Unsupervised Segmentation of Micro-CT Scans of Polyurethane Structures By Combining Hidden-Markov-Random Fields and a U-Net

TL;DR

This paper introduces an unsupervised segmentation method combining Hidden Markov Random Fields and a U-Net CNN, achieving high accuracy on Micro-CT scans of polyurethane structures without needing extensive labeled data.

Contribution

It presents a novel integration of HMRF theory with CNNs for unsupervised segmentation, reducing reliance on ground-truth data and improving speed and accuracy.

Findings

HMRF-UNet achieves high segmentation accuracy without ground truth.

Pre-training strategy significantly reduces labeled data requirements.

The method effectively segments Micro-CT images of polyurethane foam.

Abstract

Extracting digital material representations from images is a necessary prerequisite for a quantitative analysis of material properties. Different segmentation approaches have been extensively studied in the past to achieve this task, but were often lacking accuracy or speed. With the advent of machine learning, supervised convolutional neural networks (CNNs) have achieved state-of-the-art performance for different segmentation tasks. However, these models are often trained in a supervised manner, which requires large labeled datasets. Unsupervised approaches do not require ground-truth data for learning, but suffer from long segmentation times and often worse segmentation accuracy. Hidden Markov Random Fields (HMRF) are an unsupervised segmentation approach that incorporates concepts of neighborhood and class distributions. We present a method that integrates HMRF theory and CNN segmentation, leveraging the advantages of both areas: unsupervised learning and fast segmentation times. We investigate the contribution of different neighborhood terms and components for the unsupervised HMRF loss. We demonstrate that the HMRF-UNet enables high segmentation accuracy without ground truth on a Micro-Computed Tomography (${\mu}$CT) image dataset of Polyurethane (PU) foam structures. Finally, we propose and demonstrate a pre-training strategy that considerably reduces the required amount of ground-truth data when training a segmentation model.