Dataset Information

Automated Detection, Localization, and Classification of Traumatic Vertebral Body Fractures in the Thoracic and Lumbar Spine at CT.

ABSTRACT:

Purpose

To design and validate a fully automated computer system for the detection and anatomic localization of traumatic thoracic and lumbar vertebral body fractures at computed tomography (CT).

Materials and methods

This retrospective study was HIPAA compliant. Institutional review board approval was obtained, and informed consent was waived. CT examinations in 104 patients (mean age, 34.4 years; range, 14-88 years; 32 women, 72 men), consisting of 94 examinations with positive findings for fractures (59 with vertebral body fractures) and 10 control examinations (without vertebral fractures), were performed. There were 141 thoracic and lumbar vertebral body fractures in the case set. The locations of fractures were marked and classified by a radiologist according to Denis column involvement. The CT data set was divided into training and testing subsets (37 and 67 subsets, respectively) for analysis by means of prototype software for fully automated spinal segmentation and fracture detection. Free-response receiver operating characteristic analysis was performed.

Results

Training set sensitivity for detection and localization of fractures within each vertebra was 0.82 (28 of 34 findings; 95% confidence interval [CI]: 0.68, 0.90), with a false-positive rate of 2.5 findings per patient. The sensitivity for fracture localization to the correct vertebra was 0.88 (23 of 26 findings; 95% CI: 0.72, 0.96), with a false-positive rate of 1.3. Testing set sensitivity for the detection and localization of fractures within each vertebra was 0.81 (87 of 107 findings; 95% CI: 0.75, 0.87), with a false-positive rate of 2.7. The sensitivity for fracture localization to the correct vertebra was 0.92 (55 of 60 findings; 95% CI: 0.79, 0.94), with a false-positive rate of 1.6. The most common cause of false-positive findings was nutrient foramina (106 of 272 findings [39%]).

Conclusion

The fully automated computer system detects and anatomically localizes vertebral body fractures in the thoracic and lumbar spine on CT images with a high sensitivity and a low false-positive rate.

SUBMITTER: Burns JE

PROVIDER: S-EPMC4699497 | biostudies-literature | 2016 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Automated Detection, Localization, and Classification of Traumatic Vertebral Body Fractures in the Thoracic and Lumbar Spine at CT.

Burns Joseph E JE Yao Jianhua J Muñoz Hector H Summers Ronald M RM

Radiology 20150714 1

<h4>Purpose</h4>To design and validate a fully automated computer system for the detection and anatomic localization of traumatic thoracic and lumbar vertebral body fractures at computed tomography (CT).<h4>Materials and methods</h4>This retrospective study was HIPAA compliant. Institutional review board approval was obtained, and informed consent was waived. CT examinations in 104 patients (mean age, 34.4 years; range, 14-88 years; 32 women, 72 men), consisting of 94 examinations with positive ...[more]

PMID: 26172532

Similar Datasets

Project description:Purpose To create and validate a computer system with which to detect, localize, and classify compression fractures and measure bone density of thoracic and lumbar vertebral bodies on computed tomographic (CT) images. Materials and Methods Institutional review board approval was obtained, and informed consent was waived in this HIPAA-compliant retrospective study. A CT study set of 150 patients (mean age, 73 years; age range, 55-96 years; 92 women, 58 men) with (n = 75) and without (n = 75) compression fractures was assembled. All case patients were age and sex matched with control subjects. A total of 210 thoracic and lumbar vertebrae showed compression fractures and were electronically marked and classified by a radiologist. Prototype fully automated spinal segmentation and fracture detection software were then used to analyze the study set. System performance was evaluated with free-response receiver operating characteristic analysis. Results Sensitivity for detection or localization of compression fractures was 95.7% (201 of 210; 95% confidence interval [CI]: 87.0%, 98.9%), with a false-positive rate of 0.29 per patient. Additionally, sensitivity was 98.7% and specificity was 77.3% at case-based receiver operating characteristic curve analysis. Accuracy for classification by Genant type (anterior, middle, or posterior height loss) was 0.95 (107 of 113; 95% CI: 0.89, 0.98), with weighted κ of 0.90 (95% CI: 0.81, 0.99). Accuracy for categorization by Genant height loss grade was 0.68 (77 of 113; 95% CI: 0.59, 0.76), with a weighted κ of 0.59 (95% CI: 0.47, 0.71). The average bone attenuation for T12-L4 vertebrae was 146 HU ± 29 (standard deviation) in case patients and 173 HU ± 42 in control patients; this difference was statistically significant (P < .001). Conclusion An automated machine learning computer system was created to detect, anatomically localize, and categorize vertebral compression fractures at high sensitivity and with a low false-positive rate, as well as to calculate vertebral bone density, on CT images. © RSNA, 2017 Online supplemental material is available for this article.

