Radiographic Texture Analysis Research Articles

Radiographic texture analysis of the hard tissue changes following socket preservation with allograft and xenograft materials for dental implantation: a randomized clinical trial.

This study aimed to assess the hard tissue changes following socket preservation with allograft and xenograft materials for dental implantation by texture analysis (TA) using cone-beam computed tomography (CBCT). This prospective clinical trial was conducted on 25 patients who required the extraction of carious mandibular posterior teeth and their subsequent replacement with dental implants. The patients were categorized into three groups: (I) no socket preservation, (II) socket preservation with xenograft material, and (III) socket preservation with allograft material. Four months after tooth extraction, the patients were recalled for preoperative assessment before dental implantation, and CBCT scans were obtained (Kvp:110, mA:1.94, S:3.6). MaZda software was used to compare homogeneity, contrast, and texture complexity on axial CBCT sections among the three groups. Significant differences existed among the three groups in all parameters (P < 0.05) except for the mean correlation parameter (P > 0.05). The results showed no significant difference between the no graft and xenograft groups regarding contrast and differential (dif.) entropy (P > 0.05). Also, no significant difference was found between the xenograft and allograft groups regarding the dif. variance and also between the no graft and allograft groups regarding the inverse difference moment(InvDfMom) and dif. variance parameters (P > 0.05). All other pairwise comparisons revealed significant differences (P < 0.05). TA can be used for the quantification of radiographic changes of bone following socket preservation and potentially accelerate the process of decision-making for dental implant treatment.

Radiomic and deep learning characterization of breast parenchyma on full field digital mammograms and specimen radiographs: a pilot study of a potential cancer field effect.

In women with biopsy-proven breast cancer, histologically normal areas of the parenchyma have shown molecular similarity to the tumor, supporting a potential cancer field effect. The purpose of this work was to investigate relationships of human-engineered radiomic and deep learning features between regions across the breast in mammographic parenchymal patterns and specimen radiographs. This study included mammograms from 74 patients with at least 1 identified malignant tumor, of whom 32 also possessed intraoperative radiographs of mastectomy specimens. Mammograms were acquired with a Hologic system and specimen radiographs were acquired with a Fujifilm imaging system. All images were retrospectively collected under an Institutional Review Board-approved protocol. Regions of interest (ROI) of were selected from three regions: within the identified tumor, near to the tumor, and far from the tumor. Radiographic texture analysis was used to extract 45 radiomic features and transfer learning was used to extract 20 deep learning features in each region. Kendall's Tau-b and Pearson correlation tests were performed to assess relationships between features in each region. Statistically significant correlations in select subgroups of features with tumor, near to the tumor, and far from the tumor ROI regions were identified in both mammograms and specimen radiographs. Intensity-based features were found to show significant correlations with ROI regions across both modalities. Results support our hypothesis of a potential cancer field effect, accessible radiographically, across tumor and non-tumor regions, thus indicating the potential for computerized analysis of mammographic parenchymal patterns to predict breast cancer risk.

Differential Diagnosis of Cysts and Granulomas Supported by Texture Analysis of Intraoral Radiographs.

The aim of this study was to evaluate whether textural analysis could differentiate between the two common types of lytic lesions imaged with use of radiography. Sixty-two patients were enrolled in the study with intraoral radiograph images and a histological reference study. Full textural analysis was performed using MaZda software. For over 10,000 features, logistic regression models were applied. Fragments containing lesion edges were characterized by significant correlation of structural information. Although the input images were stored using lossy compression and their scale was not preserved, the obtained results confirmed the possibility of distinguishing between cysts and granulomas with use of textural analysis of intraoral radiographs. It was shown that the important information distinguishing the aforementioned types of lesions is located at the edges and not within the lesion.

Trabecular bone texture analysis of conventional radiographs for the prediction of total knee replacement risk: data from the osteoarthritis initiative cohort

Purpose: To examine the ability of trabecular bone texture (TBT) analysis to predict total knee replacement (TKR) risk in patients with knee osteoarthritis (KOA): a 9-years prospective follow up study.

