Title: Classification of skin lesions using deep learning neural network

Authors: S.P. Godlin Jasil; V. Ulagamuthalvi

Addresses: Department of Computer Science and Engineering, Sathyabama Institute of Science and Technology, Chennai, 600119, India ' Department of Computer Science and Engineering, Sathyabama Institute of Science and Technology, Chennai, 600119, India

Abstract: In recent years, skin cancer is one of most deadly diseases in the world. Early detection of skin cancer leads to the advanced treatment. Skin cancer is diagnosed by dermatoscopic analysis, histopathological assessment and biopsy. Since the skin lesion appears very similar when comparing with the surrounding skin, classification becomes a challenging process. Due to the development in automated systems, classification of skin lesions can be done with the higher accuracy. This paper presents a deep learning neural network architecture used for automatic skin classification. Our dataset consists of 1,456 images of seven classes which is taken from HAM1000 dataset. Preprocessing such as data argumentation is done to improve the performance. The proposed architecture gives the higher classification rate with accuracy.

Keywords: skin cancer; dermatoscopic; histopathological; biopsy; skin lesion; deep learning; neural network; data argumentation.

DOI: 10.1504/IJPSPM.2024.138041

International Journal of Public Sector Performance Management, 2024 Vol.13 No.3, pp.436 - 442

Received: 10 Jul 2020
Accepted: 12 Aug 2020
Published online: 18 Apr 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article