Image Analysis Framework Research Articles

A Heuristic Framework for Image Filtering and Segmentation: Application to Blood Vessel Immunohistochemistry.

The blood vessel density in a cancerous tissue sample may represent increased levels of tumor growth. However, identifying blood vessels in the histological (tissue) image is difficult and time-consuming and depends heavily on the observer's experience. To overcome this drawback, computer-aided image analysis frameworks have been investigated in order to boost object identification in histological images. We present a novel algorithm to automatically abstract the salient regions in blood vessel images. Experimental results show that the proposed framework is capable of deriving vessel boundaries that are comparable to those demarcated manually, even for vessel regions with weak contrast between the object boundaries and background clutter.

Abstract 4188: Evolutionary dynamics in breast cancer via MRI textural kinetic analysis

Abstract Objective: Genetic and clinical heterogeneity in breast cancer, as in other malignant tumors, is both a cause and consequence of evolutionary dynamics. Tissue-level intratumoral heterogeneity is apparent on imaging, as magnetic resonance imaging (MRI) studies typically show regional variations in blood flow and cell density. These imaging characteristics can be linked to underlying Darwinian dynamics since blood flow, through delivery of metabolic substrate and growth factors determines key environmental selection forces. In turn, changes in selection forces will select new cellular adaptations and molecular properties. Here we examine the connection between blood flow and a well recognized predictive and prognostic molecular characteristic of breast cancer cells - the expression of estrogen receptor (ER). In a Darwinian environment, cellular properties persist only if they confer a competitive advantage so ER expression will be maintained only if adequate concentrations of estrogen are present. Since estrogen is largely delivered via blood flow, we reasoned that ER negative tumors will be relatively avascular and vice-versa. We hypothesize that, quantitative analysis of blood flow, definable on MRI, can predict the ER status of the cancer cells. Materials and Methods: An IRB approved, retrospective chart review was performed on Breast Imaging Reporting and Data System (BI-RADS) 5 and 6 MRI reports at a single institution from 6/1/2010 to 1/1/2013. Twenty patients with clinical stage IIB or III and histopathologic diagnosis of invasive ductal or lobular carcinoma were identified: 12 were ER positive and 8 ER negative. To quantify blood flow, we examined T1 fat saturated pre and post contrast images performed at five time points: T0 (pre-contrast) and T1-T4 (approximately 120-480 seconds adjusted for breast thickness and field of view). Weight-based Gadolinum contrast agents were utilized. Image analysis included: post initial enhancement (PIE) map from pre and post contrast images, texture features (gray level co-occurrence matrix (GLCM), gray level run length matrix (GLRM) and local binary pattern histogram features (LBP-HF)). The imaging features were compared in ER positive and ER negative tumors. Results: Differing contrast kinetic patterns in ER positive and ER negative breast tumors were observed on textural kinetic analysis. A diagnostic accuracy of 90% was achieved with Naives Bayes classifier and leave-one-out cross validation. The combination of GLCM, LBP-HF and GLRM texture features could discriminate ER positive from ER negative breast tumors with 85% accuracy. Conclusion: Our data supports the hypothesis that imaging characteristics can, through application of evolutionary principles, provide insights into the cellular and molecular properties of cancer cells. This novel technique provides a framework for quantitative image analysis that may be applicable to other molecular and clinical aspects of breast cancer. Citation Format: Jennifer S. Drukteinis, Baishali Chaudhury, Lawrence O. Hall, Dmitry B. Goldgof, Robert Gillies, Robert A. Gatenby. Evolutionary dynamics in breast cancer via MRI textural kinetic analysis. [abstract]. In: Proceedings of the 105th Annual Meeting of the American Association for Cancer Research; 2014 Apr 5-9; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2014;74(19 Suppl):Abstract nr 4188. doi:10.1158/1538-7445.AM2014-4188

The undecimated wavelet transform–multivariate image analysis (UWT-MIA) for simultaneous extraction of spectral and spatial information