Changes of Radiographic Trabecular Bone Density and Peri-Implant Marginal Bone Vertical Dimensions Around Non-Submerged Dental Implants with a Laser-Microtextured Collar after 5 Years of Functional Loading.

Objectives: The progressive peri-implant bone remodeling caused by dynamic cycles of microdamage may change peri-implant bone characteristics and volume after the functional loading. This prospective study was designed to evaluate the radiographic trabecular bone density and peri-implant vertical dimensional changes around the non submerged dental implant with a laser-microtextured collar (NSLI)s after 5 years of functional loading. Methods: Digital periapical radiographs of 58 NSLIs supported fixed single crowns and fixed partial dentures in 26 patients (14 men, mean age of 52 ± 3.8 years) were used for comparative evaluation between the implant placement [Baseline (BSL)], the definitive Crowns Delivery (CD) and the 5 years post-functional loading examination (T5). Regions of interest (ROI) were taken into consideration for the measurement of mean gray levels, standard deviation, and variation coefficient. The texture parameters, such as contrast, correlation, angular second moment and entropy, were investigated by using the software ImageJ (v.1.50i), by means of the Gray-level Co-occurrence Matrix (GLCM) Texture Tool plugin. Vertical Peri-implant Marginal Bone Level (VPMBL) was assessed at the mesial and the distal sides of each implant by subtracting the measure at BSL from the measure at T5 by means of dedicate software (VixWin Platinum Imaging Software). Mixed regression models were adopted to analyze data. The possible effects of some variables, such as the use of provisional denture, location, crown/implant ratio, type of prosthetic design (single or splinted), on radiographic dimensional vertical changes, gray levels and texture analysis variables were also evaluated. Results: From BSL to T5, mesial and distal VPMBL showed a statistically significant gain of 0.9 ±0.5, and 0.10 mm ±0.6, respectively (P&lt;0.05). From CD to T5, mean gray levels increased from 94.4±26.8) to 111.8±27.1 (P&lt;0.05), while the coefficient of variation decreased from 0.08±0,03 to 0.05±0.04) (P&lt;0.05). Variables showed no statistically significant correlation with texture parameters (P &gt; 0.05). Conclusion: NSLIs showed an increase in radiographic vertical peri-implant marginal bone levels and bone density up to 5 years of loading.

Early diagnosis of osteoporosis using radiogrammetry and texture analysis from hand and wrist radiographs in Indian population.

We propose a low cost automated diagnostic tool for early diagnosis of reduction in bone mass using cortical radiogrammetry and cancellous texture analysis of hand and wrist radiographs. Reduction in bone mass could lead to osteoporosis, a disease observed to be increasingly occurring at a younger age in recent times. Dual X-ray absorptiometry (DXA), currently used in clinical practice, is expensive and available only in urban areas in India. Therefore, there is a need to develop a low cost diagnostic tool in order to facilitate large-scale screening of people for early diagnosis of osteoporosis at primary health centers. Cortical radiogrammetry from third metacarpal bone shaft and cancellous texture analysis from distal radius are used to detect low bone mass. Cortical bone indices and cancellous features using Gray Level Run Length Matrices and Laws' masks are extracted. A neural network classifier is trained using these features to classify healthy subjects and subjects having low bone mass. In our pilot study, the proposed segmentation method shows 89.9 and 93.5% accuracy in detecting third metacarpal bone shaft and distal radius ROI, respectively. The trained classifier shows training accuracy of 94.3% and test accuracy of 88.5%. An automated diagnostic technique for early diagnosis of onset of osteoporosis is developed using cortical radiogrammetric measurements and cancellous texture analysis of hand and wrist radiographs. The work shows that a combination of cortical and cancellous features improves the diagnostic ability and is a promising low cost tool for early diagnosis of increased risk of osteoporosis.

Deep learning in breast cancer risk assessment: evaluation of convolutional neural networks on a clinical dataset of full-field digital mammograms.

