Abstract

This study considers the use of deep learning to diagnose osteoporosis from hip radiographs, and whether adding clinical data improves diagnostic performance over the image mode alone. For objective labeling, we collected a dataset containing 1131 images from patients who underwent both skeletal bone mineral density measurement and hip radiography at a single general hospital between 2014 and 2019. Osteoporosis was assessed from the hip radiographs using five convolutional neural network (CNN) models. We also investigated ensemble models with clinical covariates added to each CNN. The accuracy, precision, recall, specificity, negative predictive value (npv), F1 score, and area under the curve (AUC) score were calculated for each network. In the evaluation of the five CNN models using only hip radiographs, GoogleNet and EfficientNet b3 exhibited the best accuracy, precision, and specificity. Among the five ensemble models, EfficientNet b3 exhibited the best accuracy, recall, npv, F1 score, and AUC score when patient variables were included. The CNN models diagnosed osteoporosis from hip radiographs with high accuracy, and their performance improved further with the addition of clinical covariates from patient records.

Highlights

  • 50% of women and 20% of men will experience osteoporotic fractures in their lifetime [1]

  • The standard test for diagnosing osteoporosis is the estimation of bone mineral density (BMD) in the proximal femur and lumbar spine with dual-energy X-ray absorptiometry (DXA)

  • We investigated the accuracy of the predictive diagnosis of osteoporosis from the combination of clinical covariates with the various convolutional neural network (CNN) models

Read more

Summary

Introduction

50% of women and 20% of men will experience osteoporotic fractures in their lifetime [1]. The standard test for diagnosing osteoporosis is the estimation of bone mineral density (BMD) in the proximal femur and lumbar spine with dual-energy X-ray absorptiometry (DXA). The US Preventive Services Task Force has recommended screening for osteoporosis with BMD to prevent osteoporotic fractures in women 65 years and older [2]. The early diagnosis of osteoporosis is important for the prevention of osteoporotic fractures because therapeutic drug treatments fractures, because treatments are more effective in the early stages of the condition, before fractures have appeared [3]. One disadvantage of using DXA is the occurrence of relevant measurement errors that caused by the surrounding soft tissues [4,5]. Easy access to bone densitometry examinations is important, in developing countries

Objectives
Methods
Discussion
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call