Image Translation Based Nuclei Segmentation for Immunohistochemistry Images

TL;DR

This paper introduces a GAN-based image translation method to convert IHC images into virtual H&E images, enabling the use of existing nuclei segmentation models for improved accuracy in immunohistochemistry image analysis.

Contribution

The paper presents a novel GAN approach for IHC to H&E image translation, enhancing nuclei segmentation performance on IHC images compared to existing methods.

Findings

The proposed method outperforms baseline methods including Cellpose, HoVer-Net, and DeepLIIF.

Virtual H&E images enable more accurate nuclei segmentation on IHC images.

The approach is validated on two public IHC datasets.

Abstract

Numerous deep learning based methods have been developed for nuclei segmentation for H&E images and have achieved close to human performance. However, direct application of such methods to another modality of images, such as Immunohistochemistry (IHC) images, may not achieve satisfactory performance. Thus, we developed a Generative Adversarial Network (GAN) based approach to translate an IHC image to an H&E image while preserving nuclei location and morphology and then apply pre-trained nuclei segmentation models to the virtual H&E image. We demonstrated that the proposed methods work better than several baseline methods including direct application of state of the art nuclei segmentation methods such as Cellpose and HoVer-Net, trained on H&E and a generative method, DeepLIIF, using two public IHC image datasets.