Project description:In a population-based study, we found that computed tomography (CT)-based bone density and strength measures from the thoracic spine predicted new vertebral fracture as well as measures from the lumbar spine, suggesting that CT scans at either the thorax or abdominal regions are useful to assess vertebral fracture risk.IntroductionPrior studies have shown that computed tomography (CT)-based lumbar bone density and strength measurements predict incident vertebral fracture. This study investigated whether CT-based bone density and strength measurements from the thoracic spine predict incident vertebral fracture and compared the performance of thoracic and lumbar bone measurements to predict incident vertebral fracture.MethodsThis case-control study of community-based men and women (age 74.6 ± 6.6) included 135 cases with incident vertebral fracture at any level and 266 age- and sex-matched controls. We used baseline CT scans to measure integral and trabecular volumetric bone mineral density (vBMD) and vertebral strength (via finite element analysis, FEA) at the T8 and L2 levels. Association between these measurements and vertebral fracture was determined by using conditional logistic regression. Sensitivity and specificity for predicting incident vertebral fracture were determined for lumbar spine and thoracic bone measurements.ResultsBone measurements from T8 and L2 predicted incident vertebral fracture equally well, regardless of fracture location. Specifically, for predicting vertebral fracture at any level, the odds ratio (per 1-SD decrease) for the vBMD and strength measurements at L2 and T8 ranged from 2.0 to 2.7 (p < 0.0001) and 1.8 to 2.8 (p < 0.0001), respectively. Results were similar when predicting fracture only in the thoracic versus the thoracolumbar spine. Lumbar and thoracic spine bone measurements had similar sensitivity and specificity for predicting incident vertebral fracture.ConclusionThese findings indicated that like those from the lumbar spine, CT-based bone density and strength measurements from the thoracic spine may be useful for identifying individuals at high risk for vertebral fracture.

Project description:ObjectiveTo evaluate the performance of a convolutional neural network (CNN) model that can automatically detect and classify rib fractures, and output structured reports from computed tomography (CT) images.Materials and methodsThis study included 1079 patients (median age, 55 years; men, 718) from three hospitals, between January 2011 and January 2019, who were divided into a monocentric training set (n = 876; median age, 55 years; men, 582), five multicenter/multiparameter validation sets (n = 173; median age, 59 years; men, 118) with different slice thicknesses and image pixels, and a normal control set (n = 30; median age, 53 years; men, 18). Three classifications (fresh, healing, and old fracture) combined with fracture location (corresponding CT layers) were detected automatically and delivered in a structured report. Precision, recall, and F1-score were selected as metrics to measure the optimum CNN model. Detection/diagnosis time, precision, and sensitivity were employed to compare the diagnostic efficiency of the structured report and that of experienced radiologists.ResultsA total of 25054 annotations (fresh fracture, 10089; healing fracture, 10922; old fracture, 4043) were labelled for training (18584) and validation (6470). The detection efficiency was higher for fresh fractures and healing fractures than for old fractures (F1-scores, 0.849, 0.856, 0.770, respectively, p = 0.023 for each), and the robustness of the model was good in the five multicenter/multiparameter validation sets (all mean F1-scores > 0.8 except validation set 5 [512 × 512 pixels; F1-score = 0.757]). The precision of the five radiologists improved from 80.3% to 91.1%, and the sensitivity increased from 62.4% to 86.3% with artificial intelligence-assisted diagnosis. On average, the diagnosis time of the radiologists was reduced by 73.9 seconds.ConclusionOur CNN model for automatic rib fracture detection could assist radiologists in improving diagnostic efficiency, reducing diagnosis time and radiologists' workload.

