Quantifying the effects of data augmentation and stain color normalization in convolutional neural networks for computational pathology
This work addresses generalization issues in pathology image analysis across different laboratories, providing practical guidelines for stain handling, though it is incremental in comparing existing techniques.
The study tackled the problem of stain variation in computational pathology by comparing data augmentation and normalization techniques, finding that stain color augmentation improved classification performance by up to 15% in cross-laboratory tests. It also proposed a novel unsupervised neural network method for stain normalization.
Stain variation is a phenomenon observed when distinct pathology laboratories stain tissue slides that exhibit similar but not identical color appearance. Due to this color shift between laboratories, convolutional neural networks (CNNs) trained with images from one lab often underperform on unseen images from the other lab. Several techniques have been proposed to reduce the generalization error, mainly grouped into two categories: stain color augmentation and stain color normalization. The former simulates a wide variety of realistic stain variations during training, producing stain-invariant CNNs. The latter aims to match training and test color distributions in order to reduce stain variation. For the first time, we compared some of these techniques and quantified their effect on CNN classification performance using a heterogeneous dataset of hematoxylin and eosin histopathology images from 4 organs and 9 pathology laboratories. Additionally, we propose a novel unsupervised method to perform stain color normalization using a neural network. Based on our experimental results, we provide practical guidelines on how to use stain color augmentation and stain color normalization in future computational pathology applications.