skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Computerized detection of vertebral compression fractures on lateral chest radiographs: Preliminary results with a tool for early detection of osteoporosis

Abstract

Vertebral fracture (or vertebral deformity) is a very common outcome of osteoporosis, which is one of the major public health concerns in the world. Early detection of vertebral fractures is important because timely pharmacologic intervention can reduce the risk of subsequent additional fractures. Chest radiographs are used routinely for detection of lung and heart diseases, and vertebral fractures can be visible on lateral chest radiographs. However, investigators noted that about 50% of vertebral fractures visible on lateral chest radiographs were underdiagnosed or under-reported, even when the fractures were severe. Therefore, our goal was to develop a computerized method for detection of vertebral fractures on lateral chest radiographs in order to assist radiologists' image interpretation and thus allow the early diagnosis of osteoporosis. The cases used in this study were 20 patients with severe vertebral fractures and 118 patients without fractures, as confirmed by the consensus of two radiologists. Radiologists identified the locations of fractured vertebrae, and they provided morphometric data on the vertebral shape for evaluation of the accuracy of detecting vertebral end plates by computer. In our computerized method, a curved search area, which included a number of vertebral end plates, was first extracted automatically, and was straightened somore » that vertebral end plates became oriented horizontally. Edge candidates were enhanced by use of a horizontal line-enhancement filter in the straightened image, and a multiple thresholding technique, followed by feature analysis, was used for identification of the vertebral end plates. The height of each vertebra was determined from locations of identified vertebral end plates, and fractured vertebrae were detected by comparison of the measured vertebral height with the expected height. The sensitivity of our computerized method for detection of fracture cases was 95% (19/20), with 1.03 (139/135) false-positive fractures per image. The accuracy of identifying vertebral end plates, marked by radiologists in a morphometric study, was 76.6% (400/522) and 70.9% (420/592) for cases used for training and those for testing, respectively. We prepared 32 additional fracture cases for a validation test, and we examined the detection accuracy of our computerized method. The sensitivity for these cases was 75% (24/32) at 1.03 (33/32) false-positive fractures per image. Our preliminary results show that the automated computerized scheme for detecting vertebral fractures on lateral chest radiographs has the potential to assist radiologists in detecting vertebral fractures.« less

Authors:
; ; ; ;  [1]
  1. Kurt Rossmann Laboratories for Radiologic Image Research, Department of Radiology, University of Chicago, 5841 South Maryland Avenue, Chicago, Illinois 60637 (United States)
Publication Date:
OSTI Identifier:
20853834
Resource Type:
Journal Article
Resource Relation:
Journal Name: Medical Physics; Journal Volume: 33; Journal Issue: 12; Other Information: DOI: 10.1118/1.2364053; (c) 2006 American Association of Physicists in Medicine; Country of input: International Atomic Energy Agency (IAEA)
Country of Publication:
United States
Language:
English
Subject:
62 RADIOLOGY AND NUCLEAR MEDICINE; ACCURACY; BONE FRACTURES; CARDIOVASCULAR DISEASES; CHEST; DIAGNOSIS; IMAGES; LUNGS; OSTEOPOROSIS; PATIENTS; PUBLIC HEALTH; SENSITIVITY; VERTEBRAE

