# Residual Pyramid FCN for Robust Follicle Segmentation

## TL;DR

This paper introduces a residual pyramid FCN architecture called Res-Seg-Net, enhancing follicle segmentation in histology images by capturing both major structures and details through hierarchical residual modules.

## Contribution

It presents a novel residual pyramid structure integrated into a U-Net based architecture for improved segmentation accuracy and robustness in histology image analysis.

## Key findings

- Enhanced segmentation accuracy over baseline models
- Robustness to variations in histology images
- Effective multi-resolution hierarchical approach

## Abstract

In this paper, we propose a pyramid network structure to improve the FCN-based segmentation solutions and apply it to label thyroid follicles in histology images. Our design is based on the notion that a hierarchical updating scheme, if properly implemented, can help FCNs capture the major objects, as well as structure details in an image. To this end, we devise a residual module to be mounted on consecutive network layers, through which pixel labels would be propagated from the coarsest layer towards the finest layer in a bottom-up fashion. We add five residual units along the decoding path of a modified U-Net to make our segmentation network, Res-Seg-Net. Experiments demonstrate that the multi-resolution set-up in our model is effective in producing segmentations with improved accuracy and robustness.