利用预训练模型进行 FF 到 FFPE 组织病理学图像转换
Leveraging Pre-trained Models for FF-to-FFPE Histopathological Image Translation
AI总结：
本文提出 Diffusion-FFPE 方法，利用预训练单步扩散模型作为生成器并结合 LoRA 微调，引入多尺度特征融合模块和视觉语言模型判别器，实现 FF 到 FFPE 组织病理学图像转换，在 TCGA-NSCLC 数据集上优于现有方法。
摘要：
组织病理学中苏木精和伊红（H&E）切片的两种主要类型是福尔马林固定石蜡包埋（FFPE）和新鲜冷冻（FF）。FFPE 切片提供高质量的组织病理学图像，但获取过程费力。相比之下，FF 切片制备快，但图像质量相对较差。我们的任务是将 FF 图像转换为 FFPE 风格，从而提高用于诊断的图像质量。本文提出 Diffusion-FFPE，一种使用预训练扩散模型进行 FF 到 FFPE 组织病理学图像转换的方法。具体而言，我们利用单步扩散模型作为生成器，并在对抗学习框架内使用 LoRA 适配器对其进行微调。为使模型有效捕获全局结构模式和局部细节，我们引入多尺度特征融合模块，利用两个 VAE 编码器在不同图像分辨率下提取特征，在输入 UNet 前进行特征融合。此外，用于组织病理学的预训练视觉语言模型作为判别器的主干，增强模型性能。我们在 TCGA-NSCLC 数据集上的转换实验表明，所提方法优于现有方法。代码和模型已发布。
英文摘要：
The two primary types of Hematoxylin and Eosin (H&E) slides in histopathology are Formalin-Fixed Paraffin-Embedded (FFPE) and Fresh Frozen (FF). FFPE slides offer high quality histopathological images but require a labor-intensive acquisition process. In contrast, FF slides can be prepared quickly, but the image quality is relatively poor. Our task is to translate FF images into FFPE style, thereby improving the image quality for diagnostic purposes. In this paper, we propose Diffusion-FFPE, a method for FF-to-FFPE histopathological image translation using a pre-trained diffusion model. Specifically, we utilize a one-step diffusion model as the generator, which we fine-tune using LoRA adapters within an adversarial learning framework. To enable the model to effectively capture both global structural patterns and local details, we introduce a multi-scale feature fusion module that leverages two VAE encoders to extract features at different image resolutions, performing feature fusion before inputting them into the UNet. Additionally, a pre-trained vision-language model for histopathology serves as the backbone for the discriminator, enhancing model performance. Our FF-to-FFPE translation experiments on the TCGA-NSCLC dataset demonstrate that the proposed approach outperforms existing methods. The code and models are released at https://github.com/QilaiZhang/Diffusion-FFPE.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