Project description:ImportanceThe association of chemoradiotherapy (CRT) with a thoracic vertebral fracture in patients with esophageal cancer is unknown.ObjectiveTo determine whether CRT is associated with thoracic vertebral fractures in patients with esophageal cancer.Design, setting, and participantsThis retrospective cohort study included patients with clinical stages I to III thoracic esophageal cancer who visited the Kyoto University Hospital, Kyoto, Japan, from January 1, 2007, to December 31, 2013. Data were analyzed from April 6, 2018, to June 4, 2020.ExposuresChemoradiotherapy (CRT group) or surgery or endoscopic treatment (non-CRT group).Main outcomes and measuresThe main outcome of this study was the cumulative incidence rate of thoracic vertebral fractures in 36 months. The incidence rate was calculated taking censoring into account. Possible risk factors, including CRT, were explored in the multivariable analysis. The association of irradiated doses with fractured vertebrae was also evaluated.ResultsA total of 315 patients (119 for the CRT group and 196 for the non-CRT group) were included. The median age of patients was 65 (range, 32-85) years. Fifty-six patients (17.8%) were female and 259 (82.2%) were male. The median observation time was 40.4 (range, 0.7-124.1) months. Thoracic vertebral fractures were observed in 20 patients (16.8%) in the CRT group and 8 patients (4.1%) in the non-CRT group. The 36-month incidence rate of thoracic vertebral fractures was 12.3% (95% CI, 7.0%-19.1%) in the CRT group and 3.5% (95% CI, 1.3%-7.5%) in the non-CRT group (hazard ratio [HR], 3.41 [95% CI, 1.50-7.73]; P = .003). The multivariable analysis showed that the HR of the thoracic vertebral fracture in the CRT group to non-CRT group was 3.91 (95% CI, 1.66-9.23; P = .002) with adjusting for sex, 3.14 (95% CI, 1.37-7.19; P = .007) with adjusting for age, and 3.10 (95% CI, 1.33-7.24; P = .009) with adjusting for the history of vertebral or hip fractures. The HR of the thoracic vertebral fracture for a 5-Gy increase in the mean radiation dose to the single vertebra was 1.19 (95% CI, 1.04-1.36; P = .009).Conclusions and relevanceThis study found that chemoradiotherapy was associated with thoracic vertebral fractures in patients with esophageal cancers. A reduced radiation dose to thoracic vertebrae may decrease the incidence of fractures.

Project description:ObjectivesUndiagnosed osteoporosis may lead to severe complications after spinal surgery. This study aimed to construct and validate a radiomic signature based on CT scans to screen for lumbar spine osteoporosis.MethodsUsing a stratified random sample method, 386 vertebral bodies were randomly divided into a training set (n = 270) and a test set (n = 116). A total of 1040 radiomics features were automatically retracted from lumbar spine CT scans using the 3D slicer pyradiomics module, and a radiomic signature was created. The sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve (AUC) of the Hounsfield and radiomics signature models were calculated. The AUCs of the two models were compared using the DeLong test. Their clinical usefulness was assessed using a decision curve analysis.ResultsTwelve features were chosen to establish the radiomic signature. The AUCs of the radiomics signature and Hounsfield models were 0.96 and 0.88 in the training set and 0.92 and 0.84 in the test set, respectively. According to the DeLong test, the AUCs of the two models were significantly different (p < 0.05). The radiomics signature model indicated a higher overall net benefit than the Hounsfield model, as determined by decision curve analysis.ConclusionsThe CT-based radiomic signature can differentiate patients with/without osteoporosis prior to lumbar spinal surgery. Without additional medical cost and radiation exposure, the radiomics method may provide valuable information facilitating surgical decision-making.Key points• The goal of the study was to evaluate the efficacy of a radiomics signature model based on routine preoperative lumbar spine CT scans in screening osteoporosis. • The radiomics signature model demonstrated excellent prediction performance in both the training and test sets. • This radiomics method may provide valuable information and facilitate surgical decision-making without additional medical costs and radiation exposure.

Dataset Information

Automated Detection, Localization, and Classification of Traumatic Vertebral Body Fractures in the Thoracic and Lumbar Spine at CT.

Purpose

Materials and methods

Results

Conclusion

Publications

Automated Detection, Localization, and Classification of Traumatic Vertebral Body Fractures in the Thoracic and Lumbar Spine at CT.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets