Research Article
Entropy and Gaussian Filter-Based Adaptive Active Contour for
Segmentation of Skin Lesions
Saleem Mustafa,
1
Muhammad Waseem Iqbal ,
2
Toqir A. Rana ,
3,4
Arfan Jaffar,
1
Muhammad Shiraz,
5
Muhammad Arif,
3
and Samia Allaoua Chelloug
6
1
Department of Computer Science, Superior University, Lahore 54600, Pakistan
2
Department of Software Engineering, Superior University, Lahore 54600, Pakistan
3
Department of Computer Science and IT, e University of Lahore, Lahore 54000, Pakistan
4
School of Computer Sciences, Universiti Sains Malaysia, Penang 11800, Malaysia
5
Department of Computer Science, Federal Urdu University of Arts, Science & Technology, Islamabad 44000, Pakistan
6
Department of Information Technology, College of Computer and Information Sciences,
Princess Nourah bint Abdulrahman University, P. O. Box 84428, Riyadh 11671, Saudi Arabia
Correspondence should be addressed to Samia Allaoua Chelloug; sachelloug@pnu.edu.sa
Received 14 April 2022; Revised 13 June 2022; Accepted 28 June 2022; Published 19 July 2022
Academic Editor: Abdul Rehman Javed
Copyright © 2022 Saleem Mustafa et al. is is an open access article distributed under the Creative Commons Attribution
License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is
properly cited.
Malignant melanoma is considered one of the deadliest skin diseases if ignored without treatment. e mortality rate caused by
melanoma is more than two times that of other skin malignancy diseases. ese facts encourage computer scientists to find
automated methods to discover skin cancers. Nowadays, the analysis of skin images is widely used by assistant physicians to
discover the first stage of the disease automatically. One of the challenges the computer science researchers faced when developing
such a system is the un-clarity of the existing images, such as noise like shadows, low contrast, hairs, and specular reflections,
which complicates detecting the skin lesions in that images. is paper proposes the solution to the problem mentioned earlier
using the active contour method. Still, seed selection in the dynamic contour method has the main drawback of where it should
start the segmentation process. is paper uses Gaussian filter-based maximum entropy and morphological processing methods
to find automatic seed points for active contour. By incorporating this, it can segment the lesion from dermoscopic images
automatically. Our proposed methodology tested quantitative and qualitative measures on standard dataset dermis and used to
test the proposed method’s reliability which shows encouraging results.
1. Introduction
Melanoma is one form of skin cancer. Recent researches
show that melanoma is the most dangerous kind of skin
cancer. An important reason is that melanoma affects about
75% of death reported skin cancer. In 2017, research shows
that around 9,480 out of 76,690 melanoma patients died by
the cause of melanoma in the USA [1]. In addition, 1 in 74
males and 1 in 90 females may infect with melanoma in their
life in Canada. Previous research also shows that for non-
Hispanic American white people, occurrence rates have
increased yearly by around 3%. For grown people ages 15
and 30, melanoma is considered the most popular identi-
fiable type of cancer [2]. Discovering melanoma in the early
stage will increase the probability from 5 years to 96% of
remaining alive. Still, in case of finding it in the very ad-
vanced stage, that percentage will decrease to 5% [2]. e
recovery percentage is affected, and the melanoma treatment
cost in the advanced stage is 30 times more than the cost of
melanoma treatment in the early stages. Dermoscopic device
helps physicians view the lesion features more clearly than
the naked eye [3].
Hindawi
Computational Intelligence and Neuroscience
Volume 2022, Article ID 4348235, 10 pages
https://doi.org/10.1155/2022/4348235