Attention-Based Chaotic Self-Supervision for Medical Image Classification

TL;DR

This paper introduces a novel self-supervised learning method for medical image classification that uses chaotic transformations instead of masking, combined with an attentive fusion mechanism to improve feature robustness and classification accuracy.

Contribution

The paper proposes the Chaotic Denoising Autoencoder (CDAE) with an attentive fusion mechanism, offering a new SSL pre-training strategy that preserves diagnostic features better than traditional masking methods.

Findings

Achieved 0.9221 accuracy on ISIC 2018 dataset.

Attained 0.8644 accuracy on APTOS 2019 dataset.

Demonstrated improved feature robustness and classification performance.

Abstract

Deep learning models for medical image classification usually achieve promising results but typically rely on large, annotated datasets or standard transfer learning from ImageNet. Self-Supervised Learning (SSL) has emerged as a powerful alternative, yet common methods like masked autoencoders (MAEs) may inadvertently destroy fine-grained diagnostic features by using random masking. In this paper, we propose a novel SSL pre-training strategy, the Chaotic Denoising Autoencoder (CDAE). Instead of masking, we apply a chaotic transformation to the input image, tasking an autoencoder to reconstruct the original. We hypothesize this forces the encoder to learn robust, domain-specific features by "inverting the chaos". Furthermore, we propose an attentive fusion mechanism that combines features from our CDAE-trained encoder with a standard encoder, leveraging the strengths of both general and domain-specific representations. Our method is evaluated on two public medical datasets: ISIC 2018 (skin lesions) and APTOS 2019 (diabetic retinopathy). The proposed model achieves high performance, with an accuracy of 0.9221 and an F1-macro of 0.8530 on ISIC 2018, and an accuracy of 0.8644 and F1-macro of 0.7433 on APTOS 2019, demonstrating the efficacy of our approach.