To evaluate deep learning in the assessment of breast cancer risk in which convolutional neural networks (CNNs) with transfer learning are used to extract parenchymal characteristics directly from full-field digital mammographic (FFDM) images instead of using computerized radiographic texture analysis (RTA), 456 clinical FFDM cases were included: a "high-risk" BRCA1/2 gene-mutation carriers dataset (53 cases), a "high-risk" unilateral cancer patients dataset (75 cases), and a "low-risk dataset" (328 cases). Deep learning was compared to the use of features from RTA, as well as to a combination of both in the task of distinguishing between high- and low-risk subjects. Similar classification performances were obtained using CNN [area under the curve [Formula: see text]; standard error [Formula: see text]] and RTA ([Formula: see text]; [Formula: see text]) in distinguishing BRCA1/2 carriers and low-risk women. However, in distinguishing unilateral cancer patients and low-risk women, performance was significantly greater with CNN ([Formula: see text]; [Formula: see text]) compared to RTA ([Formula: see text]; [Formula: see text]). Fusion classifiers performed significantly better than the RTA-alone classifiers with AUC values of 0.86 and 0.84 in differentiating BRCA1/2 carriers from low-risk women and unilateral cancer patients from low-risk women, respectively. In conclusion, deep learning extracted parenchymal characteristics from FFDMs performed as well as, or better than, conventional texture analysis in the task of distinguishing between cancer risk populations.

SU‐E‐J‐248: Contributions of Tumor and Stroma Phenotyping in Computer‐Aided Diagnosis

Purpose:To gain insight into the role of parenchyma stroma in the characterization of breast tumors by incorporating computerized mammographic parenchyma assessment into breast CADx in the task of distinguishing between malignant and benign lesions.Methods:This study was performed on 182 biopsy‐proven breast mass lesions, including 76 benign and 106 malignant lesions. For each full‐field digital mammogram (FFDM) case, our quantitative imaging analysis was performed on both the tumor and a region‐of‐interest (ROI) from the normal contralateral breast. The lesion characterization includes automatic lesion segmentation and feature extraction. Radiographic texture analysis (RTA) was applied on the normal ROIs to assess the mammographic parenchymal patterns of these contralateral normal breasts. Classification performance of both individual computer extracted features and the output from a Bayesian artificial neural network (BANN) were evaluated with a leave‐one‐lesion‐out method using receiver operating characteristic (ROC) analysis with area under the curve (AUC) as the figure of merit.Results:Lesion characterization included computer‐extracted phenotypes of spiculation, size, shape, and margin. For parenchymal pattern characterization, five texture features were selected, including power law beta, contrast, and edge gradient. Merging of these computer‐selected features using BANN classifiers yielded AUC values of 0.79 (SE=0.03) and 0.67 (SE=0.04) in the task of distinguishing between malignant and benign lesions using only tumor phenotypes and texture features from the contralateral breasts, respectively. Incorporation of tumor phenotypes with parenchyma texture features into the BANN yielded improved classification performance with an AUC value of 0.83 (SE=0.03) in the task of differentiating malignant from benign lesions.Conclusion:Combining computerized tumor and parenchyma phenotyping was found to significantly improve breast cancer diagnostic accuracy highlighting the need to consider both tumor and stroma in decision making.Funding: University of Chicago Dean Bridge Fund, NCI U24‐CA143848‐05, P50‐CA58223 Breast SPORE program, and Breast Cancer Research Foundation. COI: MLG is a stockholder in R2 technology/Hologic and receives royalties from Hologic, GE Medical Systems, MEDIAN Technologies, Riverain Medical, Mitsubishi, and Toshiba. MLG is a cofounder and stockholder in Quantitative Insights.

Comparative analysis of image-based phenotypes of mammographic density and parenchymal patterns in distinguishing between BRCA1/2 cases, unilateral cancer cases, and controls.

