BriefGPT.xyz
Dec, 2023
利用非配对生成对抗网络实现组织切片图像的可编辑染色转换
Editable Stain Transformation Of Histological Images Using Unpaired GANs
HTML
PDF
Tibor Sloboda, Lukáš Hudec, Wanda Benešová
TL;DR
引入了结合可解释性特征和保存结构能力的xAI-CycleGAN先进架构，用于将H&E染色的乳腺组织图像转换成类似P63染色的图像，并展示了其在保持结构完整性和生成高质量图像方面的有效性，验证了该模型的高质量输出。
Abstract
double staining
in histopathology, particularly for
metaplastic breast cancer
, typically employs H&E and P63 dyes. However, P63's tissue damage and high cost necessitate alternative methods. This study introduces
→