Files and links (1)
PDFOpen Access (License Unspecified), Open Access
Thesis
An automated wound identification system based on image segmentation and artificial neural networks
Master of Science (M.S.), Drexel University
Jun 2012
DOI:
https://doi.org/10.17918/etd-3915
Abstract
Chronic wounds are a global, ongoing health challenge that afflicts a large number of people. Effective diagnosis and treatment of the wounds relies largely on a precise identification and measurement of the wounded tissue; however, in current clinical process, wound evaluation is based on subjective visual inspection and manual measurements which are often inaccurate. An automatic computer-based system for fast and accurate segmentation and identification of wounds is desirable, both from the standpoint of improving health outcomes in chronic wound care and management, and in making clinical practice more efficient and cost-effective. As presented in this thesis, we design such a system that uses color wound photographs taken from the patients, and is capable of automatic image segmentation and wound region identification. Several commonly used segmentation methods are utilized to obtain a collection of candidate wound areas. The parameters of each method are fine-tuned through an optimization procedure. Two different types of Artificial Neural Networks (ANNs), the Multi-Layer Perceptron (MLP) and the Radial Basis Function (RBF) with parameters decided by a cross-validation approach, are then applied with supervised learning in the prediction procedure, and their results are compared. Satisfactory results of this system suggest a promising tool to assist in the field of clinical wound evaluation.
Metrics
64 File views/ downloads
33 Record Views
Details
- Title
- An automated wound identification system based on image segmentation and artificial neural networks
- Creators
- Bo Song - DU
- Contributors
- Ahmet Sacan (Advisor) - Drexel University (1970-)Elisabeth S. Papazoglou (Advisor) - DU
- Awarding Institution
- Drexel University
- Degree Awarded
- Master of Science (M.S.)
- Publisher
- Drexel University; Philadelphia, Pennsylvania
- Resource Type
- Thesis
- Language
- English
- Academic Unit
- School of Biomedical Engineering, Science, and Health Systems (1997-2026); Drexel University
- Other Identifier
- 3915; 991014632308904721