Combining color (spectral) and textural information often leads to improved performance of image-based sensors developed for different applications, such as process monitoring and prediction of process or product quality variables. A new method based on the undecimated wavelet transform and multivariate image analysis (UWT-MIA) is proposed in this paper for simultaneous extraction of spatial and spectral information. The key advantages of this approach are: 1) it uses continuous wavelets which have a constant resolution over all scales compared to discrete wavelets, and are better suited for extracting size distribution features, 2) the wavelet detail and approximation sub-images have the same size and are spatially congruent which allows stacking the sub-images obtained at all scales and orientations (and wavelengths for multi- and hyperspectral images) as a separate channel in a new multivariate image from which a single MIA model can be built. The performance of UWT-MIA is illustrated using both synthetic and natural images. It is shown that variations in color, size and orientation of objects of interest can be tracked efficiently within the same MIA model. The method can also be cast within the multiresolutional multivariate image analysis (MR-MIA) framework proposed in the literature.

A comparison of Gaussian process regression, random forests and support vector regression for burn severity assessment in diseased forests

Remote sensing has been widely adopted to map post-fire burn severity over large forested areas. Statistical regression based on linear or simple non-linear assumptions is typically used to link post-fire forest reflectance with the degree of burn severity. However, this linkage becomes complicated if forests experienced severe mortality caused by pre-fire disease or insect outbreaks, which is likely to occur more frequently as a result of rapid climate change. In an effort to improve the understanding of the relationship between forest reflectance and fire-disease disturbances, this study explored the efficacy of three machine learning techniques, that is, Gaussian process regression (GPR), random forests (RF) and support vector regression (SVR), within a geographic object-based image analysis (GEOBIA) framework to assess burn severity in a forest subject to pre-fire disease epidemics. MASTER [MODIS (Moderate Resolution Imaging Spectroradiometer)/ASTER (Advanced Spaceborne Thermal Emission and Reflection Radiometer)] airborne sensor was applied to collect relatively high spatial (4 m) and high spectral (50 bands) resolution reflectance data. Results show that RF, SVR and GPR models outperformed conventional multiple regression by 48%, 29% and 27%, respectively. Compared to SVR and GPR, RF not only achieved better performance in burn severity assessment, but also demonstrated lower sensitivity to the application of different combinations of remote sensing variables. In addition to Normalized Burn Ratio (NBR), this study further revealed the importance of image-texture (representing spectral variability within and between neighbourhood forest patches) in burn severity mapping over diseased forests.

Integral-geometry characterization of photobiomodulation effects on retinal vessel morphology.

The morphological characterization of quasi-planar structures represented by gray-scale images is challenging when object identification is sub-optimal due to registration artifacts. We propose two alternative procedures that enhances object identification in the integral-geometry morphological image analysis (MIA) framework. The first variant streamlines the framework by introducing an active contours segmentation process whose time step is recycled as a multi-scale parameter. In the second variant, we used the refined object identification produced in the first variant to perform the standard MIA with exact dilation radius as multi-scale parameter. Using this enhanced MIA we quantify the extent of vaso-obliteration in oxygen-induced retinopathic vascular growth, the preventative effect (by photobiomodulation) of exposure during tissue development to near-infrared light (NIR, 670 nm), and the lack of adverse effects due to exposure to NIR light.

