Loading [MathJax]/extensions/MathMenu.js
Early Detection of Melanoma Disease with Artificial Intelligence-Driven Skin Cancer Diagnosis Using Deep Learning Approach | IEEE Conference Publication | IEEE Xplore

Early Detection of Melanoma Disease with Artificial Intelligence-Driven Skin Cancer Diagnosis Using Deep Learning Approach


Abstract:

Melanoma, a type of skin cancer originating in the pigment-producing cells (melanocytes), poses a significant public health concern due to its aggressive nature and poten...Show More

Abstract:

Melanoma, a type of skin cancer originating in the pigment-producing cells (melanocytes), poses a significant public health concern due to its aggressive nature and potential for metastasis if left untreated. Early detection is pivotal for effective intervention and improved patient outcomes. Traditional methods of diagnosing skin cancer often rely on examinations by dermatologists, which can be subjective and lead to delays in treatment. To address this challenge, the proposed study presents a novel approach utilizing artificial intelligence (AI) powered by deep learning models for the early diagnosis of melanoma, aiming to enhance diagnostic accuracy and facilitate timely medical intervention. The model was trained using the ISIC 2018 skin challenge dataset which includes both malignant and benign skin disease images. The proposed model applied the U-Net algorithm with ResNet50 and VGG16 as Backbone to train the annotated images and Convolutional Neural Network (CNN) to extract intricate features from skin lesion images. The incorporation of Artificial Intelligence does not only speed up the diagnostic process but also reduces subjective variations in assessments. The model was evaluated using various performance metrics to determine the accuracy of the model. The results showed promising outcomes with accuracy rates of 92% for U-Net, 87% for ResNet50, and 88% for VGG16 in early-stage melanoma detection. The developed model serves as a tool for dermatologists by facilitating early detection and intervention of melanoma disease. The research indicates that using AI technology to detect skin cancer has the potential to greatly enhance the accuracy of diagnoses thereby improving outcomes by enabling effective medical interventions.
Date of Conference: 24-26 July 2024
Date Added to IEEE Xplore: 23 October 2024
ISBN Information:
Conference Location: Trichirappalli, India

I. Introduction

Skin cancer, particularly melanoma, presents a growing global health challenge, emphasizing the critical need for early detection to improve patient outcomes. Melanoma is a serious form of skin cancer that originates in the melanocytes, the cells responsible for producing melanin, the pigment that gives skin its color. It is known for its ability to spread rapidly to other parts of the body if not detected and treated early. Melanoma often manifests as a change in an existing mole or as a new, unusual-looking growth on the skin. Risk factors include excessive exposure to ultraviolet (UV) radiation from the sun or tanning beds, having a fair complexion, a history of sunburns, and a family history of the disease [1]. Early detection through regular skin checks and prompt medical attention is crucial for effective treatment and improving survival rates. Recent advancements in artificial intelligence (AI) and deep learning have paved the way for innovative solutions in healthcare, such as AI-powered models for early skin cancer diagnosis [2]. This study aims to integrate deep learning algorithms into dermatology to establish an efficient system for detecting melanoma in its early stages. Melanoma, originating from pigment-producing melanocytes is renowned for its aggressive nature; however, early identification significantly enhances treatment prospects and patient outcomes [3]. The proposed AI-powered model for skin cancer diagnosis leverages learning techniques to analyze high-resolution dermatoscopic images, capturing lesion details crucial for diagnosis. Trained on a dataset of such images, the deep learning model discerns intricate patterns indicative of melanoma, providing a powerful diagnostic tool. AI integration in melanoma detection offers the potential to expedite diagnostics, leading to earlier interventions and improved outcomes, while bolstering diagnostic accuracy and supporting healthcare decision-making [4]. This automated approach to early melanoma detection using advanced AI techniques addresses the time-consuming and error-prone nature of manual examination methods [5]. Through image preprocessing steps and deep learning-based Convolutional Neural Networks, the system accurately extracts features from skin lesion images, facilitating early melanoma detection with enhanced efficiency and accuracy [6]. The system's advantages over traditional methods include error reduction, faster diagnosis, and robust detection mechanisms, ultimately contributing to improved patient care [7].

References

References is not available for this document.