Abstract
This paper proposes a computer-based method to support medical science students in the detection of skin diseases accurately. It uses the Gaussian filter and applies the 2-D Wavelet Transformation and-2-D Inverse Wavelet Transformation techniques for the aim of image preprocessing in order to get rid of the noises, and segment skin cancer lesion by fusing edge-based and region-based segmentation approaches. The next step consists of applying Morphological filters to get rid of external noise and the interior one of the object, which remained in the segmented image as well as to soften the edges. Then, use the k-Nearest Neighbor (kNN) classifiers. The desired goal of this paper is to test the accuracy of the following proposed segmentation algorithm. The proposed method is tested on 133 images whereas 78 are malignant melanoma skin cancer type and 55 benign ones. This approach allowed detecting two different Pathological cases of skin lesions images which are malignant melanoma and benign nevi. The segmentation achieved 97.75% of accuracy for these two types of skin cancer lesions.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Eisa MM, Ewees AA, Refaat MM, Elgamal AF (2013) Effective medical image retrieval technique based on texture features. Int J Intell Comput Inf Sci 13(1)
Houssein EH, Ewees AA, ElAziz MA (2018) Improving twin support vector machine based on hybrid swarm optimizer for heartbeat classification. Pattern Recognit Image Anal 28(2):243–253
El Aziz MA, Ewees AA, Hassanien AE (2017) Whale optimization algorithm and moth-flame optimization for multilevel thresholding image segmentation. Expert Syst Appl 83:242–256
Roy P, Goswami S, Chakraborty S, Azar AT, Dey N (2014) Int J Rough Sets Data Anal (IJRSDA) 1(2)
El Aziz MA, Ewees AA, Hassanien AE (2016) Hybrid swarms optimization based image segmentation. In: Hybrid soft computing for image segmentation. Springer, Cham, pp 1–21. https://doi.org/10.1007/978-3-319-47223-2_1
Ewees AA, El Aziz MA, Hassanien AE (2017) Chaotic multi-verse optimizer-based feature selection. Neural Comput Appl 1–16. https://doi.org/10.1007/s00521-017-3131-4
Ibrahim RA, Elaziz MA, Ewees AA, Selim IM, Lua S (2018) Galaxy images classification using hybrid brain storm optimization with moth flame optimization. J Astron Telesc, Instrum, Syst 4(3)
Elaziz MEA, Ewees AA, Oliva D, Duan P, Xiong S (2017) A hybrid method of sine cosine algorithm and differential evolution for feature selection. In: International conference on neural information processing. Springer, Cham. https://doi.org/10.1007/978-3-319-70139-4_15
Ibrahim RA, Oliva D, Ewees AA, Lu S (2017) Feature selection based on improved runner-root algorithm using chaotic singer map and opposition-based learning. In: International conference on neural information processing. Springer, Cham. https://doi.org/10.1007/978-3-319-70139-4_16
El Aziz MA, Ewees AA, Hassanien AE, Mudhsh M, Xiong S (2018) Multi-objective whale optimization algorithm for multilevel thresholding segmentation. In: Advances in soft computing and machine learning in image processing. Springer, Cham, pp 23–39. https://doi.org/10.1007/978-3-319-63754-9_2
Ewees AA, Sahlol AT (2018) Bio-inspired optimization algorithms for improving artificial neural networks: a case study on handwritten letter recognition. Comput Linguist, Speech Image Process Arab Lang 4:249. https://doi.org/10.1142/9789813229396_0012
Gopinath J, Krishnan R (2015) A Survey on different types of segmentation techniques. Int J Mod Trends Eng Res 02(10)
Dalila F, Zohra A, Redab K, Hocine C (2017) Segmentation and classification of melanoma and benign skin lesions. Optik—Int J Light Electron Opt 140:749–761
Oliveira RB, Marranghellob N, Pereira AS, Tavares JMRS (2016) A computational approach for detecting pigmented skin lesions in macroscopic images. Expert Syst Appl: Int J Arch 61(C):53–63
Jain S, Jagtap V, Pise N (2015) Computer aided Melanoma skin cancer detection using image processing. Procedia Comput Sci 48:735–740
Lavanya S, Naveen Kumar B, Obuliraj R, Dhanalakshmi S (2014) Gradient watershed transform based automated cell segmentation for THG microscopy medical images to detect skin cancer. Int J Sci Technol 2
Oliveira RB, Tavares JMRS, Marranghello N, Pereira AS (2013) An approach to edge detection in images of skin lesions by Chan-Vese model. In: 8th Doctoral Symposium in Informatics Engineering Conference, Porto, vol 1
de Araujo AF, Tavares JMRS, Pereira AS, Marranghello N (2013) Segmentation of skin lesions by watershed using markers approximated by the Mumford-Shah region growing method, summer school and work shop on imaging science and medical applications. University of Coimbra, Portugal
Mabrouk MS, Sheha MA, Sharawy A (2012) Automatic detection of Melanoma skin cancer using texture analysis. Int J Comput Appl 42(20):22–26
El Aziz MA, Ewees AA, Hassanien AE (2018) Multi-objective whale optimization algorithm for content-based image retrieval. Multimed Tools Appl 77(19):26135–26172
Ewees AA, Elaziz MA, Oliva D (2018) Image segmentation via multilevel thresholding using hybrid optimization algorithms. J Electron Imaging 27(6):063008
Dermnet skin disease image atlas, http://www.dermnet.com. Accessed 11 Feb 2018
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Ibrahim, E., Ewees, A.A., Eisa, M. (2020). Proposed Method for Segmenting Skin Lesions Images. In: Hitendra Sarma, T., Sankar, V., Shaik, R. (eds) Emerging Trends in Electrical, Communications, and Information Technologies. Lecture Notes in Electrical Engineering, vol 569. Springer, Singapore. https://doi.org/10.1007/978-981-13-8942-9_2
Download citation
DOI: https://doi.org/10.1007/978-981-13-8942-9_2
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-8941-2
Online ISBN: 978-981-13-8942-9
eBook Packages: EngineeringEngineering (R0)