.png){kind=icon}
.png){kind=icon}
Return
Features identification for automatic burn classification
.png){kind=icon}
PRE
AI
DOI：10.1016/j.burns.2015.05.011.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Purpose: In this paper an automatic system to diagnose burn depths based on colour digital photographs is presented. Justification: There is a low success rate in the determination of burn depth for inexperienced surgeons (around 50%), which rises to the range from 64 to 76% for experienced surgeons. In order to establish the first treatment, which is crucial for the patient evolution, the determination of the burn depth is one of the main steps. As the cost of maintaining a Burn Unit is very high, it would be desirable to have an automatic system to give a first assessment in local medical centres or at the emergency, where there is a lack of specialists. Method: To this aim a psychophysical experiment to determine the physical characteristics that physicians employ to diagnose a Burn depth is described. A Multidimensional Scaling Analysis (MDS) is then applied to the data obtained from the experiment in order to identify these physical features. Subsequently, these characteristics are translated into mathematical features. Finally, via a classifier (Support Vector Machine) and a feature selection method, the discriminant power of these mathematical features to distinguish among burn depths is analysed, and the subset of features that better estimates the burn depth is selected. Results: A success rate of 79.73% was obtained when burns were classified as those which needed grafts and those which did not. Conclusions: Results validate the ability of the features extracted from the psychophysical experiment to classify Burns into their depths. (C) 2015 Elsevier Ltd and ISBI. All rights reserved.
Keywords:
Computer aided diagnosis (CAD)
Automatic burn depth estimation
Digital photograph
Multidimensional Scaling Analysis
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
2.9
Papers:
7.2K
Citations:
1.1W