Dataset Information

A deep learning algorithm for automated measurement of vertebral body compression from X-ray images.

ABSTRACT: The vertebral compression is a significant factor for determining the prognosis of osteoporotic vertebral compression fractures and is generally measured manually by specialists. The consequent misdiagnosis or delayed diagnosis can be fatal for patients. In this study, we trained and evaluated the performance of a vertebral body segmentation model and a vertebral compression measurement model based on convolutional neural networks. For vertebral body segmentation, we used a recurrent residual U-Net model, with an average sensitivity of 0.934 (± 0.086), an average specificity of 0.997 (± 0.002), an average accuracy of 0.987 (± 0.005), and an average dice similarity coefficient of 0.923 (± 0.073). We then generated 1134 data points on the images of three vertebral bodies by labeling each segment of the segmented vertebral body. These were used in the vertebral compression measurement model based on linear regression and multi-scale residual dilated blocks. The model yielded an average mean absolute error of 2.637 (± 1.872) (%), an average mean square error of 13.985 (± 24.107) (%), and an average root mean square error of 3.739 (± 2.187) (%) in fractured vertebral body data. The proposed algorithm has significant potential for aiding the diagnosis of vertebral compression fractures.

SUBMITTER: Seo JW

PROVIDER: S-EPMC8253748 | biostudies-literature | 2021 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A deep learning algorithm for automated measurement of vertebral body compression from X-ray images.

Seo Jae Won JW Lim Sang Heon SH Jeong Jin Gyo JG Kim Young Jae YJ Kim Kwang Gi KG Jeon Ji Young JY

Scientific reports 20210702 1

The vertebral compression is a significant factor for determining the prognosis of osteoporotic vertebral compression fractures and is generally measured manually by specialists. The consequent misdiagnosis or delayed diagnosis can be fatal for patients. In this study, we trained and evaluated the performance of a vertebral body segmentation model and a vertebral compression measurement model based on convolutional neural networks. For vertebral body segmentation, we used a recurrent residual U- ...[more]

PMID: 34215761

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:PurposeTo develop and validate a deep learning radiomics (DLR) model that uses X-ray images to predict the classification of osteoporotic vertebral fractures (OVFs).Material and methodsThe study encompassed a cohort of 942 patients, involving examinations of 1076 vertebrae through X-ray, CT, and MRI across three distinct hospitals. The OVFs were categorized as class 0, 1, or 2 based on the Assessment System of Thoracolumbar Osteoporotic Fracture. The dataset was divided randomly into four distinct subsets: a training set comprising 712 samples, an internal validation set with 178 samples, an external validation set containing 111 samples, and a prospective validation set consisting of 75 samples. The ResNet-50 architectural model was used to implement deep transfer learning (DTL), undergoing -pre-training separately on the RadImageNet and ImageNet datasets. Features from DTL and radiomics were extracted and integrated using X-ray images. The optimal fusion feature model was identified through least absolute shrinkage and selection operator logistic regression. Evaluation of the predictive capabilities for OVFs classification involved eight machine learning models, assessed through receiver operating characteristic curves employing the "One-vs-Rest" strategy. The Delong test was applied to compare the predictive performance of the superior RadImageNet model against the ImageNet model.ResultsFollowing pre-training separately on RadImageNet and ImageNet datasets, feature selection and fusion yielded 17 and 12 fusion features, respectively. Logistic regression emerged as the optimal machine learning algorithm for both DLR models. Across the training set, internal validation set, external validation set, and prospective validation set, the macro-average Area Under the Curve (AUC) based on the RadImageNet dataset surpassed those based on the ImageNet dataset, with statistically significant differences observed (P<0.05). Utilizing the binary "One-vs-Rest" strategy, the model based on the RadImageNet dataset demonstrated superior efficacy in predicting Class 0, achieving an AUC of 0.969 and accuracy of 0.863. Predicting Class 1 yielded an AUC of 0.945 and accuracy of 0.875, while for Class 2, the AUC and accuracy were 0.809 and 0.692, respectively.ConclusionThe DLR model, based on the RadImageNet dataset, outperformed the ImageNet model in predicting the classification of OVFs, with generalizability confirmed in the prospective validation set.

