Unpaired Modality Translation for Pseudo Labeling of Histology Images

TL;DR

This paper introduces an unsupervised image translation method to generate pseudo labels for histology image segmentation, reducing the need for manual annotations across different imaging modalities.

Contribution

It presents a novel microscopy pseudo labeling pipeline that translates between labeled and unlabeled domains without prior annotations, improving segmentation in diverse histology images.

Findings

Achieved a mean Dice score of 0.736 on SEM data using the tutoring path.

Effectively translated labeled datasets to target modalities for pseudo labeling.

Demonstrated improved segmentation performance across multiple dissimilar image domains.

Abstract

The segmentation of histological images is critical for various biomedical applications, yet the lack of annotated data presents a significant challenge. We propose a microscopy pseudo labeling pipeline utilizing unsupervised image translation to address this issue. Our method generates pseudo labels by translating between labeled and unlabeled domains without requiring prior annotation in the target domain. We evaluate two pseudo labeling strategies across three image domains increasingly dissimilar from the labeled data, demonstrating their effectiveness. Notably, our method achieves a mean Dice score of $0.736 \pm 0.005$ on a SEM dataset using the tutoring path, which involves training a segmentation model on synthetic data created by translating the labeled dataset (TEM) to the target modality (SEM). This approach aims to accelerate the annotation process by providing high-quality pseudo labels as a starting point for manual refinement.