Lightweight Deep Learning Model for Melanoma Classification in Dermoscopy Images for Smart Healthcare

Among various types of skin cancers, melanoma is the most aggressive and deadly. There is a notable growth in the implementation of deep learning (DL) methods to identify skin malignancies in dermoscopy images. This paper introduces a lightweight DL-based approach designed for seamless integration i...

Full description

Saved in:
Bibliographic Details
Published in2024 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET) pp. 1 - 6
Main Authors Sree Charan Teja, Pentapati Naga, Krishna, Thunakala Bala, Reddy Poreddy, Ajay Kumar, Kokil, Priyanka
Format Conference Proceeding
LanguageEnglish
Published IEEE 21.03.2024
Subjects
Adaptation models
classification
Computational modeling
Deep learning
Feature extraction
lightweight models
Medical services
Melanoma
smart healthcare
Wireless communication
Online AccessGet full text

Cover

More Information
Summary:Among various types of skin cancers, melanoma is the most aggressive and deadly. There is a notable growth in the implementation of deep learning (DL) methods to identify skin malignancies in dermoscopy images. This paper introduces a lightweight DL-based approach designed for seamless integration into low-memory devices within healthcare applications. The proposed method incorporates three lightweight convolutional neural network (CNN) models: MobileNet-v2, SqueezeNet, and GoogLeNet. Initially, test features are computed from fine-tuned deep CNN models. Subsequently, probability scores for each class are derived by training and testing a random forest classifier with features extracted from the models. Then, the proposed method uses an average ensemble voting technique on the probability scores to enhance the classification performance compared to the individual models. The proposed of lightweight CNN model demonstrated an accuracy of 85.19 % which is better than existing works.
DOI:10.1109/WiSPNET61464.2024.10532923