Coupling high-resolution satellite imagery with ALS-based canopy height model and digital elevation model in object-based boreal forest habitat type classification

We developed a classification workflow for boreal forest habitat type mapping. In object-based image analysis framework, Fractal Net Evolution Approach segmentation was combined with random forest classification. High-resolution WorldView-2 imagery was coupled with ALS based canopy height model and digital terrain model. We calculated several features (e.g. spectral, textural and topographic) per image object from the used datasets. We tested different feature set alternatives; a classification accuracy of 78.0% was obtained when all features were used. The highest classification accuracy (79.1%) was obtained when the amount of features was reduced from the initial 328 to the 100 most important using Boruta feature selection algorithm and when ancillary soil and land-use GIS-datasets were used. Although Boruta could rank the importance of features, it could not separate unimportant features from the important ones. Classification accuracy was bit lower (78.7%) when the classification was performed separately on two areas: the areas above and below 1m vertical distance from the nearest stream. The data split, however, improved the classification accuracy of mire habitat types and streamside habitats, probably because their proportion in the below 1m data was higher than in the other datasets. It was found that several types of data are needed to get the highest classification accuracy whereas omitting some feature groups reduced the classification accuracy. A major habitat type in the study area was mesic forests in different successional stages. It was found that the inner heterogeneity of different mesic forest age groups was large and other habitat types were often inside this heterogeneity.

Coupling formalized knowledge bases with object-based image analysis

Object-based image analysis (OBIA) is a widely used method for knowledge-based interpretation of very high resolution imagery. It relies on expert knowledge to classify the desired classes from the imagery at hand. The definition of classes is subjective, usually project-specific and not shared with the community. Ontologies as a form of knowledge representation technique are acknowledged as solution to establish and document class definitions independently of an OBIA framework. However, ontologies have not yet been strongly integrated in this image analysis framework. This paper presents a method to automatically integrate ontologies in OBIA. The method has been implemented as a tool to be used with the eCognition® software (Trimble, Sunnyvale, CA, USA). A case study was conducted for classifying the land cover classes defined by the Environment Agency of Austria in the Land Information System Austria (LISA) project using WorldView-2 image. The strength of this approach is the direct integration of ontologies into the OBIA process, which reduces the effort necessary to define the classes for image analysis and simultaneously reduces its subjectivity.

Development of a nationwide approach for large scale estimation of green roof retrofitting areas and roof-top solar energy potential using VHR natural colour orthoimagery and DSM data over Thessaloniki, Greece

Buildings, and other engineered structures that form cities, are responsible for a significant portion of the local and global impacts of climate change. Therefore, there is a need for the increase and large-scale implementation of energy-efficient and renewable energy-generation technologies. In this paper, we investigate a remotely sensed approach for assessing the potential capacity of installing rooftop photovoltaic systems and/or implementing green roof retrofitting measures in an urbanized area. In particular, we analyse the ways in which freely available, no-cost, very high spatial resolution orthoimagery and Digital Surfaces Models, along with geospatial vector data, can assist in delineating available roof area at the level of individual buildings across a Mediterranean city. The available data-sets are integrated and processed within a Geographical Object Based Image Analysis framework. The method was developed on the basis of a test area consisting of the town of Thessaloniki in Northern Greece. The correlation between the automated extracted roof area and the manual digitized reference data had a value of up to 0.9. The described approach can be applied nationwide across Greece, considering the national availability coverage of the data-sets, while the semantics can readily be transferred to neighbouring Mediterranean countries.

