Wound image segmentation using clustering based algorithms

• Autorzy: Farmaha Ihor , Banaś Marian , Savchyn Vasyl , Lukashchuk Bohdan , Farmaha Taras

Identyfikatory

DOI

10.2478/ntpe-2019-0062

• Języki publikacji: EN

Abstrakty

EN

Classic methods of measurement and analysis of the wounds on the images are very time consuming and inaccurate. Automation of this process will improve measurement accuracy and speed up the process. Research is aimed to create an algorithm based on machine learning for automated segmentation based on clustering algorithms Methods. Algorithms used: SLIC (Simple Linear Iterative Clustering), Deep Embedded Clustering (that is based on artificial neural networks and k-means). Because of insufficient amount of labeled data, classification with artificial neural networks can`t reach good results. Clustering, on the other hand is an unsupervised learning technique and doesn`t need human interaction. Combination of traditional clustering methods for image segmentation with artificial neural networks leads to combination of advantages of both of them. Preliminary step to adapt Deep Embedded Clustering to work with bio-medical images is introduced and is based on SLIC algorithm for image segmentation. Segmentation with this method, after model training, leads to better results than with traditional SLIC.

Słowa kluczowe

EN

clustering; Segmentation; machine learning; neural networks; wounds

PL

segmentacja; nauczanie maszynowe; sieci neuronowe; rany; klastrowanie

• Wydawca: STE GROUP ; De Gruyter
• Czasopismo: New Trends in Production Engineering
• Rocznik: 2019
• Tom: Vol. 2, Iss. 1
• Strony: 570--578
• Opis fizyczny: Bibliogr. 10 poz., rys., tab.

Twórcy

autor

Farmaha Ihor

• Lviv Polytechnic National University, Ukraine

autor

Banaś Marian

• AGH University of Science and Technology, Poland

autor

Savchyn Vasyl

• Lviv Polytechnic National University, Ukraine

autor

Lukashchuk Bohdan

• Lviv Polytechnic National University, Ukraine

autor

Farmaha Taras

• Danylo Halytsky Lviv National Medical University, Ukraine

Bibliografia

• 1. Jansen, S., Rachel, K. (2016). The Evolving Field of Wound Measurement Techniques: A Literature Review. [online] Available at: https://www.woundsresearch.com/article/evolving-field-wound-measurement-techniques-literature-review [Accessed 31 June 2019].
• 2. WoundEducators.com (2012). Wound measurement techniques. [online] Available at: https://woundeducators.com/wound-measurement-techniques/ [Accessed 31 June 2019].
• 3. Flanagan M. (2003) Improving accuracy of wound measurement in clinical practice. Ostomy Wound Manage., pp. 28-40.
• 4. Lukavetskyi, O., Stoianovskyi, I. and Farmaha, T. (2017). Computer program for vulnerometry (in Ukrainian), Kharkiv Surgical School: Medical Scientific and Practical Journal, pp. 145-147.
• 5. Jaworski, N., Farmaha, I., Farmaha, T., Savchyn, V. and Marikutsa, U. (2018). Implementation features of wounds visual comparison subsystem. XIVth International Conference perspective technologies and methods in mems design., pp. 114-117.
• 6. Nejati, H., Ghazijahani, H. and Abdollahzadeh, M. (2018). Fine-grained wound tissue analysis using deep neural network [online] Available at: https://arxiv.org/pdf/1802.10426.pdf [Accessed 31 June 2019].
• 7. Lai, Z. and Deng, H. (2018) Medical Image Classification Based on Deep Features Extracted by Deep Model and Statistic Feature Fusion with Multilayer Perceptron. [online] Computational Intelligenceand Neuroscience Available at: https://www.hindawi.com/journals/cin/2018/2061516/ [Accessed 31 June 2019].
• 8. Kumar, K., Reddy, B. (2014) Wound image analysis classifier for efficient tracking of wound healing status. [online] An International Journal. Available at: http://aircconline.com/sipij/V5N2/5214sipij02.pdf [Accessed 31 June 2019].
• 9. Hemalatha, R., Thamizhvani, T. and Dhivya, A. (2018). Active Contour Based Segmentation Techniques for Medical Image Analysis. [online] Available at: https://www.intechopen.com/books/medical-and-biological-image-analysis/active-contour-based-segmentation-techniques-for-medical-image-analysis [Accessed 31 June 2019].
• 10. Xie, J., Girshick, R. and Farhadi, A. (2016). Unsupervised Deep Embedding for Clustering Analysis. [online] Available at: https://arxiv.org/pdf/1511.06335.pdf [Accessed 31 June 2019].

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021).