Search

Background: More than 50 percent of all infants born very preterm will experience significant motor and cognitive impairment. Provision of early intervention is dependent upon accurate, early identification of infants at risk of adverse outcomes. Magnetic resonance imaging at term equivalent age combined with General Movements assessment at 12 weeks corrected age is currently the most accurate method for early prediction of cerebral palsy at 12 months corrected age. To date no studies have compared the use of earlier magnetic resonance imaging combined with neuromotor and neurobehavioural assessments (at 30 weeks postmenstrual age) to predict later motor and neurodevelopmental outcomes including cerebral palsy (at 12-24 months corrected age). This study aims to investigate i) the relationship between earlier brain imaging and neuromotor/neurobehavioural assessments at 30 and 40 weeks postmenstrual age, and ii) their ability to predict motor and neurodevelopmental outcomes at 3 and 12 months corrected age., Methods/design: This prospective cohort study will recruit 80 preterm infants born ≤ 30 week's gestation and a reference group of 20 healthy term born infants from the Royal Brisbane & Women's Hospital in Brisbane, Australia. Infants will undergo brain magnetic resonance imaging at approximately 30 and 40 weeks postmenstrual age to develop our understanding of very early brain structure at 30 weeks and maturation that occurs between 30 and 40 weeks postmenstrual age. A combination of neurological (Hammersmith Neonatal Neurologic Examination), neuromotor (General Movements, Test of Infant Motor Performance), neurobehavioural (NICU Network Neurobehavioural Scale, Premie-Neuro) and visual assessments will be performed at 30 and 40 weeks postmenstrual age to improve our understanding of the relationship between brain structure and function. These data will be compared to motor assessments at 12 weeks corrected age and motor and neurodevelopmental outcomes at 12 months corrected age (neurological assessment by paediatrician, Bayley scales of Infant and Toddler Development, Alberta Infant Motor Scale, Neurosensory Motor Developmental Assessment) to differentiate atypical development (including cerebral palsy and/or motor delay)., Discussion: Earlier identification of those very preterm infants at risk of adverse neurodevelopmental and motor outcomes provides an additional period for intervention to optimise outcomes., Trial Registration: Australian New Zealand Clinical Trials Registry ACTRN12613000280707. Registered 8 March 2013.

Background: CT-MR registration is a critical component of many radiation oncology protocols. In prostate external beam radiation therapy, it allows the propagation of MR-derived contours to reference CT images at the planning stage, and it enables dose mapping during dosimetry studies. The use of carefully registered CT-MR atlases allows the estimation of patient specific electron density maps from MRI scans, enabling MRI-alone radiation therapy planning and treatment adaptation. In all cases, the precision and accuracy achieved by registration influences the quality of the entire process., Problem: Most current registration algorithms do not robustly generalize and lack inverse-consistency, increasing the risk of human error and acting as a source of bias in studies where information is propagated in a particular direction, e.g. CT to MR or vice versa. In MRI-based treatment planning where both CT and MR scans serve as spatial references, inverse-consistency is critical, if under-acknowledged., Purpose: A robust, inverse-consistent, rigid/affine registration algorithm that is well suited to CT-MR alignment in prostate radiation therapy is presented., Method: The presented method is based on a robust block-matching optimization process that utilises a half-way space definition to maintain inverse-consistency. Inverse-consistency substantially reduces the influence of the order of input images, simplifying analysis, and increasing robustness. An open source implementation is available online at http://aehrc.github.io/Mirorr/., Results: Experimental results on a challenging 35 CT-MR pelvis dataset demonstrate that the proposed method is more accurate than other popular registration packages and is at least as accurate as the state of the art, while being more robust and having an order of magnitude higher inverse-consistency than competing approaches., Conclusion: The presented results demonstrate that the proposed registration algorithm is readily applicable to prostate radiation therapy planning., (Copyright © 2015. Published by Elsevier B.V.)

