DERMATOLOGICAL TRACKING OF CHRONIC ACNE

Authors

  • Sergiu Lucut Ph.D. Student, Human Performance Laboratory, University of Calgary
  • Michael Smith

Abstract

INTRODUCTION

Acne is a condition with severe physical and psychological implications on chronic sufferers, affecting approximately 80 percent of people between the ages of 11 and 30, at some point in their lives. The purpose of the research was to create a prototype that has the potential track changes in the condition for a person suffering from acne, in order to provide an accurate and standardized tool of assessment. Such a tool would be useful in both clinical and research settings where qualitative and quantifiable results are needed [1]. These are normally hard to obtain due to the low reproducibility and high subjectivity of the assessment which often leads to high inter and intra variability in graders.

METHODS

Images of (20) patients with healthy skin, acne, and other conditions similar in appearance to acne were used to test the algorithm, LS-KMC, that is explained in the schematic in Figure 1. The left side outlines the previous method based on Ramli et al.’s work [2], RMH-KMC, for comparison.

RESULTS

The results show that LS-KMC outclasses the previous system, not just by its ability to automatically characterize the condition in the region of interest (ROI), but also by achieving higher scores across all relevant metrics in 19 of the 20 cases.

DISCUSSION AND CONCLUSIONS

We proposed a new acne recognition approach to extend the previous k-clustering method proposed by Ramli et al. to introduce a higher level of computer aided support for providing acne scores. The new algorithm includes a number of steps to automate the identification and classification of acne features. Previously used metrics failed to take into account the nature of the condition and lead to unrealistically high success rates. A new metric, Characterization Sensitivity, was proposed for identifying the relative success of acne recognition algorithms. The metric uses a weighted area technique with assigned coefficients to the areas of the lesions based on the Michaelson grading scale [3]. The results showed that the proposed Lucut-Smith k-clustering algorithm performs much better than the previous systems.

Author Biography

Sergiu Lucut, Ph.D. Student, Human Performance Laboratory, University of Calgary

I am a PhD Student working in Walter Herzog's lab. My research aims to clarify if obesity is an independent risk factor for Osteoarthritis using a preclinical animal model. Understanding how low-level systemic inflammation affects joints and muscle tissue can help us identif early targeted treatment strategies and assist in preventing the onset and progression of joint disease. There are many incredible resources for undergraduates in Alberta to participate in research. My goal is to help facilitate the transaltion of undergraduate research projects into print by increasing the impact, scope, and contributors to JURA during my term as co-editor.

Downloads

Published

2014-09-05

Issue

Vol. 4 No. 1: 2014 NSERC CREATE Symposium at the University of Calgary

Section

Extended Abstracts

License

Authors retain all rights to their research work. Articles may be submitted to and accepted in other journals subsequent to publishing in JURA. Our only condition is that articles cannot be used in another undergraduate journal. Authors must be aware, however, that professional journals may refuse articles submitted or accepted elsewhere—JURA included.