Next Article in Journal
Molecular Context-Dependent Effects Induced by Rett Syndrome-Associated Mutations in MeCP2
Previous Article in Journal
Magnoflorine—Isolation and the Anticancer Potential against NCI-H1299 Lung, MDA-MB-468 Breast, T98G Glioma, and TE671 Rhabdomyosarcoma Cancer Cells
Previous Article in Special Issue
Image Segmentation of the Ventricular Septum in Fetal Cardiac Ultrasound Videos Based on Deep Learning Using Time-Series Information
Open AccessArticle

Deep Learning for Osteoporosis Classification Using Hip Radiographs and Patient Clinical Covariates

1
Department of Orthopaedic Surgery, Kagawa Prefectural Central Hospital, Takamatsu, Kagawa 760-8557, Japan
2
Department of Oral and Maxillofacial Surgery, Kagawa Prefectural Central Hospital, 1-2-1, Asahi-machi, Takamatsu, Kagawa 760-8557, Japan
3
Department of Oral Pathology and Medicine, Graduate School of Medicine, Dentistry and Pharmaceutical Sciences, Okayama University, Okayama 700-8525, Japan
4
Search Space Inc., Tokyo 151-0072, Japan
5
Department of Musculoskeletal Traumatology, Okayama University Graduate School of Medicine, Dentistry and Pharmaceutical Sciences, Okayama 700-8558, Japan
6
Department of Orthopaedic Surgery, Okayama University Graduate School of Medicine, Dentistry and Pharmaceutical Sciences, Okayama 700-8558, Japan
*
Author to whom correspondence should be addressed.
Biomolecules 2020, 10(11), 1534; https://doi.org/10.3390/biom10111534
Received: 4 September 2020 / Revised: 8 November 2020 / Accepted: 8 November 2020 / Published: 10 November 2020
(This article belongs to the Special Issue Application of Artificial Intelligence for Medical Research)
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. View Full-Text
Keywords: osteoporosis; deep learning; hip radiograph; ensemble model osteoporosis; deep learning; hip radiograph; ensemble model
Show Figures

Figure 1

MDPI and ACS Style

Yamamoto, N.; Sukegawa, S.; Kitamura, A.; Goto, R.; Noda, T.; Nakano, K.; Takabatake, K.; Kawai, H.; Nagatsuka, H.; Kawasaki, K.; Furuki, Y.; Ozaki, T. Deep Learning for Osteoporosis Classification Using Hip Radiographs and Patient Clinical Covariates. Biomolecules 2020, 10, 1534.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop