论文标题
超高分辨率的未配对的污渍转化通过核心实例归一化
Ultra-high-resolution unpaired stain transformation via Kernelized Instance Normalization
论文作者
论文摘要
虽然苏木精和曙红（H＆E）是标准染色程序，但免疫组织化学（IHC）染色进一步用作诊断和预后方法。但是，获得特殊的染色结果需要大量成本。 因此，我们提出了一种超高分辨率不配对的图像到图像翻译的策略：内核实例归一化（KIN），该策略保留了局部信息并成功地实现了使用恒定的GPU存储器使用的无缝染色转换。给定补丁，相应的位置和一个内核，Kin使用卷积操作计算本地统计。此外，Kin可以轻松地插入当前开发的大多数框架中，而无需重新训练。 我们证明，亲属通过在三个流行的框架中用亲属层替换实例归一化（以层为单位）来实现最新的染色转换，并在两个组织病理学数据集中进行测试。此外，我们以高分辨率的自然图像表现出亲属的普遍性。最后，使用人类评估和几个客观指标来比较不同方法的性能。 总体而言，这是对超高分辨率未配对的图像到图像翻译的首次成功研究，并具有恒定的空间复杂性。代码可用：https：//github.com/kaminyou/urust
While hematoxylin and eosin (H&E) is a standard staining procedure, immunohistochemistry (IHC) staining further serves as a diagnostic and prognostic method. However, acquiring special staining results requires substantial costs. Hence, we proposed a strategy for ultra-high-resolution unpaired image-to-image translation: Kernelized Instance Normalization (KIN), which preserves local information and successfully achieves seamless stain transformation with constant GPU memory usage. Given a patch, corresponding position, and a kernel, KIN computes local statistics using convolution operation. In addition, KIN can be easily plugged into most currently developed frameworks without re-training. We demonstrate that KIN achieves state-of-the-art stain transformation by replacing instance normalization (IN) layers with KIN layers in three popular frameworks and testing on two histopathological datasets. Furthermore, we manifest the generalizability of KIN with high-resolution natural images. Finally, human evaluation and several objective metrics are used to compare the performance of different approaches. Overall, this is the first successful study for the ultra-high-resolution unpaired image-to-image translation with constant space complexity. Code is available at: https://github.com/Kaminyou/URUST
