CateNorm: Categorical Normalization for Robust Medical Image Segmentation

TL;DR

CateNorm introduces a novel normalization method that leverages foreground categorical statistics to improve the robustness and accuracy of medical image segmentation across diverse datasets.

Contribution

The paper proposes CateNorm, a new normalization strategy that focuses on foreground pixel statistics, enhancing segmentation performance and domain invariance.

Findings

Achieves precise segmentation across five diverse datasets.

Demonstrates robustness to complex and variable data distributions.

Captures domain-invariant features from multiple medical data sources.

Abstract

Batch normalization (BN) uniformly shifts and scales the activations based on the statistics of a batch of images. However, the intensity distribution of the background pixels often dominates the BN statistics because the background accounts for a large proportion of the entire image. This paper focuses on enhancing BN with the intensity distribution of foreground pixels, the one that really matters for image segmentation. We propose a new normalization strategy, named categorical normalization (CateNorm), to normalize the activations according to categorical statistics. The categorical statistics are obtained by dynamically modulating specific regions in an image that belong to the foreground. CateNorm demonstrates both precise and robust segmentation results across five public datasets obtained from different domains, covering complex and variable data distributions. It is attributable to the ability of CateNorm to capture domain-invariant information from multiple domains (institutions) of medical data. Code is available at https://github.com/lambert-x/CateNorm.