Cardiac image processing techniques

Heart disease is the leading cause of death in the modern world. Cardiac image processing is now routinely applied for detecting, classification and diagnosis of heart diseases. One of the most common uses of processing methods that are now widely applied are cardiac segmentation [1] and registration methods [2], that are used in order to extract the detailed anatomy and function of the heart. Automatic segmentation plays a central role when inspecting reconstructed 3D cardiac images from CT or MR scanners. An accurate classification of the different cardiac regions is usually the first step of tasks like: cardiac visualization, coronary artery inspection, measurement of the ejection fraction for the left and right ventricles and wall motion analysis. In a clinical context, physicians often mentally integrate image information from different modalities. Automatic registration, based on computer programs, might, however, offer better accuracy and repeatability and save time [3]. Cardiac image registration remains a challenge because of the numerous specific problems mainly related to the different motion sources (patient, respiration, heart) and to the specificity of each imaging modality. Up to now, no general method could automatically register any modality with any other modality so far. This paper presents a survey of shape modeling applications to cardiac image analysis from MRI, CT, echocardiography, PET, and SPECT and aims to introduce new methodologies in this field, classify major contributions in image-based cardiac modeling, provide a tutorial to beginners to initiate their own studies, and introduce the major challenges of registration and segmentation and provide practical examples. Image-driven processing methods, such as thresholding, region-based or edge-based techniques, or else pixel classification [4-6], provide a limited framework for further medical image analysis. They can include geometrical information, as well as high level information, in the so-called shape prior based segmentation framework, or through active shape models and active appearance models. At last, atlas guided segmentation also make use of a set of manually segmented images. By using different analysis software of cardiac images, CAD prototypes can be used in clinical routines in order to provide a computer output as a second reader to assist physicians in the detection of abnormalities, quantification of disease progression and differential diagnosis of lesions [7]. Computerized analysis of cardiac images in combination with artificial intelligence can be used in clinical practice and may contribute to more efficient diagnosis.

TH‐E‐BRF‐04: Characterizing the Response of Texture‐Based CT Image Features for Quantification of Radiation‐Induced Normal Lung Damage

Purpose:Radiation induced lung damage (RILD) is an important dose‐limiting toxicity for patients treated with radiation therapy. Scoring systems for RILD are subjective and limit our ability to find robust predictors of toxicity. We investigate the dose and time‐related response for texture‐based lung CT image features that serve as potential quantitative measures of RILD.Methods:Pre‐ and post‐RT diagnostic imaging studies were collected for retrospective analysis of 21 patients treated with photon or proton radiotherapy for NSCLC. Total lung and selected isodose contours (0–5, 5–15, 15–25Gy, etc.) were deformably registered from the treatment planning scan to the pre‐RT and available follow‐up CT studies for each patient. A CT image analysis framework was utilized to extract 3698 unique texture‐based features (including co‐occurrence and run length matrices) for each region of interest defined by the isodose contours and the total lung volume. Linear mixed models were fit to determine the relationship between feature change (relative to pre‐RT), planned dose and time post‐RT.Results:Seventy‐three follow‐up CT scans from 21 patients (median: 3 scans/patient) were analyzed to describe CT image feature change. At the p=0.05 level, dose affected feature change in 2706 (73.1%) of the available features. Similarly, time affected feature change in 408 (11.0%) of the available features. Both dose and time were significant predictors of feature change in a total of 231 (6.2%) of the extracted image features.Conclusion:Characterizing the dose and time‐related response of a large number of texture‐based CT image features is the first step toward identifying objective measures of lung toxicity necessary for assessment and prediction of RILD. There is evidence that numerous features are sensitive to both the radiation dose and time after RT. Beyond characterizing feature response, further investigation is warranted to determine the utility of these features as surrogates of clinically significant lung injury.

Efficient processing of fluorescence images using directional multiscale representations.

Recent advances in high-resolution fluorescence microscopy have enabled the systematic study of morphological changes in large populations of cells induced by chemical and genetic perturbations, facilitating the discovery of signaling pathways underlying diseases and the development of new pharmacological treatments. In these studies, though, due to the complexity of the data, quantification and analysis of morphological features are for the vast majority handled manually, slowing significantly data processing and limiting often the information gained to a descriptive level. Thus, there is an urgent need for developing highly efficient automated analysis and processing tools for fluorescent images. In this paper, we present the application of a method based on the shearlet representation for confocal image analysis of neurons. The shearlet representation is a newly emerged method designed to combine multiscale data analysis with superior directional sensitivity, making this approach particularly effective for the representation of objects defined over a wide range of scales and with highly anisotropic features. Here, we apply the shearlet representation to problems of soma detection of neurons in culture and extraction of geometrical features of neuronal processes in brain tissue, and propose it as a new framework for large-scale fluorescent image analysis of biomedical data.