Project description:ObjectiveMeasurement of the liver and spleen volumes has clinical implications. Although computed tomography (CT) volumetry is considered to be the most reliable noninvasive method for liver and spleen volume measurement, it has limited application in clinical practice due to its time-consuming segmentation process. We aimed to develop and validate a deep learning algorithm (DLA) for fully automated liver and spleen segmentation using portal venous phase CT images in various liver conditions.Materials and methodsA DLA for liver and spleen segmentation was trained using a development dataset of portal venous CT images from 813 patients. Performance of the DLA was evaluated in two separate test datasets: dataset-1 which included 150 CT examinations in patients with various liver conditions (i.e., healthy liver, fatty liver, chronic liver disease, cirrhosis, and post-hepatectomy) and dataset-2 which included 50 pairs of CT examinations performed at ours and other institutions. The performance of the DLA was evaluated using the dice similarity score (DSS) for segmentation and Bland-Altman 95% limits of agreement (LOA) for measurement of the volumetric indices, which was compared with that of ground truth manual segmentation.ResultsIn test dataset-1, the DLA achieved a mean DSS of 0.973 and 0.974 for liver and spleen segmentation, respectively, with no significant difference in DSS across different liver conditions (p = 0.60 and 0.26 for the liver and spleen, respectively). For the measurement of volumetric indices, the Bland-Altman 95% LOA was -0.17 ± 3.07% for liver volume and -0.56 ± 3.78% for spleen volume. In test dataset-2, DLA performance using CT images obtained at outside institutions and our institution was comparable for liver (DSS, 0.982 vs. 0.983; p = 0.28) and spleen (DSS, 0.969 vs. 0.968; p = 0.41) segmentation.ConclusionThe DLA enabled highly accurate segmentation and volume measurement of the liver and spleen using portal venous phase CT images of patients with various liver conditions.

Project description:Background: Bone marrow fat (BMF) fraction quantification in vertebral bodies is used as a novel imaging biomarker to assess and characterize chronic lower back pain. However, manual segmentation of vertebral bodies is time consuming and laborious. Purpose: (1) Develop a deep learning pipeline for segmentation of vertebral bodies using quantitative water-fat MRI. (2) Compare BMF measurements between manual and automatic segmentation methods to assess performance. Materials and Methods: In this retrospective study, MR images using a 3D spoiled gradient-recalled echo (SPGR) sequence with Iterative Decomposition of water and fat with Echo Asymmetry and Least-squares estimation (IDEAL) reconstruction algorithm were obtained in 57 subjects (28 women, 29 men, mean age, 47.2 ± 12.6 years). An artificial network was trained for 100 epochs on a total of 165 lumbar vertebrae manually segmented from 31 subjects. Performance was assessed by analyzing the receiver operating characteristic curve, precision-recall, F1 scores, specificity, sensitivity, and similarity metrics. Bland-Altman analysis was used to assess performance of BMF fraction quantification using the predicted segmentations. Results: The deep learning segmentation method achieved an AUC of 0.92 (CI 95%: 0.9186, 0.9195) on a testing dataset (n = 24 subjects) on classification of pixels as vertebrae. A sensitivity of 0.99 and specificity of 0.80 were achieved for a testing dataset, and a mean Dice similarity coefficient of 0.849 ± 0.091. Comparing manual and automatic segmentations on fat fraction maps of lumbar vertebrae (n = 124 vertebral bodies) using Bland-Altman analysis resulted in a bias of only -0.605% (CI 95% = -0.847 to -0.363%) and agreement limits of -3.275% and +2.065%. Automatic segmentation was also feasible in 16 ± 1 s. Conclusion: Our results have demonstrated the feasibility of automated segmentation of vertebral bodies using deep learning models on water-fat MR (Dixon) images to define vertebral regions of interest with high specificity. These regions of interest can then be used to quantify BMF with comparable results as manual segmentation, providing a framework for completely automated investigation of vertebral changes in CLBP.

Project description:ObjectiveTo develop a multi-scene model that can automatically segment acute vertebral compression fractures (VCFs) from spine radiographs.MethodsIn this multicenter study, we collected radiographs from five hospitals (Hospitals A-E) between November 2016 and October 2019. The study included participants with acute VCFs, as well as healthy controls. For the development of the Positioning and Focus Network (PFNet), we used a training dataset consisting of 1071 participants from Hospitals A and B. The validation dataset included 458 participants from Hospitals A and B, whereas external test datasets 1-3 included 301 participants from Hospital C, 223 from Hospital D, and 261 from Hospital E, respectively. We evaluated the segmentation performance of the PFNet model and compared it with previously described approaches. Additionally, we used qualitative comparison and gradient-weighted class activation mapping (Grad-CAM) to explain the feature learning and segmentation results of the PFNet model.ResultsThe PFNet model achieved accuracies of 99.93%, 98.53%, 99.21%, and 100% for the segmentation of acute VCFs in the validation dataset and external test datasets 1-3, respectively. The receiver operating characteristic curves comparing the four models across the validation and external test datasets consistently showed that the PFNet model outperformed other approaches, achieving the highest values for all measures. The qualitative comparison and Grad-CAM provided an intuitive view of the interpretability and effectiveness of our PFNet model.ConclusionIn this study, we successfully developed a multi-scene model based on spine radiographs for precise preoperative and intraoperative segmentation of acute VCFs.Critical relevance statementOur PFNet model demonstrated high accuracy in multi-scene segmentation in clinical settings, making it a significant advancement in this field.Key pointsThis study developed the first multi-scene deep learning model capable of segmenting acute VCFs from spine radiographs. The model's architecture consists of two crucial modules: an attention-guided module and a supervised decoding module. The exceptional generalization and consistently superior performance of our model were validated using multicenter external test datasets.

Dataset Information

A deep learning algorithm for automated measurement of vertebral body compression from X-ray images.

Publications

A deep learning algorithm for automated measurement of vertebral body compression from X-ray images.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets