Multi-scale fully convolutional neural networks for histopathology image segmentation: from nuclear aberrations to the global tissue architecture

Abstract

Histopathologic diagnosis is dependent on simultaneous information from a broad range of scales, ranging from nuclear aberrations (≈ O(0.1 μm)) over cellular structures (≈ O(10 μm)) to the global tissue architecture (􏰀 O(1mm)). Bearing in mind which information is employed by human pathologists, we introduce and examine different strategies for the integration of multiple and widely separate spatial scales into common U-Net-based architectures. Based on this, we present a family of new, end-to-end trainable, multi-scale multi-encoder fully-convolutional neural networks for human modus operandi-inspired computer vision in histopathology.