An Interpretable Deep Learning Approach for Skin Cancer Categorization

Faysal Mahmud, Md. Mahin Mahfiz, Md. Zobayer Ibna Kabir, Yusha Abdullah
12/17/2023
eess.IVcs.CV

Official code: Faysal-MD/An-Interpretable-Deep-Learning-Approach-for-Skin-Cancer-Categorization-IEEE2023 (11 stars, MIT, last commit 2024-05-27).

Abstract

Skin cancer is a serious worldwide health issue, precise and early detection is essential for better patient outcomes and effective treatment. In this research, we use modern deep learning methods and explainable artificial intelligence (XAI) approaches to address the problem of skin cancer detection. To categorize skin lesions, we employ four cutting-edge pre-trained models: XceptionNet, EfficientNetV2S, InceptionResNetV2, and EfficientNetV2M. Image augmentation approaches are used to reduce class imbalance and improve the generalization capabilities of our models. Our models decision-making process can be clarified because of the implementation of explainable artificial intelligence (XAI). In the medical field, interpretability is essential to establish credibility and make it easier to implement AI driven diagnostic technologies into clinical workflows. We determined the XceptionNet architecture to be the best performing model, achieving an accuracy of 88.72%. Our study shows how deep learning and explainable artificial intelligence (XAI) can improve skin cancer diagnosis, laying the groundwork for future developments in medical image analysis. These technologies ability to allow for early and accurate detection could enhance patient care, lower healthcare costs, and raise the survival rates for those with skin cancer. Source Code: https://github.com/Faysal-MD/An-Interpretable-Deep-Learning?Approach-for-Skin-Cancer-Categorization-IEEE2023

View on arXivView PDF

Code Implementations(1)

Faysal-MD/An-Interpretable-Deep-Learning-Approach-for-Skin-Cancer-Categorization-IEEE2023Official100%
MIT

Multiclass skin cancer detection using explainable AI for checking the models' robustness

116Jupyter Notebook2 years agoMIT
cnndeep-learningexplainable-aiham10000skin-cancer-detection

Similar Papers

Cancer-Net SCa-Synth: An Open Access Synthetically Generated 2D Skin Lesion Dataset for Skin Cancer Classification

92% match1 repo42024

Using Computer Vision for Skin Disease Diagnosis in Bangladesh Enhancing Interpretability and Transparency in Deep Learning Models for Skin Cancer Classification

91% match2025

Exploring the Challenge and Value of Deep Learning in Automated Skin Disease Diagnosis

91% match2025

A Deep Learning Approach for Automated Skin Lesion Diagnosis with Explainable AI

91% match2026

Enhancing Skin Disease Diagnosis: Interpretable Visual Concept Discovery with SAM

90% match2024

Comparison of Deep Learning and Machine Learning Models and Frameworks for Skin Lesion Classification

90% match2022

Cite this paper

@article{mahmud2023interpretable,
  title  = {An Interpretable Deep Learning Approach for Skin Cancer Categorization},
  author = {Faysal Mahmud and Md. Mahin Mahfiz and Md. Zobayer Ibna Kabir and Yusha Abdullah},
  year   = {2023},
  eprint = {2312.10696},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2312.10696v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2312.10696.svg)](https://codeofpaper.com/paper/2312.10696)

Discussion