论文标题
使用潜在的自动编码器来代表非黑色素瘤皮肤癌
Representation Learning for Non-Melanoma Skin Cancer using a Latent Autoencoder
论文作者
论文摘要
生成学习是代表学习的强大工具，并显示出对生物医学成像中问题的特殊希望。但是，在这种情况下，从分布中进行的采样是找到真实图像的表示的次要的，这些图像通常带有标签并明确表示目标分布的内容和质量。从生成模型，尤其是像组织学图像一样复杂的生成模型中，忠实地重建图像仍然很难。在这项工作中，将两种现有方法（自动编码器和对抗性潜在自动编码器）组合在一起，以提高我们编码和解码非黑色素瘤皮肤癌的真实图像的能力，特别是表皮内癌（IEC）。这项工作利用IEC高质量图像的数据集（256 x 256）评估了图像重建质量和表示学习的结果。结果表明，对抗训练可以将基线FID得分从76提高到50，并且代表学习的基准可以提高3％。还首次提出了形态结构变化的平稳和现实的插值，将表示表示为计算病理学的有希望的方向。
Generative learning is a powerful tool for representation learning, and shows particular promise for problems in biomedical imaging. However, in this context, sampling from the distribution is secondary to finding representations of real images, which often come with labels and explicitly represent the content and quality of the target distribution. It remains difficult to faithfully reconstruct images from generative models, particularly those as complex as histological images. In this work, two existing methods (autoencoders and adversarial latent autoencoders) are combined in attempt to improve our ability to encode and decode real images of non-melanoma skin cancer, specifically intra-epidermal carcinoma (IEC). Utilising a dataset of high-quality images of IEC (256 x 256), this work assesses the result of both image reconstruction quality and representation learning. It is shown that adversarial training can improve baseline FID scores from 76 to 50, and that benchmarks on representation learning can be improved by up to 3%. Smooth and realistic interpolations of the variation in the morphological structure are also presented for the first time, positioning representation learning as a promising direction in the context of computational pathology.
