# Dealing with Topological Information within a Fully Convolutional Neural Network

## TL;DR

This paper introduces a method to incorporate topological information into fully convolutional neural networks for histological image segmentation by using a geodesic operator as a pre-processing step.

## Contribution

The paper proposes a novel pre-processing technique with a geodesic operator to enable CNNs to utilize global topological information.

## Key findings

- Improved segmentation accuracy on histological images.
- Effective integration of topological data into CNNs.
- Demonstrated applicability to Whole Slide Imaging data.

## Abstract

A fully convolutional neural network has a receptive field of limited size and therefore cannot exploit global information, such as topological information. A solution is proposed in this paper to solve this problem, based on pre-processing with a geodesic operator. It is applied to the segmentation of histological images of pigmented reconstructed epidermis acquired via Whole Slide Imaging.