Mobile application-based computer-aided diagnosis of skin tumours from dermal images

ABSTRACT

Skin tumour is defined as the enormous growth of cells in the skin. The aim is to design standalone application for diagnosis of skin tumours. The dermal images of three different types obtained from the authorized PH2 database are used to analyse the defined image processing algorithm. In this algorithm, pre-processing was performed to remove hair cells. Contour-based level set is used to segment lesion from which clinical and morphological features are extracted for classification. Significant features are obtained with the feature selection technique, Random subset. Classification is performed with three classifiers. The efficiency of the classifier obtained with different trials of classification is analysed with the ANOVA test. With these results, the Multiclass Support vector machine was configured as a suitable classifier to categorize dermal images. Therefore, an application is developed for the analysis of images acquired through mobile with the help of a magnification set-up. Thus, extracted features, segmented and original images are transferred to a database for storage.

KEYWORDS:

• Contour-based level set
• random subset feature selection
• multiclass support vector machine
• standalone application

Notes on contributors

Ms. T. R. Thamizhvani has completed her B.E. in Biomedical Engineering from Jerusalem College of Engineering, M.E. in Medical Electronics from SSN College of Engineering, Master studies on Mobile application based on Computer diagnosis of Skin tumours. Her areas of interests are Medical Image processing, Biomedical Instrumentation and rehabilitation. Currently, she is working as Assistant Professor in Vels Institute of Science, Technology and Advanced Studies, Pallavaram.

Dr. Suganthi Lakshmanan has completed her B.E in Electronics and Communication Engineering from National Engineering College, M.E in Communication and Networking from MIT Chennai. Doctoral studies on Takayasu’s Arteritis – Clinical Analysis, Modeling and Simulation towards Novel Diagnostic Technique from Indian Institute of Technology Madras. Her areas of interests are Biomedical Instrumentation, Mathematical modeling of human physiological system, Biomedical signal & Image processing and Embedded system. Currently, she is working as Associate Professor in SSN College of Engineering, Kalavakkam.

Dr. R. Sivaramakrishnan graduated in the discipline of Electronics and Communication Engineering from Madurai Kamaraj University and completed his Post Graduation in Medical Electronics from Anna University. He holds a doctoral degree in Information and Communication discipline from Anna University, Chennai. His work on “Early Detection of Cancer using Fuzzy Based Photoplethysmography” received the prestigious AT&T Bell Laboratories Award, from U.S.A., with a cash grant. He is currently pursuing postdoctoral research at the renowned Lister Hill National Center for Biomedical Communications (LHNCBC), National Library of Medicine (NLM), National Institutes of Health (NIH), U.S.A., in the field of Deep Learning-based Medical Image Understanding/Analysis. His areas of interest include Machine Learning, Biomedical Image Processing and Music Therapy.

ORCID

T. R. Thamizhvani http://orcid.org/0000-0002-7408-648X