We statistically compare the contributions of parenchymal phenotypes to mammographic density in distinguishing between high-risk cases and low-risk controls. The age-matched evaluation included computerized mammographic assessment of breast percent density (PD) and parenchymal patterns (phenotypes of coarseness and contrast) from radiographic texture analysis (RTA) of the full-field digital mammograms from 456 cases: 53 women with BRCA1/2 gene mutations, 75 with unilateral cancer, and 328 at low risk of developing breast cancer. Image-based phenotypes of parenchymal pattern coarseness and contrast were each found to significantly discriminate between the groups; however, PD did not. From ROC analysis, PD alone yielded area under the fitted ROC curve (AUC) values of 0.53 ([Formula: see text]) and 0.57 ([Formula: see text]) in the classification task between BRCA1/2 gene-mutation carriers and low-risk women, and between unilateral cancer and low-risk women, respectively. In a round-robin evaluation with Bayesian artificial neural network (BANN) analysis, RTA yielded AUC values of 0.81 (95% confidence interval [0.71, 0.89]) and 0.70 (95% confidence interval [0.63, 0.77]) between the BRCA1/2 gene-mutation carriers and low-risk women, and between unilateral cancer and low-risk women, respectively. These results show that high-risk and low-risk women have different mammographic parenchymal patterns with significantly higher discrimination resulting from characteristics of the parenchymal patterns than just the breast PD.

Relationships between computer-extracted mammographic texture pattern features and BRCA1/2 mutation status: a cross-sectional study.

IntroductionMammographic density is similar among women at risk of either sporadic or BRCA1/2-related breast cancer. It has been suggested that digitized mammographic images contain computer-extractable information within the parenchymal pattern, which may contribute to distinguishing between BRCA1/2 mutation carriers and non-carriers.MethodsWe compared mammographic texture pattern features in digitized mammograms from women with deleterious BRCA1/2 mutations (n = 137) versus non-carriers (n = 100). Subjects were stratified into training (107 carriers, 70 non-carriers) and testing (30 carriers, 30 non-carriers) datasets. Masked to mutation status, texture features were extracted from a retro-areolar region-of-interest in each subject’s digitized mammogram. Stepwise linear regression analysis of the training dataset identified variables to be included in a radiographic texture analysis (RTA) classifier model aimed at distinguishing BRCA1/2 carriers from non-carriers. The selected features were combined using a Bayesian Artificial Neural Network (BANN) algorithm, which produced a probability score rating the likelihood of each subject’s belonging to the mutation-positive group. These probability scores were evaluated in the independent testing dataset to determine whether their distribution differed between BRCA1/2 mutation carriers and non-carriers. A receiver operating characteristic analysis was performed to estimate the model’s discriminatory capacity.ResultsIn the testing dataset, a one standard deviation (SD) increase in the probability score from the BANN-trained classifier was associated with a two-fold increase in the odds of predicting BRCA1/2 mutation status: unadjusted odds ratio (OR) = 2.00, 95% confidence interval (CI): 1.59, 2.51, P = 0.02; age-adjusted OR = 1.93, 95% CI: 1.53, 2.42, P = 0.03. Additional adjustment for percent mammographic density did little to change the OR. The area under the curve for the BANN-trained classifier to distinguish between BRCA1/2 mutation carriers and non-carriers was 0.68 for features alone and 0.72 for the features plus percent mammographic density.ConclusionsOur findings suggest that, unlike percent mammographic density, computer-extracted mammographic texture pattern features are associated with carrying BRCA1/2 mutations. Although still at an early stage, our novel RTA classifier has potential for improving mammographic image interpretation by permitting real-time risk stratification among women undergoing screening mammography.Electronic supplementary materialThe online version of this article (doi:10.1186/s13058-014-0424-8) contains supplementary material, which is available to authorized users.