Citation Formats

Kasai, Satoshi, Li Feng, Shiraishi, Junji, Li Qiang, and Doi, Kunio. Computerized detection of vertebral compression fractures on lateral chest radiographs: Preliminary results with a tool for early detection of osteoporosis. United States: N. p., 2006. Web. doi:10.1118/1.2364053.
Kasai, Satoshi, Li Feng, Shiraishi, Junji, Li Qiang, & Doi, Kunio. Computerized detection of vertebral compression fractures on lateral chest radiographs: Preliminary results with a tool for early detection of osteoporosis. United States. doi:10.1118/1.2364053.
Kasai, Satoshi, Li Feng, Shiraishi, Junji, Li Qiang, and Doi, Kunio. Fri . "Computerized detection of vertebral compression fractures on lateral chest radiographs: Preliminary results with a tool for early detection of osteoporosis". United States. doi:10.1118/1.2364053.
@article{osti_20853834,
title = {Computerized detection of vertebral compression fractures on lateral chest radiographs: Preliminary results with a tool for early detection of osteoporosis},
author = {Kasai, Satoshi and Li Feng and Shiraishi, Junji and Li Qiang and Doi, Kunio},
abstractNote = {Vertebral fracture (or vertebral deformity) is a very common outcome of osteoporosis, which is one of the major public health concerns in the world. Early detection of vertebral fractures is important because timely pharmacologic intervention can reduce the risk of subsequent additional fractures. Chest radiographs are used routinely for detection of lung and heart diseases, and vertebral fractures can be visible on lateral chest radiographs. However, investigators noted that about 50% of vertebral fractures visible on lateral chest radiographs were underdiagnosed or under-reported, even when the fractures were severe. Therefore, our goal was to develop a computerized method for detection of vertebral fractures on lateral chest radiographs in order to assist radiologists' image interpretation and thus allow the early diagnosis of osteoporosis. The cases used in this study were 20 patients with severe vertebral fractures and 118 patients without fractures, as confirmed by the consensus of two radiologists. Radiologists identified the locations of fractured vertebrae, and they provided morphometric data on the vertebral shape for evaluation of the accuracy of detecting vertebral end plates by computer. In our computerized method, a curved search area, which included a number of vertebral end plates, was first extracted automatically, and was straightened so that vertebral end plates became oriented horizontally. Edge candidates were enhanced by use of a horizontal line-enhancement filter in the straightened image, and a multiple thresholding technique, followed by feature analysis, was used for identification of the vertebral end plates. The height of each vertebra was determined from locations of identified vertebral end plates, and fractured vertebrae were detected by comparison of the measured vertebral height with the expected height. The sensitivity of our computerized method for detection of fracture cases was 95% (19/20), with 1.03 (139/135) false-positive fractures per image. The accuracy of identifying vertebral end plates, marked by radiologists in a morphometric study, was 76.6% (400/522) and 70.9% (420/592) for cases used for training and those for testing, respectively. We prepared 32 additional fracture cases for a validation test, and we examined the detection accuracy of our computerized method. The sensitivity for these cases was 75% (24/32) at 1.03 (33/32) false-positive fractures per image. Our preliminary results show that the automated computerized scheme for detecting vertebral fractures on lateral chest radiographs has the potential to assist radiologists in detecting vertebral fractures.},
doi = {10.1118/1.2364053},
journal = {Medical Physics},
number = 12,
volume = 33,
place = {United States},
year = {Fri Dec 15 00:00:00 EST 2006},
month = {Fri Dec 15 00:00:00 EST 2006}
}
  • PurposeWe aim to determine the predictors of new adjacent vertebral fractures (AVCFs) after percutaneous vertebroplasty (PVP) in patients with osteoporotic vertebral compression fractures (OVCFs) and to construct a risk prediction score to estimate a 2-year new AVCF risk-by-risk factor condition.Materials and MethodsPatients with OVCFs who underwent their first PVP between December 2006 and December 2013 at Hospital A (training cohort) and Hospital B (validation cohort) were included in this study. In training cohort, we assessed the independent risk predictors and developed the probability of new adjacent OVCFs (PNAV) score system using the Cox proportional hazard regression analysis. The accuracy ofmore » this system was then validated in both training and validation cohorts by concordance (c) statistic.Results421 patients (training cohort: n = 256; validation cohort: n = 165) were included in this study. In training cohort, new AVCFs after the first PVP treatment occurred in 33 (12.9%) patients. The independent risk factors were intradiscal cement leakage and preexisting old vertebral compression fracture(s). The estimated 2-year absolute risk of new AVCFs ranged from less than 4% in patients with neither independent risk factors to more than 45% in individuals with both factors.ConclusionsThe PNAV score is an objective and easy approach to predict the risk of new AVCFs.« less
  • This paper describes a computerized clavicle identification system, primarily designed to resolve the identities of unaccounted for US soldiers who fought in the Korean War. Elliptical Fourier analysis is used to quantify the clavicle outline shape from skeletons and postero-anterior antemortem chest radiographs to rank individuals in terms of metric distance. Similar to leading fingerprint identification systems, shortlists of the top matching candidates are extracted for subsequent human visual assessment. Two independent tests of the computerized system using 17 field-recovered skeletons and 409 chest radiographs demonstrate that true positive matches are captured within the top 5% of the sample 75%more » of the time. These results are outstanding given the eroded state of some field-recovered skeletons and the faintness of the 1950’s photoflurographs. These methods enhance the capability to resolve several hundred cold cases for which little circumstantial information exists and current DNA and dental record technologies cannot be applied.« less
  • An active 38-year-old patient presenting a vertebral compression fracture associated with a pelvic fracture was treated in one stage with CT-guided fixation of the sacrum and kyphoplasty. This treatment decreased the pain, restored the vertebral height, and enabled the patient to be ambulatory. The main advantage of this double approach was to shorten the hospital stay and the nonworking period.
  • The aim of this study was to assess the feasibility of and venous leakage reduction in percutaneous vertebroplasty (PV) using a new high-viscosity bone cement (PMMA). PV has been used effectively for pain relief in osteoporotic and malignant vertebral fractures. Cement extrusion is a common problem and can lead to complications. Sixty patients (52 female; mean age, 72.2 {+-} 7.2) suffering from osteoporosis (46), malignancy (12), and angiomas (2), divided into two groups (A and B), underwent PV on 190 vertebrae (86 dorsal, 104 lumbar). In Group A, PV with high-viscosity PMMA (Confidence, Disc-O-Tech, Israel) was used. This PMMA wasmore » injected by a proprietary delivery system, a hydraulic saline-filled screw injector. In Group B, a standard low-viscosity PMMA was used. Postprocedural CT was carried out to detect PMMA leakages and complications. Fisher's exact test and Wilcoxon rank test were used to assess significant differences (p < 0.05) in leakages and to evaluate the clinical outcome. PV was feasible, achieving good clinical outcome (p < 0.0001) without major complications. In Group A, postprocedural CT showed an asymptomatic leak in the venous structures of 8 of 98 (8.2%) treated vertebrae; a discoidal leak occurred in 6 of 98 (6.1%). In Group B, a venous leak was seen in 38 of 92 (41.3%) and a discoidal leak in 12 of 92 (13.0%). Reduction of venous leak obtained by high-viscosity PMMA was highly significant (p < 0.0001), whereas this result was not significant (p = 0.14) related to the disc. The high-viscosity PMMA system is safe and effective for clinical use, allowing a significant reduction of extravasation rate and, thus, leakage-related complications.« less