Active contour techniques have been widely employed for medical image segmentation. Significant effort has been focused on the use of training data to build prior statistical models applicable specifically to problems where the objects of interest are embedded in cluttered background. Usually, the training data consist of whole shapes of certain organs or structures obtained manually by clinical experts. The resulting prior models enforce segmentation accuracy uniformly over the entire structure or structures to be identified. In this paper, we consider a new coupled prior shape model which is demonstrated to provide high accuracy, specifically in the region of the interest where precision is most needed for the application of the segmentation of the femur and tibia in magnetic resonance (MR) images. Experimental results for the segmentation of MR images of human knees demonstrate that the combination of the new coupled prior shape and a directional edge force provides the improved segmentation performance. Moreover, the new approach allows for equivalent accurate identification of bone marrow lesions, a promising biomarker related to osteoarthritis, to the current state of the art but requires significantly less manual interaction.

Purpose: To propose a robust and automated model-based semantic registration for the multimodal alignment of the knee bone and cartilage from three-dimensional (3D) MR image data., Materials and Methods: The movement of the knee joint can be semantically interpreted as a combination of movements of each bone. A semantic registration of the knee joint was implemented by separately reconstructing the rigid movements of the three bones. The proposed method was validated by registering 3D morphological MR datasets of 25 subjects into the corresponding T2 map datasets, and was compared with rigid and elastic methods using two criteria: the spatial overlap of the manually segmented cartilage and the distance between the same landmarks in the reference and target datasets., Results: The mean Dice Similarity Coefficient (DSC) of the overlapped cartilage segmentation was increased to 0.68 ± 0.1 (mean ± SD) and the landmark distance was reduced to 1.3 ± 0.3 mm after the proposed registration method. Both metrics were statistically superior to using rigid (DSC: 0.59 ± 0.12; landmark distance: 2.1 ± 0.4 mm) and elastic (DSC: 0.64 ± 0.11; landmark distance: 1.5 ± 0.5 mm) registrations., Conclusion: The proposed method is an efficient and robust approach for the automated registration between morphological knee datasets and T2 MRI relaxation maps., (© 2014 Wiley Periodicals, Inc.)

We present a statistical shape model approach for automated segmentation of the proximal humerus and scapula with subsequent bone-cartilage interface (BCI) extraction from 3D magnetic resonance (MR) images of the shoulder region. Manual and automated bone segmentations from shoulder MR examinations from 25 healthy subjects acquired using steady-state free precession sequences were compared with the Dice similarity coefficient (DSC). The mean DSC scores between the manual and automated segmentations of the humerus and scapula bone volumes surrounding the BCI region were 0.926  ±  0.050 and 0.837  ±  0.059, respectively. The mean DSC values obtained for BCI extraction were 0.806  ±  0.133 for the humerus and 0.795  ±  0.117 for the scapula. The current model-based approach successfully provided automated bone segmentation and BCI extraction from MR images of the shoulder. In future work, this framework appears to provide a promising avenue for automated segmentation and quantitative analysis of cartilage in the glenohumeral joint.

(11)C-Pittsburgh compound B (PiB) is a positron emission tomography (PET) tracer designed to bind to amyloid-β (Aβ) plaques, one of the hallmarks of Alzheimer's disease (AD). The potential of PiB as an early marker of AD led to the increasing use of PiB in clinical research studies and development of several F-18-labeled Aβ radiotracers. Automatic quantification of PiB images requires an accurate parcellation of the brain's gray matter (GM). Typically, this relies on a coregistered magnetic resonance imaging (MRI) to extract the cerebellar GM, compute the standardized uptake value ratio (SUVR), and provide parcellation and segmentation for quantification of regional and global SUVR. However, not all subjects can undergo MRI, in which case, an MR-less method is desirable. In this study, we assess 3 PET-only quantification methods: a mean atlas, an adaptive atlas, and a multi-atlas approaches on a database of 237 subjects having been imaged with both PiB PET and MRI. The PET-only methods were compared against MR-based SUVR quantification and evaluated in terms of correlation, average error, and performance in classifying subjects with low and high Aβ deposition. The mean atlas method suffered from a significant bias between the estimated neocortical SUVR and the PiB status, resulting in an overall error of 5.6% (R(2) = 0.98), compared with the adaptive and multi-atlas approaches that had errors of 3.06% and 2.74%, respectively (R(2) = 0.98), and no significant bias. In classifying PiB-negative from PiB-positive subjects, the mean atlas had 10 misclassified subjects compared with 0 for the adaptive and 1 for the multi-atlas approach. Overall, the adaptive and the multi-atlas approaches performed similarly well against the MR-based quantification and would be a suitable replacements for PiB quantification when no MRI is available., (Copyright © 2015 Elsevier Inc. All rights reserved.)

