Skin Cancer Detection Using Convolutional Neural Networks

• Author(s): Arunperiyakaruppan A; Senthilkumar E; M. Barath Kesavan
• Paper ID: 1717853
• Page: 2160-2162
• Published Date: 18-05-2026
• Published In: Iconic Research And Engineering Journals
• Publisher: IRE Journals
• e-ISSN: 2456-8880
• Volume/Issue: Volume 9 Issue 11 May-2026

Abstract

Skin cancer is one of the most dangerous and rapidly spreading diseases across the world. Early-stage diagnosis plays a major role in improving patient survival and reducing treatment cost. Traditional diagnosis techniques depend heavily on dermatologist expertise and laboratory testing, which often increases diagnosis time and reduces accessibility in rural healthcare environments. This project presents an AI-powered skin cancer detection system using Convolutional Neural Networks (CNN) and Region-Based CNN (R-CNN) models for accurate lesion classification and localization. The proposed system analyses dermoscopic images, identifies suspicious lesion regions, and predicts whether the lesion is benign, malignant, or melanoma. TensorFlow.js is used for browser-based AI inference, while Google Apps Script and Google Sheets are used for cloud-based storage and report management. Experimental testing shows that the proposed R-CNN approach improves lesion localization and prediction accuracy compared to traditional CNN-based systems. The project provides a lightweight, scalable, and accessible healthcare solution suitable for hospitals, clinics, and remote healthcare centers.

Citations

IRE Journals:
Arunperiyakaruppan A, Senthilkumar E, M. Barath Kesavan "Skin Cancer Detection Using Convolutional Neural Networks" Iconic Research And Engineering Journals Volume 9 Issue 11 2026 Page 2160-2162

IEEE:
Arunperiyakaruppan A, Senthilkumar E, M. Barath Kesavan "Skin Cancer Detection Using Convolutional Neural Networks" Iconic Research And Engineering Journals, 9(11)