SKIN CANCER CLASSIFICATION USING CNN

Abstract

Skin cancer is a very big health issue in today’s fastgrowing
population not only for old age people but for
all age groups. Skin Cancer is the most common
human malignancy, is primarily diagnosed visually,
beginning with an initial clinical screening and
followed potentially by dermoscopic analysis, a
biopsy and histopathological examination. Automated
classification of skin lesions using images is a
challenging task owing to the fine-grained variability
in the appearance of skin lesions. So, this project helps
to identify if the person is suffering from cancer or not
and also predicts the type of cancer at ease. The
existing model is able to predict only a specific type of
cancer called melanoma. In this proposed model the
model is trained. This project is used in classifying
skin cancer of a person according to dermatoscopic
images into seven different types. With the help of this
project, a person will get to know if he/she is suffering
from any kind of skin cancer or not, so before going to
consult any doctor a person will have some assurance
about skin cancer. Skin cancer is the most common
human malignancy now-a-days, taking away the
lifespan of humans. Automated classification of skin
lesions using images is a challenging task owing to the
fine-grained variability in the appearance of “SKIN
CARE-10000”.