Environmental Object Recognition in a Natural Image

Natural images, which are filled with intriguing stimuli of spatial objects, represent our cognition and are rich in spatial information. Accurate extraction of spatial objects is challenging due to the associated spatial and spectral complexities in object recognition. In this paper, the authors tackle the problem of spatial object extraction in a GEOgraphic Object Based Image Analysis framework taking psychological and mathematical complexities into account. In doing so, the authors experimented with human and GEOBIA based recognition and segmentation in an image of an area of natural importance, the Ventoux Mountain, France. Focus was given to scales, color, and texture properties at multiple levels in delineating the candidate spatial objects from the natural image. Such objects along with the original image were provided to the human subjects in two stages and three different groups of samples. The results of two stages were collated and analyzed. The analysis showed that there exist different ways to comprehend the geographical objects according to priori knowledge.

Automated image analysis framework for high-throughput determination of grapevine berry sizes using conditional random fields

The berry size is one of the most important fruit traits in grapevine breeding. Non-invasive, image-based phenotyping promises a fast and precise method for the monitoring of the grapevine berry size. In the present study an automated image analyzing framework was developed in order to estimate the size of grapevine berries from images in a high-throughput manner. The framework includes (i) the detection of circular structures which are potentially berries and (ii) the classification of these into the class ‘berry’ or ‘non-berry’ by utilizing a conditional random field. The approach used the concept of a one-class classification, since only the target class ‘berry’ is of interest and needs to be modeled. Moreover, the classification was carried out by using an automated active learning approach, i.e. no user interaction is required during the classification process and in addition, the process adapts automatically to changing image conditions, e.g. illumination or berry color. The framework was tested on three datasets consisting in total of 139 images. The images were taken in an experimental vineyard at different stages of grapevine growth according to the BBCH scale. The mean berry size of a plant estimated by the framework correlates with the manually measured berry size by 0.88.

Optimizing multi-resolution segmentation scale using empirical methods: Exploring the sensitivity of the supervised discrepancy measure Euclidean distance 2 (ED2)

Multiresolution segmentation (MRS) has proven to be one of the most successful image segmentation algorithms in the geographic object-based image analysis (GEOBIA) framework. This algorithm is relatively complex and user-dependent; scale, shape, and compactness are the main parameters available to users for controlling the algorithm. Plurality of segmentation results is common because each parameter may take a range of values within its parameter space or different combinations of values among parameters. Finding optimal parameter values through a trial-and-error process is commonly practiced at the expense of time and labor, thus, several alternative supervised and unsupervised methods for supervised automatic parameter setting have been proposed and tested. In the case of supervised empirical assessments, discrepancy measures are employed for computing measures of dissimilarity between a reference polygon and an image object candidate. Evidently the reliability of the optimal-parameter prediction heavily relies on the sensitivity of the segmentation quality metric. The idea behind pursuing optimal parameter setting is that, for instance, a given scale setting provides image object candidates different from the other scale setting; thus, by design the supervised quality metric should capture this difference. In this exploratory study, we selected the Euclidean distance 2 (ED2) metric, a recently proposed supervised metric, whose main design goal is to optimize the geometrical discrepancy (potential segmentation error (PSE)) and arithmetic discrepancy between image objects and reference polygons (number-of segmentation ratio (NSR)) in two dimensional Euclidean space, as a candidate to investigate the validity and efficacy of empirical discrepancy measures for finding the optimal scale parameter setting of the MRS algorithm. We chose test image scenes from four different space-borne sensors with varying spatial resolutions and scene contents and systematically segmented them using the MRS algorithm at a series of parameter settings. The discriminative capacity of the ED2 metric across different scales groups was tested using non-parametric statistical methods. Our results showed that the ED2 metric significantly discriminates the quality of image object candidates at smaller scale values but it loses the sensitivity at larger scale values. This questions the meaningfulness of the ED2 metric in the MRS algorithm’s parameter optimization. Our contention is that the ED2 metric provides some notion of the optimal scale parameter at the expense of time. In this respect, especially in operational-level image processing, it is worth to re-think the trade-off between execution time of the processor-intensive MRS algorithm at series of parameter settings targeting a less-sensitive quality metric and an expert-lead trial-and-error approach.

