Adaptive Wavelet Filters as Practical Texture Feature Amplifiers for Parkinson's Disease Screening in OCT

2025-03-25

AI Summary

To address the need for early, non-invasive screening of Parkinson’s disease (PD), this paper proposes a deep learning framework for texture analysis of retinal optical coherence tomography (OCT) images. The method introduces three key innovations: (1) an adaptive wavelet filter (AWF) as a learnable texture enhancement module to improve sensitivity to subtle pathological textural patterns; (2) a novel feature extraction architecture integrating frequency-domain modeling with channel–token hybrid attention; and (3) a balanced confidence loss (BC Loss) that jointly optimizes predictive probabilities and class priors to enhance model calibration and reliability. Evaluated on a public OCT dataset, the proposed approach significantly outperforms state-of-the-art methods in classification accuracy, AUC, and uncertainty estimation. It establishes a new paradigm for interpretable, non-invasive PD auxiliary screening grounded in retinal biomarkers.

Technology Category

• Computer Vision: Learning & Optimization for CV
• Machine Learning: Calibration & Uncertainty Quantification
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Parkinson's disease (PD) is a prevalent neurodegenerative disorder globally. The eye's retina is an extension of the brain and has great potential in PD screening. Recent studies have suggested that texture features extracted from retinal layers can be adopted as biomarkers for PD diagnosis under optical coherence tomography (OCT) images. Frequency domain learning techniques can enhance the feature representations of deep neural networks (DNNs) by decomposing frequency components involving rich texture features. Additionally, previous works have not exploited texture features for automated PD screening in OCT. Motivated by the above analysis, we propose a novel Adaptive Wavelet Filter (AWF) that serves as the Practical Texture Feature Amplifier to fully leverage the merits of texture features to boost the PD screening performance of DNNs with the aid of frequency domain learning. Specifically, AWF first enhances texture feature representation diversities via channel mixer, then emphasizes informative texture feature representations with the well-designed adaptive wavelet filtering token mixer. By combining the AWFs with the DNN stem, AWFNet is constructed for automated PD screening. Additionally, we introduce a novel Balanced Confidence (BC) Loss by mining the potential of sample-wise predicted probabilities of all classes and class frequency prior, to further boost the PD screening performance and trustworthiness of AWFNet. The extensive experiments manifest the superiority of our AWFNet and BC over state-of-the-art methods in terms of PD screening performance and trustworthiness.

Problem

• Enhancing texture features for Parkinson's Disease screening in OCT
• Developing Adaptive Wavelet Filters to amplify texture features
• Improving PD screening performance and trustworthiness via AWFNet

Innovation

• Adaptive Wavelet Filter enhances texture features
• AWFNet combines DNNs with frequency domain learning
• Balanced Confidence Loss improves screening trustworthiness