Quantitative measurement of human ageing using computer-aided radiographic texture analysis

Studying the process of ageing in humans is dependent on methods for quantitative measurement of the physiological differences between younger and older individuals. Although in many cases the chronological age is used as a measurement of ageing, it provides merely a rough approximation of the actual physiological age of a person. Here, we propose a computer method for measuring the physiological age of the human knee by using quantitative analysis of the radiographic Haralick bone texture. Experiments using longitudinal data from the Baltimore Longitudinal Study of Aging show that the radiographic Haralick texture correlates with the chronological age, and that the ageing of the knee as reflected by the tibial anisotropy and measured using the radiographic texture is not linear to the chronological age. The analysis reveals that the bone ages until the person gets to the age of 40, then stabilises until the age of around 65, from where it continues to age. A period of rapid ageing was also detected around the age of 55. This shows that periods of rapid morphological changes of the knee occur not only during maturation, but also during ageing.

Radiographic bone texture analysis is correlated with 3D microarchitecture in the femoral head, and improves the estimation of the femoral neck fracture risk when combined with bone mineral density

PurposeFemoral neck fracture is a major public health problem in elderly persons, representing the main source of osteoporosis-related mortality and morbidity. In this study, we aimed at comparing radiographic texture analysis with three-dimensional (3D) microarchitecture in human femurs, and at evaluating whether bone texture analysis improved the assessment of the femoral neck fracture risk other than that obtainable by bone mineral density (BMD). Materials and methodsThirteen osteoporotic femoral heads from patients who fractured their femoral neck and twelve non-fractured femoral heads from osteoarthritic patients were studied using respectively (1) a new high-resolution digital X-ray device (BMA™, D3A Medical Systems) allowing for bone texture analysis with fractal parameter Hmean, and (2) a micro-computed tomograph (CT) for 3D microarchitecture. BMD was measured postoperatively by DXA in all patients in the contralateral femur. ResultsIn these femoral heads, we found that fractal parameter Hmean was correlated with 3D microarchitecture parameters: bone volume fraction (BV/TV), trabecular number (Tb.N), trabecular separation (Tb.Sp) and fractal dimension (FD) respectively (p<0.05). Then, fractal parameter Hmean was significantly lower in the femoral heads from the fractured group than from the non-fractured group (p<0.01). Finally, multiple regression analysis showed that combining bone texture analysis and total hip BMD significantly improved the estimation of the femoral neck fracture risk from adjusted r2=0.46 to adjusted r2=0.67 (p<0.05). ConclusionRadiographic bone texture analysis was correlated with 3D microarchitecture parameters in the femoral head, provided accurate discrimination between the femoral heads from the fractured and non-fractured groups, and significantly improved the estimation of the femoral neck fracture risk when combined with BMD.

Trabecular Homogeneity Index Derived From Plain Radiograph to Evaluate Bone Quality

Radiographic texture analysis has been developed lately to improve the assessment of bone architecture as a determinant of bone quality. We validate here an algorithm for the evaluation of trabecular homogeneity index (HI) in the proximal femur from hip radiographs, with a focus on the impact of the principal compressive system of the trabecular bone, and evaluate its correlation with femoral strength, bone mineral density (BMD), and volumetric trabecular structure parameters. A semiautomatic custom-made algorithm was applied to calculate the HI in the femoral neck and trochanteric areas from radiographs of 178 femoral bone specimens (mean age 79.3 ± 10.4 years). Corresponding neck region was selected in CT scans to calculate volumetric parameters of trabecular structure. The site-specific BMDs were assessed from dual-energy X-ray absorptiometry (DXA), and the femoral strength was experimentally tested in side-impact configuration. Regression analysis was performed between the HI and biomechanical femoral strength, BMD, and volumetric parameters. The correlation between HI and failure load was R(2) = 0.50; this result was improved to R(2) = 0.58 for cervical fractures alone. The discrimination of bones with high risk of fractures (load <3000 N) was similar for HI and BMD (AUC = 0.87). Regression analysis between the HIs versus site-specific BMDs yielded R(2) = 0.66 in neck area, R(2) = 0.60 in trochanteric area, and an overall of R(2) = 0.66 for the total hip. Neck HI and BMD correlated significantly with volumetric structure parameters. We present here a method to assess HI that can explain 50% of an experimental failure load and determines bones with high fracture risk with similar accuracy as BMD. The HI also had good correlation with DXA and computed tomography-derived data.

