Multiregional Segmentation Modeling in Medical Ultrasonography: Extraction, Modeling and Quantification of Skin Layers and Hypertrophic Scars
In the clinical practice of the burns treatment, an autonomous modeling of the burns morphological structure is important for a correct diagnosis. Unfortunately, the geometrical parameters of burns and skin layers are subjectively estimated. This approach leads to the inaccurate assessment depending on the experience of an individual physician. In our research, we propose the analysis of multiregional segmentation method which is able to differentiate individual skin layers in the ultrasound image records. The segmentation method is represented by the mathematical model of skin layers while other structures are suppressed. Skin layers are consequently approximated by their skeleton with target of the layers distance measurement. The main applicable output of our research is the clinical SW SkinessMeter 1.0.0 serving for an autonomous modeling and quantification of the skin layers.
KeywordsMultiregional segmentation Burns Skin layers Ultrasound Hypertrophic scars
The work and the contributions were supported by the project SV4506631/2101 ‘Biomedicínské inženýrské systémy XII’. This study was supported by the research project The Czech Science Foundation (GACR) No. 17-03037S, Investment evaluation of medical device development.
- 6.Kubicek, J., Penhaker, M., Pavelova, K., Selamat, A., Hudak, R., Majernik, J.: Segmentation of MRI data to extract the blood vessels based on fuzzy thresholding. Stud. Comput. Intell. 598, 43–52 (2015)Google Scholar
- 7.Kubicek, J., Valosek, J., Penhaker, M., Bryjova, I., Grepl, J.: Extraction of blood vessels using multilevel thresholding with color coding. In: Sulaiman, H.A., Othman, M.A., Othman, M.F.I., Rahim, Y.A., Pee, N.C. (eds.) Advanced Computer and Communication Engineering Technology. LNEE, vol. 362, pp. 397–406. Springer, Cham (2016). doi: 10.1007/978-3-319-24584-3_33CrossRefGoogle Scholar
- 10.Csabai, D., Szalai, K., Gyöngy, M.: Automated classification of common skin lesions using bioinspired features. In: IEEE International Ultrasonics Symposium, IUS, art. no. 7728752, November 2016Google Scholar
- 12.Sciolla, B., Delachartre, P., Cowell, L., Dambry, T., Guibert, B.: Multigrid level-set segmentation of high-frequency 3D ultrasound images using the Hellinger distance. In: 9th International Symposium on Image and Signal Processing and Analysis, ISPA 2015, art. no. 7306052, pp. 165–169 (2015)Google Scholar
- 14.Wawrzyniak, Z.M., Szyszka, M.: Layer measurement in high frequency ultra-sonography images for skin. In: Proceedings of SPIE - The International Society for Optical Engineering, 9662, art. no. 96621 (2015)Google Scholar