This article requires a subscription to view the full text. If you have a subscription you may use the login form below to view the article. Access to this article can also be purchased.
Abstract
BACKGROUND AND PURPOSE: Vertebral compression fractures may indicate osteoporosis but are underdiagnosed and underreported by radiologists. We have developed an ensemble of vertebral body (VB) segmentation models for lateral radiographs as a critical component of an automated, opportunistic screening tool. Our goal is to detect the approximate location of thoracic and lumbar VBs, including fractured vertebra, on lateral radiographs.
MATERIALS AND METHODS: The Osteoporotic Fractures in Men Study (MrOS) data set includes spine radiographs of 5994 men aged ≥65 years from 6 clinical centers. Two segmentation models, U-Net and Mask-RCNN (Region-based Convolutional Neural Network), were independently trained on the MrOS data set retrospectively, and an ensemble was created by combining them. Primary performance metrics for VB detection success included precision, recall, and F1 score for object detection on a held-out test set. Intersection over union (IoU) and Dice coefficient were also calculated as secondary metrics of performance for the test set. A separate external data set from a quaternary health care enterprise was acquired to test generalizability, comprising diagnostic clinical radiographs from men and women aged ≥65 years.
RESULTS: The trained models achieved F1 score of U-Net = 83.42%, Mask-RCNN = 86.30%, and ensemble = 88.34% in detecting all VBs, and F1 score of U-Net = 87.88%, Mask-RCNN = 92.31%, and ensemble = 97.14% in detecting severely fractured vertebrae. The trained models achieved an average IoU per VB of 0.759 for U-Net and 0.709 for Mask-RCNN. The trained models achieved F1 score of U-Net = 81.11%, Mask-RCNN = 79.24%, and ensemble = 87.72% in detecting all VBs in the external data set.
CONCLUSIONS: An ensemble model combining predictions from U-Net and Mask-RCNN resulted in the best performance in detecting VBs on lateral radiographs and generalized well to an external data set. This model could be a key component of a pipeline to detect fractures on all vertebrae in a radiograph in an automated, opportunistic screening tool under development.
ABBREVIATIONS:
- IoU
- intersection over union
- m2ABQ
- modified-2 algorithm based qualitative fracture classification system
- MrOS
- Osteoporotic Fractures in Men Study
- OCF
- osteoporotic compression fracture
- PPV
- positive predictive value
- VB
- vertebral body
Footnotes
This work was supported by the University of Washington Clinical Learning, Evidence, And Research (CLEAR) Center for Musculoskeletal Disorders, Administrative, Methodologic Cores and National Institute of Arthritis and Musculoskeletal and Skin Diseases/National Institutes of Health (NIAMS/NIH) grant P30AR072572; and supported in part by the General Electric-Association of University Radiologists Radiology Research Academic Fellowship (GERRAF, Dr. Cross), a career development award co-sponsored by General Electric Healthcare and the Association of University Radiologists. The content is solely the responsibility of the authors and does not necessarily represent the official views of the NIH.
The Osteoporotic Fractures in Men Study (MrOS) is supported by NIH funding. The following institutes provide support: the National Institute on Aging (NIA), NIAMS, the National Center for Advancing Translational Sciences (NCATS), and NIH Roadmap for Medical Research under the following grant numbers: U01 AG027810, U01 AG042124, U01 AG042139, U01 AG042140, U01 AG042143, U01 AG042145, U01 AG042168, U01 AR066160, R01 AG066671, and UL1 TR000128.
Gang Luo was partially supported by the National Heart, Lung, and Blood Institute of the National Institutes of Health under Award R01HL142503.
Brian Chang was supported by the National Library of Medicine training grant T15LM007442.
Disclosure forms provided by the authors are available with the full text and PDF of this article at www.ajnr.org.
- © 2024 by American Journal of Neuroradiology