method is introduced that helps develop a parametric optical skin model by utilizing interdisciplinary techniques including light back‐scatter analysis, laser speckle imaging, image‐texture analysis and Bayesian inference methods. The model aims to detect subtle skin changes and hence very early signs of skin abnormalities/diseases.
Methods
Light back‐scatter and laser speckle image textural analysis are applied onto the normal and abnormal skin regions (lesions) to generate set of attributes/parameters. These are then optimized by Bayesian inference method in order to build an optimized parametric model.
Results
The attributes selected by Bayesian inference method in the optimization stage were used to build an optimized model and then successfully verified. It was clearly proven that Bayesian inference based optimization process yields good results to build an optimized skin model.
Conclusion
The outcome of this study clearly shows the applicability of this hybrid method in the analysis of skin features and is therefore expected to lead development of non‐invasive and low‐cost instrument for early detection of skin changes.
Optical and parametric skin imaging methods which can efficiently identify invisible sub‐skin features or subtle changes in skin layers are very important for accurate optical skin modelling. In this study, a hybrid method is introduced that helps develop a parametric optical skin model by utilizing interdisciplinary techniques including light back‐scatter analysis, laser speckle imaging, image‐texture analysis and Bayesian inference methods. The model aims to detect subtle skin changes and hence very early signs of skin abnormalities/diseases.
Methods
Light back‐scatter and laser speckle image textural analysis are applied onto the normal and abnormal skin regions (lesions) to generate set of attributes/parameters. These are then optimized by Bayesian inference method in order to build an optimized parametric model.
Results
The attributes selected by Bayesian inference method in the optimization stage were used to build an optimized model and then successfully verified. It was clearly proven that Bayesian inference based optimization process yields good results to build an optimized skin model.
Conclusion
The outcome of this study clearly shows the applicability of this hybrid method in the analysis of skin features and is therefore expected to lead development of non‐invasive and low‐cost instrument for early detection of skin changes.
Original language | English |
---|---|
Pages (from-to) | 473-485 |
Journal | Skin Research and Technology |
Volume | 20 |
Issue number | 4 |
Early online date | 24 Mar 2014 |
DOIs | |
Publication status | Published - Nov 2014 |
Externally published | Yes |