Gaussian Process Emulators for Few-Shot Segmentation in Cardiac MRI

TL;DR

This paper introduces a novel few-shot learning approach for cardiac MRI segmentation that combines U-Net, Gaussian Process Emulators, and support set data to improve segmentation accuracy with limited labeled data.

Contribution

The work presents a new method integrating GPEs with few-shot learning and U-Net for cardiac MRI segmentation, enhancing performance with small support sets.

Findings

Higher DICE coefficients than state-of-the-art methods

Effective segmentation with small support sets

Improved performance in challenging orientations

Abstract

Segmentation of cardiac magnetic resonance images (MRI) is crucial for the analysis and assessment of cardiac function, helping to diagnose and treat various cardiovascular diseases. Most recent techniques rely on deep learning and usually require an extensive amount of labeled data. To overcome this problem, few-shot learning has the capability of reducing data dependency on labeled data. In this work, we introduce a new method that merges few-shot learning with a U-Net architecture and Gaussian Process Emulators (GPEs), enhancing data integration from a support set for improved performance. GPEs are trained to learn the relation between the support images and the corresponding masks in latent space, facilitating the segmentation of unseen query images given only a small labeled support set at inference. We test our model with the M&Ms-2 public dataset to assess its ability to segment the heart in cardiac magnetic resonance imaging from different orientations, and compare it with state-of-the-art unsupervised and few-shot methods. Our architecture shows higher DICE coefficients compared to these methods, especially in the more challenging setups where the size of the support set is considerably small.