Enhanced Estimation of Bone Mineral Content from an X-ray Image Using Random Fast Denoising Diffusion Probabilistic Models to Quantify Prediction Uncertainty for Osteoporosis Diagnosis.

Samuel Abena Kpalemon, Yi Gu, Naoaki ONO, Altaf-Ul-Amin, Ahmad Kamal Nasution, Shigehiko Kanaya, Keisuke Uemura, Mazen Soufi, Masaki Takao, Hugues Talbot, Seiji Okada, Nobuhiko Sugano, Yoshinobu Sato, Yoshito Otake

Keywords: Osteoporosis, Uncertainty, Bone Mineral Content, Diffusion Models

TL;DR: Bone mineral content estimation and uncertainty quantification using Diffusion Models

Abstract: Osteoporosis is the leading cause of bone fractures in the elderly, yet it often goes undiagnosed mainly due to the high cost and limited accessibility of dual-energy X-ray absorptiometry (DXA), the current gold standard for diagnosis. Additionally, deep learning algorithms like Generative Adversarial Networks (GANs) have shown promising results in diagnosing osteoporosis by estimating bone mineral content (BMC). However, previous GAN-based approaches have not addressed uncertainty estimation, which is critical to improving reliability in clinical decision-making. To build on previous work, we propose a novel method that combines random fast denoising diffusion probabilistic model (Random Fast-DDPM) for BMC estimation with a variance-based uncertainty quantification technique. Unlike GANs, which only estimate BMC, our method also captures prediction uncertainty, adding a layer of reliability to the diagnostic process. The proposed method achieved a high Pearson correlation coefficient, r=0.82 in BMC estimation and reported an overall uncertainty score of 0.189 which needs further investigation to assess its reliability.

Submission Number: 129