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:
this https URL

使用现代深度学习方法和可解释人工智能（XAI）来解决皮肤癌检测问题，采用四个先进的预训练模型进行皮肤病变分类，XceptionNet 被确定为表现最佳的模型，本研究展示了深度学习和可解释人工智能（XAI）如何改善皮肤癌诊断，为医学图像分析领域未来的发展奠定了基础。

皮肤癌分类的可解释深度学习方法

An Interpretable Deep Learning Approach for Skin Cancer Categorization

To improve the recognition ability of computer-aided breast mass
classification among mammographic images, in this work we explore the
state-of-the-art classification networks to develop an ensemble mechanism.
First, the regions of interest (ROIs) are obtained from the original dataset,
and then three models, i.e., XceptionNet, DenseNet, and EfficientNet, are
trained individually. After training, we ensemble the mechanism by summing the
probabilities outputted from each network which enhances the performance up to
5%. The scheme has been validated on a public dataset and we achieved accuracy,
precision, and recall 88%, 85%, and 76% respectively.

本研究探索了三种分类网络，即 XceptionNet、DenseNet 和 EfficientNet，通过集成机制来提高计算机辅助乳腺肿块分类的识别能力。在公共数据集上验证该方案，可以获得 88％的准确度，85％的精度和 76％的召回率。