CateNorm: Categorical Normalization for Robust Medical Image Segmentation
This work addresses a domain-specific bottleneck in medical image segmentation by improving normalization for foreground pixels, offering incremental gains over standard batch normalization.
The paper tackles the problem of batch normalization being dominated by background pixels in medical image segmentation, proposing CateNorm to normalize activations based on foreground categorical statistics, achieving precise and robust results across five public datasets from different domains.
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.