Segmentation Of Trabecular Bone Research Articles

Automatic Segmentation of Periapical Radiograph Using Color Histogram and Machine Learning for Osteoporosis Detection.

Osteoporosis leads to the loss of cortical thickness, a decrease in bone mineral density (BMD), deterioration in the size of trabeculae, and an increased risk of fractures. Changes in trabecular bone due to osteoporosis can be observed on periapical radiographs, which are widely used in dental practice. This study proposes an automatic trabecular bone segmentation method for detecting osteoporosis using a color histogram and machine learning (ML), based on 120 regions of interest (ROI) on periapical radiographs, and divided into 60 training and 42 testing datasets. The diagnosis of osteoporosis is based on BMD as evaluated by dual X-ray absorptiometry. The proposed method comprises five stages: the obtaining of ROI images, conversion to grayscale, color histogram segmentation, extraction of pixel distribution, and performance evaluation of the ML classifier. For trabecular bone segmentation, we compare K-means and Fuzzy C-means. The distribution of pixels obtained from the K-means and Fuzzy C-means segmentation was used to detect osteoporosis using three ML methods: decision tree, naive Bayes, and multilayer perceptron. The testing dataset was used to obtain the results in this study. Based on the performance evaluation of the K-means and Fuzzy C-means segmentation methods combined with 3 ML, the osteoporosis detection method with the best diagnostic performance was K-means segmentation combined with a multilayer perceptron classifier, with accuracy, specificity, and sensitivity of 90.48%, 90.90%, and 90.00%, respectively. The high accuracy of this study indicates that the proposed method provides a significant contribution to the detection of osteoporosis in the field of medical and dental image analysis.

A new straightforward method for semi-automated segmentation of trabecular bone from cortical bone in diverse and challenging morphologies.

Many physiological, biomechanical, evolutionary and clinical studies that explore skeletal structure and function require successful separation of trabecular from cortical compartments of a bone that has been imaged by X-ray micro-computed tomography (micro-CT) prior to analysis. Separation often involves manual subdivision of these two similarly radio-opaque compartments, which can be time-consuming and subjective. We have developed an objective, semi-automated protocol which reduces user bias and enables straightforward, user-friendly segmentation of trabecular from the cortical bone without requiring sophisticated programming expertise. This method can conveniently be used as a ‘recipe’ in commercial programmes (Avizo herein) and applied to a variety of datasets. Here, we characterize and share this recipe, and demonstrate its application to a range of murine and human bone types, including normal and osteoarthritic specimens, and bones with distinct embryonic origins and spanning a range of ages. We validate the method by testing inter-user bias during the scan preparation steps and confirm utility in the architecturally challenging analysis of growing murine epiphyses. We also report details of the recipe, so that other groups can readily re-create a similar method in open access programmes. Our aim is that this method will be adopted widely to create a reproducible and time-efficient method of segmenting trabecular and cortical bone.

Penalized-Likelihood Reconstruction With High-Fidelity Measurement Models for High-Resolution Cone-Beam Imaging.

We present a novel reconstruction algorithm based on a general cone-beam CT forward model, which is capable of incorporating the blur and noise correlations that are exhibited in flat-panel CBCT measurement data. Specifically, the proposed model may include scintillator blur, focal-spot blur, and noise correlations due to light spread in the scintillator. The proposed algorithm (GPL-BC) uses a Gaussian Penalized-Likelihood objective function, which incorporates models of blur and correlated noise. In a simulation study, GPL-BC was able to achieve lower bias as compared with deblurring followed by FDK as well as a model-based reconstruction method without integration of measurement blur. In the same study, GPL-BC was able to achieve better line-pair reconstructions (in terms of segmented-image accuracy) as compared with deblurring followed by FDK, a model-based method without blur, and a model-based method with blur but not noise correlations. A prototype extremities quantitative cone-beam CT test-bench was used to image a physical sample of human trabecular bone. These data were used to compare reconstructions using the proposed method and model-based methods without blur and/or correlation to a registered CT image of the same bone sample. The GPL-BC reconstructions resulted in more accurate trabecular bone segmentation. Multiple trabecular bone metrics, including trabecular thickness (Tb.Th.) were computed for each reconstruction approach as well as the CT volume. The GPL-BC reconstruction provided the most accurate Tb.Th. measurement, 0.255 mm, as compared with the CT derived value of 0.193 mm, followed by the GPL-B reconstruction, the GPL-I reconstruction, and then the FDK reconstruction (0.271 mm, 0.309 mm, and 0.335 mm, respectively).