Assessment of bone mineral density and radiographic texture analysis at the tibial subchondral bone

Microstructural changes of subchondral bone constitute one of the figures characterising osteoarthritis on a structural level. Subchondral bone mineral density may reflect the complex relationship between bone and cartilage submitted to movement and loading. In this review, the authors discussed the interest of tibial subchondral bone mineral density assessment in the perspective of its diagnostic, etiopathogenic and prognostic value in osteoarthritis. In addition, the sources of variability linked to the measurement of tibial subchondral bone mineral density are precised. Trabecular bone structure characterisation by radiographic texture analyses may also represent a new promising tool to evaluate the microarchitectural changes that occur with initiation and progression of osteoarthritis. In this paper, the authors also highlighted the interest of different radiographic texture analyses and their clinical relevance in the field of osteoarthritis.

Bone texture analysis is correlated with three-dimensional microarchitecture and mechanical properties of trabecular bone in osteoporotic femurs

Fracture of the proximal femur is a major public health problem in elderly persons. It has recently been suggested that combining texture analysis and bone mineral density measurement improves the failure load prediction in human femurs. In this study, we aimed to compare bone texture analysis with three-dimensional (3D) microarchitecture and mechanical properties of trabecular bone in osteoporotic femurs. Eight femoral heads from osteoporotic patients who fractured their femoral neck provided 31 bone cores. Bone samples were studied using a new high-resolution digital X-ray device (BMA™, D3A Medical Systems) allowing for texture analysis with fractal parameter H (mean), and were examined using micro-computed tomography (microCT) for 3D microarchitecture. Finally, uniaxial compression tests to failure were performed to estimate failure load and apparent modulus of bone samples. The fractal parameter H (mean) was strongly correlated with bone volume fraction (BV/TV) (r=0.84) and trabecular thickness (Tb.Th) (r=0.91) (p<0.01). H (mean) was also markedly correlated with failure load (r=0.84) and apparent modulus (r=0.71) of core samples (p<0.01). Bone volume fraction (BV/TV) and trabecular thickness (Tb.Th) demonstrated significant correlations with failure load (r=0.85 and0.72, respectively) and apparent modulus (r=0.72 and 0.64, respectively) (p<0.01). Overall, the best predictors of failure load were H (mean), bone volume fraction, and trabecular thickness, with r (2) coefficients of 0.83, 0.76, and 0.80 respectively. This study shows that the fractal parameter H (mean) is correlated with 3D microCT parameters and mechanical properties of femoral head bone samples, which suggests that radiographic texture analysis is a suitable approach for trabecular bone microarchitecture assessment in osteoporotic femurs.

Radiographic texture analysis of densitometric calcaneal images: Relationship to clinical characteristics and to bone fragility

Osteoporotic fractures are related not only to bone mineral density (BMD) but also to bone structure or microarchitecture, which is not assessed routinely with currently available methods. We have developed radiographic texture analysis (RTA) for calcaneal images from a peripheral densitometer as an easy, noninvasive method for assessing bone structure. We conducted a cross-sectional study of the relationship between RTA and prevalent vertebral fractures (n = 148) among 900 subjects (ages 19 to 99 years, 94 males) referred for bone densitometry as part of their routine medical care. RTA features were derived from Fourier-based image analysis of the radiographic texture pattern (including root mean square, first moment, and power spectral analyses). RTA features were associated with age, weight, gender, and race, as well as glucocorticoid use. When controlling for clinical risk factors and BMD (or a summary measure calculated using FRAX algorithms), RTA features were significantly different for subjects with and without prevalent vertebral fractures [adjusted odds ratio (OR) = 1.5 per 1 standard deviation (SD) decrease in RTA feature beta, 95% confidence interval (CI) 1.2–1.8, p = .001]. Gender and use of pharmacologic therapy for osteoporosis did not significantly affect this association, suggesting that RTA can be applied to a wide range of densitometry patients. We conclude that RTA obtained using a portable instrument has a potential as a noninvasive method to enhance identification of patients at increased risk of osteoporotic fractures. Copyright © 2010 American Society for Bone and Mineral Research

