Independent component analysis: algorithms and applications
Neural Networks
Digital Image Processing
From Colour to Tissue Histology: Physics Based Interpretation of Images of Pigmented Skin Lesions
MICCAI '02 Proceedings of the 5th International Conference on Medical Image Computing and Computer-Assisted Intervention-Part I
Case-Based Tissue Classification for Monitoring Leg Ulcer Healing
CBMS '05 Proceedings of the 18th IEEE Symposium on Computer-Based Medical Systems
Hi-index | 0.00 |
The ability to measure objectively wound healing is important for an effective wound management. Describing wound tissues in terms of percentages of each tissue colour is an approved clinical method of wound assessment. Wound healing is indicated by the growth of the red granulation tissue, which is rich in small blood capillaries that contain haemoglobin pigment reflecting the red colour of the tissue. A novel approach based on utilizing haemoglobin pigment content in chronic ulcers as an image marker to detect the growth of granulation tissue is investigated in this study. Independent Component Analysis is employed to convert colour images of chronic ulcers into images due to haemoglobin pigment only. K-means clustering is implemented to classify and segment regions of granulation tissue from the extracted haemoglobin images. Results obtained indicate an overall accuracy of 96.88% of the algorithm performance when compared to the manual segmentation.