Stain Normalization of Hematology Slides using Neural Color Transfer

TL;DR

This paper introduces a neural color transfer method to normalize hematology slide images, enhancing deep learning model robustness and accuracy in detecting white blood cells across variable samples.

Contribution

It presents a novel neural color transfer approach for stain normalization, improving deep learning inference on hematology slides with color variability.

Findings

Significant improvement in WBC detection accuracy after normalization

Neural color transfer effectively reduces staining variability

Enhances robustness of deep learning models in pathology imaging

Abstract

Deep learning is popularly used for analyzing pathology images, but variations in image properties can limit the effectiveness of the models. The study aims to develop a method that transfers the variability present in the training set to unseen images, improving the model's ability to make accurate inferences. YOLOv5 was trained on peripheral blood and bone marrow sample images and Neural Color Transfer techniques were used to incorporate invariance. The results showed significant improvement in detecting WBCs from untrained samples after normalization, highlighting the potential of deep learning-based normalization techniques for inference robustness.