D.N.V.S.L.S. Indira et al, / (IJCSIT) International Journal of Computer Science and Information Technologies, Vol. 2 (5) , 2011, 1927-1932
Detection & Analysis of Skin Cancer using
D.N.V.S.L.S. Indira # , JYOTSNA SUPRIYA P *
Department of Computer Science & Engineering,Gudlavalleru Engineering College, Gudlavalleru, Krishna Dt., AP., India
Department of Computer Science & Engineering,Swarnandhra Institute ofEngineering & Technology Narsapur-534275, WGDT, AP., India
Abstract— This paper presents a different method to develop a Texture Analysis based Classification Module to improve the decision strategy and overall accuracy
of the system.
Asymmetry, Border Irregularity, Color variation, Diameter is the major symptoms which we will use in our processing
algorithm. By applying multi-level Wavelet Transformation to the input image and then choosing a group of sub-bands to be restored for best defect detection, the procedure for Skin
cancer detection and analysis was developed.
Keywords – Skin Cancer, Wavelet Techniques, Melanoma,
Skin cancer is the most common type of cancer and
represents 50% all new cancers detected each year. The
deadliest form of skin cancer is melanoma, and its
incidence has been rising at an alarming rate of 3 % per
year. If detected at an early stage, skin cancer has one of the highest cure rates, with rather simple and economical
The incidence of malignant melanoma has increased
dramatically over the past few decades. Although a
potentially fatal disease, malignant melanoma has a near
100%cure rate if detected and excised early. Early diagnosis is obviously dependent upon patient attention but also
accurate assessment by a medical practitioner.
Dermatologist will see numerous melanoma patients,
honing their capacity to make accurate diagnoses but
general practitioners and other medical professional may
not develop such an accurate eye. A computer aided
diagnosis system is not meant to replace a trained
Dermatologist but to assist less trained practitioners. Such a system would be useful for remote medical clinics that do
not have the luxury of a trained dermatologist on hand.
This paper makes use of Matlab’s Image Processing
Toolbox and Wavelet Toolbox for all image analysis and
Cancer can be defined as a group of diseases in which cells
are aggressive (grow and divide without respect to normal
limits), invasive (invade and destroy adjacent tissues) and
metastatic (spread to other locations in the body).
Cancer is usually classified according to the tissue from
which the cancerous cells originate as well as the normal
cell type they most resemble (Lung, Skin, Breast, Prostate,
Bone, etc.).The most common type of cancer found is the
Skin cancer. It represents the most commonly diagnosed
malignancy, surpassing lung, breast and prostate cancer.
B. Skin Cancer
Skin cancer is a disease in which cancer (malignant) cells
are found in the outer layers of the skin. It develops in the epidermis (the outermost layer of skin), so a tumor is
usually clearly visible. This makes most skin cancers
detectable in the early stages.
There are 3 common types of skin cancer, each of which is
named after the type of skin cell from which it arises.
1. Basal Cell Carcinoma: It is the most common type
of skin cancer. It typically appears as a small
raised bump that has a pearly appearance. It is
most commonly seen on areas of the skin that have
received excessive sun exposure.
1) Squamous Cell Carcinoma: It is seen on the areas
of the body that have been exposed to excessive
sun (nose, lower lip, hands, and forehead). Often
this cancer appears as a firm red bump or
ulceration of the skin that does not heal.
2) Melanoma: The malignant melanoma is a highly
malignant skin cancer, it grows rapidly and
sometimes with different colors and abnormal
Please join StudyMode to read the full document