Accurate segmentation of hip joint cartilage from magnetic resonance (MR) images offers opportunities for quantitative investigations of pathoanatomical conditions such as osteoarthritis. In this paper, we present a fully automatic scheme for the segmentation of the individual femoral and acetabular cartilage plates in the human hip joint from high-resolution 3D MR images. The developed scheme uses an improved optimal multi-object multi-surface graph search framework with an arc-weighted graph representation that incorporates prior morphological knowledge as a basis for segmentation of the individual femoral and acetabular cartilage plates despite weak or incomplete boundary interfaces. This automated scheme was validated against manual segmentations from 3D true fast imaging with steady-state precession (TrueFISP) MR examinations of the right hip joints in 52 asymptomatic volunteers. Compared with expert manual segmentations of the combined, femoral and acetabular cartilage volumes, the automatic scheme obtained mean (± standard deviation) Dice's similarity coefficients of 0.81 (± 0.03), 0.79 (± 0.03) and 0.72 (± 0.05). The corresponding mean absolute volume difference errors were 8.44% (± 6.36), 9.44% (± 7.19) and 9.05% (± 8.02). The mean absolute differences between manual and automated measures of cartilage thickness for femoral and acetabular cartilage plates were 0.13 mm (± 0.12) and 0.11 mm (± 0.11), respectively.

The brains of patients suffering from Alzheimer's disease (AD) have three classical pathological hallmarks: amyloid-beta (Aβ) plaques, tau tangles, and neurodegeneration, including that of cholinergic neurons of the basal forebrain. However the relationship between Aβ burden and basal forebrain degeneration has not been extensively studied. To investigate this association, basal forebrain volumes were determined from magnetic resonance images of controls, subjects with amnestic mild cognitive impairment (aMCI) and AD patients enrolled in the longitudinal Alzheimer's Disease Neuroimaging Initiative (ADNI) and Australian Imaging, Biomarkers and Lifestyle (AIBL) studies. In the AIBL cohort, these volumes were correlated within groups to neocortical gray matter retention of Pittsburgh compound B (PiB) from positron emission tomography images as a measure of Aβ load. The basal forebrain volumes of AD and aMCI subjects were significantly reduced compared to those of control subjects. Anterior basal forebrain volume was significantly correlated to neocortical PiB retention in AD subjects and aMCI subjects with high Aβ burden, whereas posterior basal forebrain volume was significantly correlated to neocortical PiB retention in control subjects with high Aβ burden. Therefore this study provides new evidence for a correlation between neocortical Aβ accumulation and basal forebrain degeneration. In addition, cluster analysis showed that subjects with a whole basal forebrain volume below a determined cut-off value had a 7 times higher risk of having a worse diagnosis within ~18 months.

