[论文解读] A Web-based Mpox Skin Lesion Detection System Using State-of-the-art Deep Learning Models Considering Racial Diversity

Shams Nafisa Ali, Md. Tazuddin Ahmed+6 more|arXiv (Cornell University)|Jun 25, 2023

Poxvirus research and outbreaks被引用 10

一句话总结

本文提出一个基于网页的 mpox 皮肤病变检测器，在多种深度学习模型上对多样化数据集（MSLD v2.0）进行基准测试，并使用颜色空间增强和迁移学习来提升性能，达到 83.59% 的准确率。

ABSTRACT

The recent 'Mpox' outbreak, formerly known as 'Monkeypox', has become a significant public health concern and has spread to over 110 countries globally. The challenge of clinically diagnosing mpox early on is due, in part, to its similarity to other types of rashes. Computer-aided screening tools have been proven valuable in cases where Polymerase Chain Reaction (PCR) based diagnosis is not immediately available. Deep learning methods are powerful in learning complex data representations, but their efficacy largely depends on adequate training data. To address this challenge, we present the "Mpox Skin Lesion Dataset Version 2.0 (MSLD v2.0)" as a follow-up to the previously released openly accessible dataset, one of the first datasets containing mpox lesion images. This dataset contains images of patients with mpox and five other non-mpox classes (chickenpox, measles, hand-foot-mouth disease, cowpox, and healthy). We benchmark the performance of several state-of-the-art deep learning models, including VGG16, ResNet50, DenseNet121, MobileNetV2, EfficientNetB3, InceptionV3, and Xception, to classify mpox and other infectious skin diseases. In order to reduce the impact of racial bias, we utilize a color space data augmentation method to increase skin color variability during training. Additionally, by leveraging transfer learning implemented with pre-trained weights generated from the HAM10000 dataset, an extensive collection of pigmented skin lesion images, we achieved the best overall accuracy of $83.59\pm2.11\%$. Finally, the developed models are incorporated within a prototype web application to analyze uploaded skin images by a user and determine whether a subject is a suspected mpox patient.

研究动机与目标

• 解决 mpox（猴痘）在与其他皮疹相似导致的诊断挑战。
• 使用深度学习开发一个用于快速、非 PCR 辅助筛查的基于网页的工具。
• 创建并使用 Mpox Skin Lesion Dataset Version 2.0（MSLD v2.0），包含 mpox 与非 mpox 类别。
• 通过增加皮肤颜色变异性的数据增强来减轻种族偏见。
• 利用来自 HAM10000 的迁移学习提升模型性能。

提出的方法

• 基准测试多种 CNN 架构：VGG16、ResNet50、DenseNet121、MobileNetV2、EfficientNetB3、InceptionV3、Xception。
• 在训练中使用颜色空间数据增强以增加皮肤颜色变异性。
• 使用来自 HAM10000 色素性皮肤病变数据集的预训练权重进行迁移学习。
• 在 MSLD v2.0（mpox、 chickenpox、 measles、 hand‑foot‑mouth disease、 cowpox、 healthy）上训练和评估模型。
• 将表现最佳的模型整合到用于上传图像分析的原型网页应用中。

实验结果

研究问题

• RQ1 先进的 CNN 模型是否能在多样化数据集上有效将 mpox 与其他传染性皮肤病区分？
• RQ2 颜色空间数据增强是否降低种族偏见并改善不同肤色的性能？
• RQ3 来自 HAM10000 的迁移学习在多大程度上提升了 mpox 相关的分类准确率？
• RQ4 在用于用户上传皮肤图像的网页原型环境中，最佳模型的表现如何？

主要发现

• 最高整体准确率为 83.59%，标准差为 ±2.11%。
• MSLD v2.0 数据集包含 mpox 和五个非 mpox 类别（水痘、麻疹、手足口病、牛痘、健康）。
• 在训练中使用颜色空间增强以增加皮肤颜色变异性，减轻种族偏见。
• 使用 HAM10000 预训练权重的迁移学习有助于提升性能。
• 将模型整合到分析上传皮肤图像以检测疑似 mpox 的网页应用原型中。