Skin lesion segmentation using k-mean and optimized fire fly algorithm

• Published in: Multimedia tools and applications Vol. 80; no. 5; pp. 7397 - 7410
• Main Authors: Garg, Shelly, Jindal, Balkrishan
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.02.2021; Springer Nature B.V
• Subjects: Algorithms; Cancer; Casualties; Computer Communication Networks; Computer Science; Data Structures and Information Theory; Datasets; Dermatology; Digital imaging; Heuristic methods; Image processing; Image segmentation; Lesions; Medical imaging; Multimedia Information Systems; Particle swarm optimization; Skin cancer; Special Purpose and Application-Based Systems; FFA; Segmentation; Pre-processing; Automatic detection; K-mean
• ISSN: 1380-7501; 1573-7721
• DOI: 10.1007/s11042-020-10064-8

Digital image processing is turning out to be increasingly more significant in the health care field used to diagnose skin cancer. The death rate is increasing by 1% every year due to skin cancer. One of the major causes of casualties due to this cancer is the non-predictability at the early stages. This paper will help in future research work when it comes to early detection of a tumor. In this work, the proposed model comprises of two important steps which are preprocessing and segmentation. In a pre-processing case, unwanted artifacts like hair, illumination, or many other artifacts are reduced by an enhanced technique using threshold and morphological operations and In the second step, segmentation of skin lesion using k-mean segmentation algorithm with optimized firefly algorithm (FFA) technique is used to achieve high accuracy. Input sample images are taken from the International skin imaging collaboration (ISIC) archive dataset and dermatology service of Hospital Pedro Hispano (PH 2 ) dataset which are available online. The results of the proposed method are measured in terms of different parameters. It provides an accuracy of 99.1% and 98.9% using ISIC and PH 2 datasets and shows better performance than existing techniques such as K-Mean and K-Mean with Particle Swarm Optimization (PSO). The performance of this research work is, in fact, quite promising.