Unsupervised Machine Learning for Osteoporosis Diagnosis Using Singh Index Clustering on Hip Radiographs

TL;DR

This study develops an unsupervised machine learning approach using clustering on hip radiographs to automate Singh Index-based osteoporosis diagnosis, aiming to improve efficiency and accessibility.

Contribution

It introduces a novel CNN-based feature extraction and clustering pipeline for SI classification from unlabelled radiographs, addressing manual and expert-dependent limitations.

Findings

Custom CNN outperforms established models in feature extraction.

Clustering identified two high-quality SI grade clusters.

Dataset imbalance and image quality impact classification accuracy.

Abstract

Osteoporosis, a prevalent condition among the aging population worldwide, is characterized by diminished bone mass and altered bone structure, increasing susceptibility to fractures. It poses a significant and growing global public health challenge over the next decade. Diagnosis typically involves Dual-energy X-ray absorptiometry to measure bone mineral density, yet its mass screening utility is limited. The Singh Index (SI) provides a straightforward, semi-quantitative means of osteoporosis diagnosis through plain hip radiographs, assessing trabecular patterns in the proximal femur. Although cost-effective and accessible, manual SI calculation is time-intensive and requires expertise. This study aims to automate SI identification from radiographs using machine learning algorithms. An unlabelled dataset of 838 hip X-ray images from Indian adults aged 20-70 was utilized. A custom convolutional neural network architecture was developed for feature extraction, demonstrating superior performance in cluster homogeneity and heterogeneity compared to established models. Various clustering algorithms categorized images into six SI grade clusters, with comparative analysis revealing only two clusters with high Silhouette Scores for promising classification. Further scrutiny highlighted dataset imbalance and emphasized the importance of image quality and additional clinical data availability. The study suggests augmenting X-ray images with patient clinical data and reference images, alongside image pre-processing techniques, to enhance diagnostic accuracy. Additionally, exploring semi-supervised and self-supervised learning methods may mitigate labelling challenges associated with large datasets.