Robust Prototypical Few-Shot Organ Segmentation with Regularized Neural-ODEs

TL;DR

This paper introduces R-PNODE, a novel few-shot organ segmentation method using Neural-ODEs that improves accuracy and robustness against adversarial attacks in medical image segmentation tasks.

Contribution

The paper proposes R-PNODE, a regularized Neural-ODE based approach that enhances few-shot segmentation accuracy and adversarial robustness over existing CNN-based methods.

Findings

R-PNODE outperforms baseline methods in multi-organ segmentation tasks.

R-PNODE demonstrates increased robustness against various adversarial attacks.

The method effectively constrains feature representations to improve generalization.

Abstract

Despite the tremendous progress made by deep learning models in image semantic segmentation, they typically require large annotated examples, and increasing attention is being diverted to problem settings like Few-Shot Learning (FSL) where only a small amount of annotation is needed for generalisation to novel classes. This is especially seen in medical domains where dense pixel-level annotations are expensive to obtain. In this paper, we propose Regularized Prototypical Neural Ordinary Differential Equation (R-PNODE), a method that leverages intrinsic properties of Neural-ODEs, assisted and enhanced by additional cluster and consistency losses to perform Few-Shot Segmentation (FSS) of organs. R-PNODE constrains support and query features from the same classes to lie closer in the representation space thereby improving the performance over the existing Convolutional Neural Network (CNN) based FSS methods. We further demonstrate that while many existing Deep CNN based methods tend to be extremely vulnerable to adversarial attacks, R-PNODE exhibits increased adversarial robustness for a wide array of these attacks. We experiment with three publicly available multi-organ segmentation datasets in both in-domain and cross-domain FSS settings to demonstrate the efficacy of our method. In addition, we perform experiments with seven commonly used adversarial attacks in various settings to demonstrate R-PNODE's robustness. R-PNODE outperforms the baselines for FSS by significant margins and also shows superior performance for a wide array of attacks varying in intensity and design.