StainPIDR: A Pathological Image Decouplingand Reconstruction Method for Stain Normalization Based on Color Vector Quantization and Structure Restaining

TL;DR

StainPIDR is a novel stain normalization method for pathological images that decouples structure and color features, then restains structures with target colors using color vector quantization and cross-attention, improving consistency across images.

Contribution

The paper introduces StainPIDR, a new approach combining color vector quantization and structure restaining for effective stain normalization in pathology images.

Findings

Effective stain normalization demonstrated in extensive experiments.

Template image selection algorithm improves normalization performance.

Method outperforms existing techniques in maintaining image structure and color consistency.

Abstract

The color appearance of a pathological image is highly related to the imaging protocols, the proportion of different dyes, and the scanning devices. Computer-aided diagnostic systems may deteriorate when facing these color-variant pathological images. In this work, we propose a stain normalization method called StainPIDR. We try to eliminate this color discrepancy by decoupling the image into structure features and vector-quantized color features, restaining the structure features with the target color features, and decoding the stained structure features to normalized pathological images. We assume that color features decoupled by different images with the same color should be exactly the same. Under this assumption, we train a fixed color vector codebook to which the decoupled color features will map. In the restaining part, we utilize the cross-attention mechanism to efficiently stain the structure features. As the target color (decoupled from a selected template image) will also affect the performance of stain normalization, we further design a template image selection algorithm to select a template from a given dataset. In our extensive experiments, we validate the effectiveness of StainPIDR and the template image selection algorithm. All the results show that our method can perform well in the stain normalization task. The code of StainPIDR will be publicly available later.