Topological Signatures vs. Gradient Histograms: A Comparative Study for Medical Image Classification

TL;DR

This study compares gradient-based HOG features and topological data analysis features for retinal image classification, showing both approaches perform similarly and are complementary, suggesting combined use for improved medical diagnostics.

Contribution

The paper provides a comprehensive comparison of HOG and TDA features for retinal image classification, highlighting their complementary nature and potential for integrated approaches.

Findings

XGBoost performs best with both feature types.

HOG achieves 94.29% accuracy in binary classification.

TDA achieves 74.69% accuracy in multi-class classification.

Abstract

This work presents a comparative evaluation of two fundamentally different feature extraction paradigms--Histogram of Oriented Gradients (HOG) and Topological Data Analysis (TDA)--for medical image classification, with a focus on retinal fundus imagery. HOG captures local structural information by modeling gradient orientation distributions within spatial regions, effectively encoding texture and edge patterns. In contrast, TDA, implemented through cubical persistent homology, extracts global topological descriptors that characterize shape, connectivity, and intensity-based structure across images. We evaluate both approaches on the publicly available APTOS retinal fundus dataset for two classification tasks: binary classification (normal vs. diabetic retinopathy (DR)) and five-class DR severity grading. From each image, 26,244 HOG features and 800 TDA features are extracted and independently used to train seven classical machine learning models, including logistic regression, random forest, XGBoost, support vector machines, decision trees, k-nearest neighbors, and Extra Trees, using 10-fold cross-validation. Experimental results show that XGBoost achieves the best performance across both feature types. For binary classification, accuracies of 94.29% (HOG) and 94.18% (TDA) are obtained, while multi-class classification yields accuracies of 74.41% and 74.69%, respectively. These results demonstrate that gradient-based and topological features provide complementary representations of retinal image structure and highlight the potential of integrating both approaches for interpretable and robust medical image classification.