Ultra-high-resolution unpaired stain transformation via Kernelized Instance Normalization

TL;DR

This paper introduces Kernelized Instance Normalization (KIN), a novel method for ultra-high-resolution unpaired stain transformation in histopathology images, achieving state-of-the-art results with constant GPU memory usage.

Contribution

The paper presents KIN, a new normalization technique that preserves local information and enables seamless, high-resolution stain translation without re-training or high memory demands.

Findings

KIN achieves state-of-the-art stain transformation performance.

It can be integrated into existing frameworks easily.

The method generalizes well to high-resolution natural images.

Abstract

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