Digital image analysis of chronic ulcers tissues

Ahmad Fadzil, Mohd Hani (2011) Digital image analysis of chronic ulcers tissues. In: 5th Kuala Lumpur International Conference on Biomedical Engineering, BIOMED 2011, Held in Conjunction with the 8th Asian Pacific Conference on Medical and Biological Engineering, APCMBE 201, 20 June 2011 through 23 June 2011, Kuala Lumpur.

[img] PDF
Restricted to Registered users only



Ulcers are chronic wounds that do not heal within a predictable amount of time causing severe pain and discomfort to the patients. Describing the proportion of tissue types is a part of the approved clinical method of wound assessment. Many imaging techniques segment and classify different types of tissues of chronic skin wounds according to the tissue colour. The early visual indication of ulcer healing is the appearance of granulation tissue at the base of ulcers. Granulation tissue appears red in colour due to pigment hemoglobin content in the blood capillaries. The main objective of this research work is to study the optical characteristics of pigment hemoglobin content as a possible image marker in detecting granulation tissue from RGB colour images of chronic ulcers. Independent Component Analysis is employed in the study to convert RGB images of chronic ulcers into images due to pigment hemoglobin only. Preliminary results indicate areas of hemoglobin distribution obtained from hemoglobin images correspond to the presence of granulation tissue on the surface of chronic ulcers

Item Type:Conference or Workshop Item (Paper)
Subjects:Q Science > QA Mathematics > QA75 Electronic computers. Computer science
R Medicine > RL Dermatology
Departments / MOR / COE:Centre of Excellence > Center for Intelligent Signal and Imaging Research
Departments > Electrical & Electronic Engineering
Research Institutes > Institute for Health Analytics
ID Code:6696
Deposited By: Prof Ir Dr Ahmad Fadzil Mohd Hani
Deposited On:21 Nov 2011 06:29
Last Modified:19 Jan 2017 08:23

Repository Staff Only: item control page

Document Downloads

More statistics for this item...