# Reducing the Hausdorff Distance in Medical Image Segmentation with Convolutional Neural Networks

## TL;DR

This paper introduces novel loss functions for CNN-based medical image segmentation that directly aim to reduce the Hausdorff Distance, significantly improving boundary accuracy without compromising other segmentation metrics.

## Contribution

The paper proposes three innovative loss functions to directly minimize Hausdorff Distance in CNN training for medical image segmentation, a novel approach compared to traditional methods.

## Key findings

- Achieved 18-45% reduction in Hausdorff Distance
- Maintained Dice similarity coefficient performance
- Validated on ultrasound, MRI, and CT images

## Abstract

The Hausdorff Distance (HD) is widely used in evaluating medical image segmentation methods. However, existing segmentation methods do not attempt to reduce HD directly. In this paper, we present novel loss functions for training convolutional neural network (CNN)-based segmentation methods with the goal of reducing HD directly. We propose three methods to estimate HD from the segmentation probability map produced by a CNN. One method makes use of the distance transform of the segmentation boundary. Another method is based on applying morphological erosion on the difference between the true and estimated segmentation maps. The third method works by applying circular/spherical convolution kernels of different radii on the segmentation probability maps. Based on these three methods for estimating HD, we suggest three loss functions that can be used for training to reduce HD. We use these loss functions to train CNNs for segmentation of the prostate, liver, and pancreas in ultrasound, magnetic resonance, and computed tomography images and compare the results with commonly-used loss functions. Our results show that the proposed loss functions can lead to approximately 18-45 % reduction in HD without degrading other segmentation performance criteria such as the Dice similarity coefficient. The proposed loss functions can be used for training medical image segmentation methods in order to reduce the large segmentation errors.