Scale-Equivariant UNet for Histopathology Image Segmentation
This addresses the challenge of scale invariance in medical image analysis for histopathology, offering a more efficient solution for nuclei and tissue segmentation.
The paper tackles the problem of convolutional neural networks failing to generalize across different scales in histopathology image segmentation by proposing a scale-equivariant UNet that uses trainable Gaussian basis filters, resulting in outperforming other methods with fewer parameters.
Digital histopathology slides are scanned and viewed under different magnifications and stored as images at different resolutions. Convolutional Neural Networks (CNNs) trained on such images at a given scale fail to generalise to those at different scales. This inability is often addressed by augmenting training data with re-scaled images, allowing a model with sufficient capacity to learn the requisite patterns. Alternatively, designing CNN filters to be scale-equivariant frees up model capacity to learn discriminative features. In this paper, we propose the Scale-Equivariant UNet (SEUNet) for image segmentation by building on scale-space theory. The SEUNet contains groups of filters that are linear combinations of Gaussian basis filters, whose scale parameters are trainable but constrained to span disjoint scales through the layers of the network. Extensive experiments on a nuclei segmentation dataset and a tissue type segmentation dataset demonstrate that our method outperforms other approaches, with much fewer trainable parameters.