用GAN生成皮肤病变图像，提升模型分类性能并增强可解释性。
Synthetic Generation of Dermatoscopic Images with GAN and Closed-Form Factorization
- 基于GAN潜空间控制生成皮肤病变图像的语义变化
- 在HAM10000数据集上超越非集成模型基准表现
- 适合医学图像增强与模型可解释性研究者
在皮肤病变诊断中，皮肤病灶的皮肤镜和显微图像分析对早期准确诊断至关重要，但构建多样且高质量的标注数据集成本高昂，制约了机器学习模型的准确性与泛化能力。本文提出一种创新的无监督数据增强方法，利用生成对抗网络（GAN）及其潜空间技术，半自动发现并生成皮肤镜图像中的可控语义变化，生成合成图像以扩充训练数据。该方法显著提升了机器学习模型性能，在HAM10000数据集上创下非集成模型的新基准。同时，通过分析生成结果与模型行为，进一步验证了方案的有效性，并支持了模型可解释性研究。
原文摘要 · Abstract (English)
In the realm of dermatological diagnoses, where the analysis of dermatoscopic and microscopic skin lesion images is pivotal for the accurate and early detection of various medical conditions, the costs associated with creating diverse and high-quality annotated datasets have hampered the accuracy and generalizability of machine learning models. We propose an innovative unsupervised augmentation solution that harnesses Generative Adversarial Network (GAN) based models and associated techniques over their latent space to generate controlled semiautomatically-discovered semantic variations in dermatoscopic images. We created synthetic images to incorporate the semantic variations and augmented the training data with these images. With this approach, we were able to increase the performance of machine learning models and set a new benchmark amongst non-ensemble based models in skin lesion classification on the HAM10000 dataset; and used the observed analytics and generated models for detailed studies on model explainability, affirming the effectiveness of our solution.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。