Chaos-Enhanced Prototypical Networks for Few-Shot Medical Image Classification

TL;DR

This paper introduces Chaos-Enhanced Prototypical Networks, which incorporate chaotic perturbations into feature embeddings to improve few-shot medical image classification accuracy and stability.

Contribution

The work proposes a novel chaos-based regularization method integrated into Prototypical Networks to enhance robustness against noise and intra-class variance in medical imaging tasks.

Findings

Achieved 84.52% peak accuracy on brain tumor classification.

Chaotic perturbation at 15% level stabilized high-dimensional feature clusters.

Method outperformed standard ProtoNet with minimal computational overhead.

Abstract

The scarcity of labeled clinical data in oncology makes Few-Shot Learning (FSL) a critical framework for Computer Aided Diagnostics, but we observed that standard Prototypical Networks often struggle with the "prototype instability" caused by morphological noise and high intra-class variance in brain tumor scans. Our work attempts to minimize this by integrating a non-linear Logistic Chaos Module into a fine-tuned ResNet-18 backbone creating the Chaos-Enhanced ProtoNet(CE-ProtoNet). Using the deterministic ergodicity of the logistic chaos map we inject controlled perturbations into support features during episodic training-essentially for "stress testing" the embedding space. This process makes the model to converge on noise-invariant representations without increasing computational overhead. Testing this on a 4-way 5-shot brain tumor classification task, we found that a 15% chaotic injection level worked efficiently to stabilize high-dimensional clusters and reduce class dispersion. Our method achieved a peak test accuracy of 84.52%, outperforming standard ProtoNet. Our results suggest the idea of using chaotic perturbation as an efficient, low-overhead regularization tool, for the data-scarce regimes.