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 employ a one-step diffusion model as the generator and fine-tune it with LoRA adapters using adversarial learning objectives. To ensure that the model effectively captures both global structural information and local details, we propose a multi-scale feature fusion (MFF) module. This module utilizes two VAE encoders to extract features of varying image sizes and performs feature fusion before feeding them into the UNet. Furthermore, we utilize a pre-trained vision-language model for histopathology as the backbone for the discriminator to further improve performance We conducted FF-to-FFPE translation experiments on the TCGA-NSCLC datasets, and our method achieved better performance compared to other methods. The code and models are released at https://github.com/QilaiZhang/Diffusion-FFPE.

翻译：组织病理学中苏木精-伊红（H&E）切片主要有两种类型：福尔马林固定石蜡包埋（FFPE）切片和新鲜冷冻（FF）切片。FFPE切片能提供高质量的组织病理学图像，但其制备过程需要耗费大量人力。相比之下，FF切片可以快速制备，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，从而提升用于诊断的图像质量。本文提出Diffusion-FFPE方法，利用预训练扩散模型实现FF至FFPE组织病理学图像转换。具体而言，我们采用一步式扩散模型作为生成器，并基于对抗学习目标通过LoRA适配器进行微调。为确保模型有效捕获全局结构信息和局部细节，我们提出多尺度特征融合（MFF）模块。该模块利用两个VAE编码器提取不同尺寸的图像特征，并在输入UNet前进行特征融合。此外，我们采用预训练的病理学视觉语言模型作为判别器主干网络以进一步提升性能。我们在TCGA-NSCLC数据集上进行了FF至FFPE转换实验，结果表明本方法相比其他方法取得了更优的性能。代码与模型已发布于https://github.com/QilaiZhang/Diffusion-FFPE。