A mesh generation and machine learning framework for Drosophila gene expression pattern image analysis.

BackgroundMulticellular organisms consist of cells of many different types that are established during development. Each type of cell is characterized by the unique combination of expressed gene products as a result of spatiotemporal gene regulation. Currently, a fundamental challenge in regulatory biology is to elucidate the gene expression controls that generate the complex body plans during development. Recent advances in high-throughput biotechnologies have generated spatiotemporal expression patterns for thousands of genes in the model organism fruit fly Drosophila melanogaster. Existing qualitative methods enhanced by a quantitative analysis based on computational tools we present in this paper would provide promising ways for addressing key scientific questions.ResultsWe develop a set of computational methods and open source tools for identifying co-expressed embryonic domains and the associated genes simultaneously. To map the expression patterns of many genes into the same coordinate space and account for the embryonic shape variations, we develop a mesh generation method to deform a meshed generic ellipse to each individual embryo. We then develop a co-clustering formulation to cluster the genes and the mesh elements, thereby identifying co-expressed embryonic domains and the associated genes simultaneously. Experimental results indicate that the gene and mesh co-clusters can be correlated to key developmental events during the stages of embryogenesis we study. The open source software tool has been made available at http://compbio.cs.odu.edu/fly/.ConclusionsOur mesh generation and machine learning methods and tools improve upon the flexibility, ease-of-use and accuracy of existing methods.

High-Performance Computational Analysis of Glioblastoma Pathology Images with Database Support Identifies Molecular and Survival Correlates.

In this paper, we present a novel framework for microscopic image analysis of nuclei, data management, and high performance computation to support translational research involving nuclear morphometry features, molecular data, and clinical outcomes. Our image analysis pipeline consists of nuclei segmentation and feature computation facilitated by high performance computing with coordinated execution in multi-core CPUs and Graphical Processor Units (GPUs). All data derived from image analysis are managed in a spatial relational database supporting highly efficient scientific queries. We applied our image analysis workflow to 159 glioblastomas (GBM) from The Cancer Genome Atlas dataset. With integrative studies, we found statistics of four specific nuclear features were significantly associated with patient survival. Additionally, we correlated nuclear features with molecular data and found interesting results that support pathologic domain knowledge. We found that Proneural subtype GBMs had the smallest mean of nuclear Eccentricity and the largest mean of nuclear Extent, and MinorAxisLength. We also found gene expressions of stem cell marker MYC and cell proliferation maker MKI67 were correlated with nuclear features. To complement and inform pathologists of relevant diagnostic features, we queried the most representative nuclear instances from each patient population based on genetic and transcriptional classes. Our results demonstrate that specific nuclear features carry prognostic significance and associations with transcriptional and genetic classes, highlighting the potential of high throughput pathology image analysis as a complementary approach to human-based review and translational research.

A Combined Object- and Pixel-Based Image Analysis Framework for Urban Land Cover Classification of VHR Imagery

This paper aims at exploiting the advantages of pixel-based and object-based image analysis approaches for urban land cover classification of very high resolution (vHR) satellite imagery through a combined object- and pixel-based image analysis framework. The framework starts with segmenting the image resulting in several spectral and spatial features of segments. To overcome the curse of dimensionality, a wavelet ­ based feature extraction method is proposed to reduce the number of features. The wavelet-based method is automatic, fast, and can preserve local variations in objects' spectral/ spatial signatures. Finally, the extracted features together with the original bands of the image are classified using the conventional pixel-based Maximum Likelihood classifica­tion. The proposed method was tested on the WorldView-2, QuickBird, and Ikonos images of the same urban area for comparison purposes. Results show up to 17 percent, 10 percent, and 11 percent improvement in kappa coefficients compared to the case in which only the original bands of the image are used for WV-2, QB, and IK, respectively. Furthermore, the objects' spectral features contribute more to increasing classification accuracy than spatial features.

