A Prediction of Skin Cancer using Mean-Shift Algorithm with Deep Forest Classifier

V. Gokula Krishnan; K. Sreerama Murthy; Srinivasarao Kongara; Kurra Upendra Chowdary; M. Somaskandan; A. Jerrin Simla

doi:10.24996/ijs.2022.63.7.39

Authors

V. Gokula Krishnan Professor, CSE Department, Saveetha School of Engineering, SIMATS, Chennai, Tamil Nadu, India https://orcid.org/0000-0002-3913-3156
K. Sreerama Murthy Associate Professor, IT Department, Sreenidhi Institute of Science and Technology, Hyderabad, TS, India
Srinivasarao Kongara Assistant Professor, CSBS Department, RVR & JC College of Engineering, Guntur, Andhra Pradesh, India
Kurra Upendra Chowdary Assistant Professor, CSBS Department, RVR & JC College of Engineering, Guntur, Andhra Pradesh, India
M. Somaskandan Assistant Professor, IT Department, Panimalar Engineering College, Chennai, Tamil Nadu, India
A. Jerrin Simla Associate Professor, CSE Department, Panimalar Institute of Technology, Chennai, Tamil Nadu, India

DOI:

https://doi.org/10.24996/ijs.2022.63.7.39

Keywords:

Benign, Deep Forest Classifier, Hair Removal, Segmentation, Skin Cancer Detection, Malignant, Classification

Abstract

Skin cancer is the most serious health problems in the globe because of its high occurrence compared to other types of cancer. Melanoma and non-melanoma are the two most common kinds of skin cancer. One of the most difficult problems in medical image processing is the automatic detection of skin cancer. Skin melanoma is classified as either benign or malignant based on the results of this test. Impediment due to artifacts in dermoscopic images impacts the analytic activity and decreases the precision level. In this research work, an automatic technique including segmentation and classification is proposed. Initially, pre-processing technique called DullRazor tool is used for hair removal process and semi-supervised mean-shift algorithm is used for segmenting the affected areas of skin cancer images. Finally, these segmented images are given to a deep learning classifier called Deep forest for prediction of skin cancer. The experiments are carried out on two publicly available datasets called ISIC-2019 and HAM10000 datasets for the analysis of segmentation and classification. From the outcomes, it is clearly verified that the projected model achieved better performance than the existing deep learning techniques.