Authors :
Nikita Mali; Prajwal Thawari; Uday Jawheri; Sulaxan Jadhav
Volume/Issue :
Volume 8 - 2023, Issue 8 - August
Google Scholar :
https://tinyurl.com/2waw5tfz
Scribd :
https://tinyurl.com/43sva9wr
DOI :
https://doi.org/10.5281/zenodo.10026122
Abstract :
Skin cancer is a common and dangerous form
of cancer. This is a dangerous kind of cancer, and early
detection is crucial for successful treatment. Malignant
tumors develop when healthy, normal skin cells
experience genetic alterations and begin to grow
uncontrolled. An important risk factor for skin cancer is
ultraviolet (UV) radiation from the sun and artificial
sources like tanning beds. Skin cancer can develop in
other places of the body, although it often occurs on the
face, neck, arms, and handsbecause of their exposure to
sunlight. Data imbalance issues are brought on by the
significant discrepancy between data from several
healthcare industry classifications. Deep learning models
frequently train on one class more than others due to
problems with data imbalance. The dataset utilized is
skin cancer MNIST: HAM10000, which contains seven
kinds of skin lesions. The seven forms of skin lesions are
as follows: melanocytic nevi (nv), melanoma (mel),
benign keratosis(bkl), basal cell carcinoma (bcc), actinic
keratosis (akiec), vascular lesions (vasc), and
dermatofibroma (df). These are used to categorize skin
cancer based on mutations andvariations. Deep learning
models (inception v3, resnet, vgg16, and mobile net) and
deep learning techniques such as data augmentation,
image normalization, and image standardization were
used to classify skin cancer.
Skin cancer is a common and dangerous form
of cancer. This is a dangerous kind of cancer, and early
detection is crucial for successful treatment. Malignant
tumors develop when healthy, normal skin cells
experience genetic alterations and begin to grow
uncontrolled. An important risk factor for skin cancer is
ultraviolet (UV) radiation from the sun and artificial
sources like tanning beds. Skin cancer can develop in
other places of the body, although it often occurs on the
face, neck, arms, and handsbecause of their exposure to
sunlight. Data imbalance issues are brought on by the
significant discrepancy between data from several
healthcare industry classifications. Deep learning models
frequently train on one class more than others due to
problems with data imbalance. The dataset utilized is
skin cancer MNIST: HAM10000, which contains seven
kinds of skin lesions. The seven forms of skin lesions are
as follows: melanocytic nevi (nv), melanoma (mel),
benign keratosis(bkl), basal cell carcinoma (bcc), actinic
keratosis (akiec), vascular lesions (vasc), and
dermatofibroma (df). These are used to categorize skin
cancer based on mutations andvariations. Deep learning
models (inception v3, resnet, vgg16, and mobile net) and
deep learning techniques such as data augmentation,
image normalization, and image standardization were
used to classify skin cancer.