Sleep posture analysis using a dense pressure sensitive bedsheet

Sleep posture affects the quality of our sleep and is especially important for such medical conditions as sleep apnea and pressure ulcers. In this paper, we propose a design for a dense pressure-sensitive bedsheet along with an algorithmic framework to recognize and monitor sleeping posture. The bedsheet system uses comfortable textile sensors that produces high-resolution pressure maps. We develop a novel framework for pressure image analysis to monitor sleep postures, including a set of geometrical features for sleep posture characterization and three sparse classifiers for posture recognition. In demonstrating this system, we run 2 pilot studies: one evaluates the performance of our methods with 14 subjects to analyze 6 common postures; the other is a series of overnight studies to verify continuous performance. The experimental results show that our proposed method enables reliable sleep posture recognition and offers better overall performance than traditional methods, achieving up to 83.0% precision and 83.2% recall on average.

Feasibility of polarized all-sky imaging for aerosol characterization

Abstract. In this study, we investigate the method of polarized all-sky imaging with respect to aerosol characterization. As a technical frame work for image processing and analysis, we propose Zernike polynomials to decompose the relative Stokes parameter distributions. This defines a suitable and efficient feature vector which is also appealing because it is independent of calibration, circumvents overexposure problems and is robust against pixel noise. We model the polarized radiances of realistic aerosol scenarios and construct the feature vector space of the key aerosol types in terms of the first two principal components describing the maximal variances. We show that, using this representation, aerosol types can be clearly distinguished with respect to fine and coarse mode dominated size distribution and index of refraction. We further investigate the individual influences of varying aerosol properties and solar zenith angle. This suggests that polarized all-sky imaging may improve aerosol characterization in combination with sky scanning radiometers of the existing Aerosol Robotic Network (AERONET) especially at low aerosol optical depths and low solar zenith angles.

Improvements in hip trabecular, subcortical, and cortical density and mass in postmenopausal women with osteoporosis treated with denosumab

In the FREEDOM study, denosumab treatment (60mg every 6months) decreased bone resorption, increased bone mineral density (BMD), and reduced new vertebral, nonvertebral, and hip fractures over 36months in postmenopausal women with osteoporosis. In a subset of these women, hip quantitative computed tomography (QCT) was performed at baseline and months 12, 24, and 36. These scans were analyzed using Medical Image Analysis Framework (MIAF) software, which allowed assessment of total hip integral, trabecular, subcortical, and cortical compartments; the cortical compartment was further divided into 2 areas of interest (outer and inner cortex). This substudy reports changes in BMD and bone mineral content (BMC) from baseline and compared placebo with denosumab over 36months of treatment (placebo N=26; denosumab N=36). Denosumab treatment resulted in significant improvements in total hip integral volumetric BMD (vBMD) and BMC from baseline at each time point. At month 36, the mean percentage increase from baseline in total hip integral vBMD and BMC was 6.4% and 4.8%, respectively (both p<0.0001). These gains were accounted for by significant increases in vBMD and BMC in the trabecular, subcortical, and cortical compartments. In the placebo group, total hip integral vBMD and BMC decreased at month 36 from baseline by −1.5% and −2.6%, respectively (both p<0.05). The differences between denosumab and placebo were also significant at months 12, 24, and 36 for integral, trabecular, subcortical, and cortical vBMD and BMC (all p<0.05 to <0.0001). While the largest percentage differences occurred in trabecular vBMD and BMC, the largest absolute differences occurred in cortical vBMD and BMC. In summary, denosumab significantly improved both vBMD and BMC from baseline and placebo, assessed by QCT MIAF, in the integral, trabecular, subcortical, and cortical hip compartments, all of which are relevant to bone strength.