Longitudinal evaluation of the effects of alendronate on MRI bone microarchitecture in postmenopausal osteopenic women

We evaluated longitudinal effects of alendronate on MRI-based trabecular bone structure parameters derived from dual thresholding and fuzzy clustering (BE-FCM) trabecular bone segmentation. Treatment effects were observed in the distal tibia after 24 months. The BE-FCM method increased correlations to HR-pQCT-based parameters. Introduction High-resolution magnetic resonance imaging (MRI) allows for non-invasive bone microarchitecture analysis. The goal of this study was to examine the potential of MRI-based trabecular bone structure parameters to monitor effects of alendronate in humans in vivo, and to compare the results to HR-pQCT and DXA measurements. Materials and methods Postmenopausal osteopenic women were divided into alendronate treatment and control groups, and imaged at baseline, 12 months, and 24 months ( n = 52 at baseline) using 3 T MRI, HR-pQCT, and DXA. Image acquisition sites included distal tibia (MRI and HR-pQCT), distal radius (MRI, DXA, and HR-pQCT), and the proximal femur (MRI and DXA). Two different regions of interest were evaluated. One contained the trabecular bone region within the entire MRI acquisition, and the second contained a subregion matched to the region contained in the HR-pQCT acquisition. The trabecular bone was segmented using two different methods; dual thresholding and BE-FCM. Trabecular bone structure parameters included bone volume fraction (BV/TV), number (Tb.N), spacing (Tb.Sp), and thickness (Tb.Th), along with seven geodesic topological analysis (GTA) parameters. Longitudinal changes and correlations to HR-pQCT and DXA measurements were evaluated. Results Apparent Tb.N and four GTA parameters showed treatment effects ( p < 0.05) in the distal tibia after 24 months in the entire MRI region using BE-FCM, as well as Tb.N using dual thresholding. No treatment effects after 24 months were observed in the HR-pQCT or in MRI analysis for the HR-pQCT-matched regions. Apparent BV/TV and Tb.N from BE-FCM had significantly higher correlations to HR-pQCT values compared to those derived from thresholding. Conclusions This study demonstrates the influence of computational methods and region of interest definitions on measurements of trabecular bone structure, and the feasibility of MRI-based quantification of longitudinal changes in bone microarchitecture due to bisphosphonate therapy. The results suggest that there may be a need to reevaluate the current standard HR-pQCT region definition for increased treatment sensitivity.

Local bone enhancement fuzzy clustering for segmentation of MR trabecular bone images

Segmentation of trabecular bone from magnetic resonance (MR) images is a challenging task due to spatial resolution limitations, signal-to-noise ratio constraints, and signal intensity inhomogeneities. This article examines an alternative approach to trabecular bone segmentation using partial membership segmentation termed fuzzy C-means clustering incorporating local second order features for bone enhancement (BE-FCM) at multiple scales. This approach is meant to allow for a soft segmentation that accounts for partial volume effects while suppressing the influence of noise. A soft segmentation method was developed and evaluated on three different sets of data; interscan reproducibility was evaluated on six test-retest in vivo MR scans of the proximal femur, correlation between MR and HR-pQCT measurements was evaluated on 49 in vivo scans from the distal tibia, and the potential for fracture discrimination was evaluated using MR scans of calcaneus specimens from 15 participants with and 15 participants without vertebral fracture. The algorithm was compared to fuzzy clustering using the intensity as the only feature (I-FCM) and a dual thresholding algorithm. The metric evaluated was bone volume over total volume (BV/TV) within user-defined regions of interest. BE-FCM had a higher interscan reproducibility (rms CV: 2.0%) compared to I-FCM (5.6%) and thresholding (4.2%), and expressed higher correlation to HR-pQCT data (r = 0.79, p < 10(-11)) compared to I-FCM (r = 0.74, p < 10(-8)) and thresholding (r = 0.70, p < 10(-6)). BE-FCM was also the method that was best able to differentiate between a control and a vertebral fracture group at a 95% significance level. The results suggest that trabecular bone segmentation by BE-FCM can provide a precise BV/TV measurement that is sensitive to pathology. The segmentation method may become useful in MR imaging-based quantification of bone microarchitecture.