Preprint / Version 1

Skin Cancer Classification Using Convolutional Neural Networks

##article.authors##

  • Trisha Raj STEM Early College at N.C. A&T

DOI:

https://doi.org/10.47611/harp.95

Keywords:

Skin Cancer, Convolutional Neural Network

Abstract

Skin cancer is the out-of-control growth of abnormal cells in the epidermis. It is usually caused by damage or mutations in the DNA. This causes the skin cells to grow and multiply rapidly and out of control, which forms tumors in the skin. Deep learning is a type of machine learning that—through many layers of artificial neurons— learns high-level features from a high-dimensional input. In image processing, the lower layers of a neural network may identify simple features such as edges, while later layers may learn complex concepts such as digits or letters. The testing and training data was downloaded from the ISIC 2019 Challenge which is a database with images of skin cancer images ranging in various types. Training images were run through the three convolutional layers with ReLU activations, each followed by a max-pooling layer. Finally, they were passed through three dense layers and a softmax layer activation. Here, we trained a 2D CNN on images of skin lesions to classify benign patterns and different types of skin cancers. The model achieved reasonably high accuracy on the most common kinds of skin lesions. These findings suggest that with the right data and modeling, a neural network can be used to limit the number of doctor visits people need to make to determine if they have skin cancer or not.

References or Bibliography

[Can20] Cancer.org. Basal and squamous cell skin cancer statistics. Cancer.org, 2020.

[Cen20] Cancer Center. Types of skin cancer: Common, rare, and more

varieties. CancerCenter.com, 2020.

[Cha14] B. Chan. Solar lentigo. Dermnetnz, 2014.

[Cli19a] Mayo Clinic. Actinic keratosis. Mayo Clinic, 2019.

[Cli19b] Mayo Clinic. Seborrheic keratosis. Mayo Clinic, 2019.

[Cli19c] Mayo Clinic. Skin cancer. Mayo Clinic, 2019.

[Hea20] SM Health. Vascular lesions. SMHealth.com, 2020.

[HH20] MD Hale, E.K. and MD. Hanke, C. W. Squamous cell carcinoma.

Skin Cancer.org, 2020.

[HR20] MD Marghoob A. A. MD Halpern, A. C. and MD. Reiter, O.

Melanoma. Skin Cancer.org, 2020.

[JM17] J. Johnson and MD. Marcin, J. Dermatofibroma: Causes, images,

and treatment. Medical News Today, 2017.

[Kar20] MD Moy R. L. MD. Karen, J. K. Basal cell carcinoma. Skin

Cancer.org, 2020.

[MC19] Veronica Rotemberg Brian Helba Veronica Vilaplana Ofer Reiter Allan C. Halpern Susana Puig Josep Malvehy Marc Combalia, Noel C.

F. Codella. Bcn20000: Dermoscopic lesions in the wild. Cornell

University, 2019.

[Med09] Medicinenet.com. Congenital nevi picture image on

medicinenet.com. Medicinenet.com, 2009.

[NCFC17] M. Emre Celebi Brian Helba Michael A. Marchetti Stephen W. Dusza

Aadi Kalloo Konstantinos Liopyris Nabin Mishra Harald Kittler Allan Halpern Noel C. F. Codella, David Gutman. Skin lesion analysis

toward melanoma detection: A challenge at the 2017 international

symposium on biomedical imaging (isbi), hosted by the international

skin imaging collaboration (isic). Cornell University, 2017.

[TP18] Rosendahl C. Kittler H. Tschandl P. The ham10000 dataset, a

large collection of multi-source dermatoscopic images of common pigmented skin lesions. PubMed, 2018.

[Wor20] Math Works. What is deep learning?: How it works, techniques

applications. MathWorks.com, 2020.

Downloads

Posted

10-27-2021