A CNN model used in a web page to classify skin cancer

Ruixuan Ni; Xi Li; Lizhuoyuan Wan

doi:10.1117/12.2636930

10 June 2022 A CNN model used in a web page to classify skin cancer

Ruixuan Ni, Xi Li, Lizhuoyuan Wan

Proceedings Volume 12179, Second International Conference on Medical Imaging and Additive Manufacturing (ICMIAM 2022); 1217916 (2022) https://doi.org/10.1117/12.2636930
Event: Second International Conference on Medical Imaging and Additive Manufacturing (ICMIAM 2022), 2022, Xiamen, China

Abstract

In recent years, to better distinguish skin cancer from common skin diseases, the CNN model, known for its precise classification, has been widely used in the clinical field to recognize skin cancer. However, since this model relies entirely on the given dataset used to train the model, it is hard for the model to recognize features, not in the given dataset. To tackle this issue, this paper proposed a CNN model to classify skin cancer, which has higher accuracy in classifying skin cancers with most of the features. This paper also proposed a web page where the CNN model and a chatbot (using Natural Language Processing) were used, providing people an interface for skin cancer diagnosis. In this experiment, we trained a CNN model with skin lesion images, enabling the model to classify malignant and benign skin cancers. The CNN model is trained with a dataset provided by ISIC, which includes 3297 images of skin cancer, consisting of 1800 benign samples and 1497 malignant samples. The experimental results demonstrated that the accuracy of this model in the classification of the test set achieves 88.04%. Furthermore, we note that the AUC value of this model also achieves 0.874, which seems to show that the model performs well.

Citation Download Citation

Ruixuan Ni, Xi Li, and Lizhuoyuan Wan "A CNN model used in a web page to classify skin cancer", Proc. SPIE 12179, Second International Conference on Medical Imaging and Additive Manufacturing (ICMIAM 2022), 1217916 (10 June 2022); https://doi.org/10.1117/12.2636930

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
8 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Tumor growth modeling

RGB color model

Skin cancer

Data modeling

Skin

Cognitive modeling

Image classification

Show All Keywords

Keywords/Phrases

Search In:

Publication Years