Radiographic Texture Analysis (RTA) During Treatment with Alendronate

Radiographic Texture Analysis (RTA) During Treatment with Alendronate

Development and testing of texture discriminators for the analysis of trabecular bone in proximal femur radiographs

Texture analysis of femur radiographs may serve as a potential low cost technique to predict osteoporotic fracture risk and has received considerable attention in the past years. A further application of this technique may be the measurement of the quality of specific bone compartments to provide useful information for treatment of bone fractures. Two challenges of texture analysis are the selection of the best suitable texture measure and reproducible placement of regions of interest (ROIs). The goal of this in vitro study was to automatically place ROIs in radiographs of proximal femur specimens and to calculate correlations between various different texture analysis methods and the femurs' anchorage strength. Radiographs were obtained from 14 femoral specimens and bone mineral density (BMD) was measured in the femoral neck. Biomechanical testing was performed to assess the anchorage strength in terms of failure load, breakaway torque, and number of cycles. Images were segmented using a framework that is based on the usage of level sets and statistical in-shape models. Five ROIs were automatically placed in the head, upper and lower neck, trochanteric, and shaft compartment in an atlas subject. All other subjects were registered rigidly, affinely, and nonlinearly, and the resulting transformation was used to map the five ROIs onto the individual femora. In each ROI, texture features were extracted using gray level co-occurence matrices (GLCM), third-order GLCM, morphological gradients (MGs), Minkowski dimensions (MDs), Minkowski functionals (MFs), Gaussian Markov random fields, and scaling index method (SIM). Coefficients of determination for each texture feature with parameters of anchorage strength were computed. In a stepwise multiregression analysis, the most predictive parameters were identified in different models. Texture features were highly correlated with anchorage strength estimated by the failure load of up to R2=0.61 (MF and MG features, p<0.01) and were partially independent of BMD. The correlations were dependent on the choice of the ROI and the texture measure. The best predictive multiregression model for failure load R2adj=0.86 (p<0.001) included a set of recently developed texture methods (MF and SIM) but excluded bone mineral density and commonly used texture measures. The results suggest that texture information contained in trabecular bone structure visualized on radiographs may predict whether an implant anchorage can be used and may determine the local bone quality from preoperative radiographs.

Radiographic Texture Analysis of Densitometric Calcaneal Images – Relationship to Clinical Characteristics and Fragility

Radiographic Texture Analysis of Densitometric Calcaneal Images – Relationship to Clinical Characteristics and Fragility

Radiographic Texture Analysis in the Characterization of Trabecular Patterns in Periprosthetic Osteolysis

Periprosthetic osteolysis is a disease attributed to the body's reaction to fine polyethylene wear debris shed from total hip replacements. The purpose of this preliminary study was to investigate the ability of radiographic texture analysis (RTA) to characterize the trabecular texture patterns on pelvic images for osteolysis and normal total hip arthroplasty (THA) cases. Fourier-based and fractal-based texture features were calculated for a database of digitized radiographs from 202 THA cases, 70 of which developed osteolysis. The features were calculated from regions of interest selected at two time points: less than 1 month after surgery, and at the first clinical indication of osteolysis (or randomly selected follow-up time for normal cases). Receiver operating characteristic (ROC) analysis was used to compare feature performance at baseline and follow-up for osteolysis and normal cases. Separation between the RTA features for osteolysis and normal cases was negligible at baseline and increased substantially for the follow-up images. The directional Fourier-based feature provided the best separation with an A(z) value from ROC analysis of 0.75 for the follow-up images, in the task of distinguishing between normal and osteolytic cases. The results from this preliminary analysis indicate that qualitative changes in trabecular patterns from immediately after surgery to the eventual detection of osteolysis correspond to quantitative changes in RTA features. It therefore appears that RTA provides information that could potentially be useful to aid in the detection of this disease.