Deep Learning for Osteoporosis Classification Using Hip Radiographs and Patient Clinical Covariates
Open Access
- 10 November 2020
- journal article
- research article
- Published by MDPI AG in Biomolecules
- Vol. 10 (11), 1534
- https://doi.org/10.3390/biom10111534
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.Keywords
This publication has 53 references indexed in Scilit:
- Osteoporosis Risk Prediction for Bone Mineral Density Assessment of Postmenopausal Women Using Machine LearningYonsei Medical Journal, 2013
- Cost-Effectiveness of Using Clinical Risk Factors with and without DXA for Osteoporosis Screening in Postmenopausal WomenValue in Health, 2009
- FRAX™ and the assessment of fracture probability in men and women from the UKOsteoporosis International, 2008
- European guidance for the diagnosis and management of osteoporosis in postmenopausal womenOsteoporosis International, 2008
- Correlation of plain radiographic indices of the hip with quantitative bone mineral densityOsteoporosis International, 2007
- Assessment of the Proximal Femoral Morphology Using Plain Radiograph—Can it Predict the Bone Quality?The Journal of Arthroplasty, 2006
- Range of change of measured BMD in the femoral neck and total hip with rotation in womenJournal of Bone and Mineral Metabolism, 2004
- Effect of Leg Rotation on Hip Bone Mineral Density MeasurementsJournal of Clinical Densitometry, 2003
- Impact of soft tissue on in vivo accuracy of bone mineral measurements in the spine, hip, and forearm: A human cadaver studyJournal of Bone and Mineral Research, 1995
- METHOD FOR MEASURING QUANTITY OF BONEThe Lancet, 1969