Background Context: Magnetic resonance (MR) examinations of morphologic characteristics of intervertebral discs (IVDs) have been used extensively for biomechanical studies and clinical investigations of the lumbar spine. Traditionally, the morphologic measurements have been performed using time- and expertise-intensive manual segmentation techniques not well suited for analyses of large-scale studies.., Purpose: The purpose of this study is to introduce and validate a semiautomated method for measuring IVD height and mean sagittal area (and volume) from MR images to determine if it can replace the manual assessment and enable analyses of large MR cohorts., Study Design/setting: This study compares semiautomated and manual measurements and assesses their reliability and agreement using data from repeated MR examinations., Methods: Seven healthy asymptomatic males underwent 1.5-T MR examinations of the lumbar spine involving sagittal T2-weighted fast spin-echo images obtained at baseline, pre-exercise, and postexercise conditions. Measures of the mean height and the mean sagittal area of lumbar IVDs (L1-L2 to L4-L5) were compared for two segmentation approaches: a conventional manual method (10-15 minutes to process one IVD) and a specifically developed semiautomated method (requiring only a few mouse clicks to process each subject)., Results: Both methods showed strong test-retest reproducibility evaluated on baseline and pre-exercise examinations with strong intraclass correlations for the semiautomated and manual methods for mean IVD height (intraclass correlation coefficient [ICC]=0.99, 0.98) and mean IVD area (ICC=0.98, 0.99), respectively. A bias (average deviation) of 0.38 mm (4.1%, 95% confidence interval 0.18-0.59 mm) was observed between the manual and semiautomated methods for the IVD height, whereas there was no statistically significant difference for the mean IVD area (0.1%±3.5%). The semiautomated and manual methods both detected significant exercise-induced changes in IVD height (0.20 and 0.28 mm) and mean IVD area (5.7 and 8.3 mm(2)), respectively., Conclusions: The presented semiautomated method provides an alternative to time- and expertise-intensive manual procedures for analysis of larger, cross-sectional, interventional, and longitudinal MR studies for morphometric analyses of lumbar IVDs., (Copyright © 2014 Elsevier Inc. All rights reserved.)

Heritability of brain anatomical connectivity has been studied with diffusion-weighted imaging (DWI) mainly by modeling each voxel's diffusion pattern as a tensor (e.g., to compute fractional anisotropy), but this method cannot accurately represent the many crossing connections present in the brain. We hypothesized that different brain networks (i.e., their component fibers) might have different heritability and we investigated brain connectivity using High Angular Resolution Diffusion Imaging (HARDI) in a cohort of twins comprising 328 subjects that included 70 pairs of monozygotic and 91 pairs of dizygotic twins. Water diffusion was modeled in each voxel with a Fiber Orientation Distribution (FOD) function to study heritability for multiple fiber orientations in each voxel. Precision was estimated in a test-retest experiment on a sub-cohort of 39 subjects. This was taken into account when computing heritability of FOD peaks using an ACE model on the monozygotic and dizygotic twins. Our results confirmed the overall heritability of the major white matter tracts but also identified differences in heritability between connectivity networks. Inter-hemispheric connections tended to be more heritable than intra-hemispheric and cortico-spinal connections. The highly heritable tracts were found to connect particular cortical regions, such as medial frontal cortices, postcentral, paracentral gyri, and the right hippocampus., (Crown Copyright © 2014. Published by Elsevier Inc. All rights reserved.)

Understanding structure-function relationships in the brain after stroke is reliant not only on the accurate anatomical delineation of the focal ischemic lesion, but also on previous infarcts, remote changes and the presence of white matter hyperintensities. The robust definition of primary stroke boundaries and secondary brain lesions will have significant impact on investigation of brain-behavior relationships and lesion volume correlations with clinical measures after stroke. Here we present an automated approach to identify chronic ischemic infarcts in addition to other white matter pathologies, that may be used to aid the development of post-stroke management strategies. Our approach uses Bayesian-Markov Random Field (MRF) classification to segment probable lesion volumes present on fluid attenuated inversion recovery (FLAIR) MRI. Thereafter, a random forest classification of the information from multimodal (T1-weighted, T2-weighted, FLAIR, and apparent diffusion coefficient (ADC)) MRI images and other context-aware features (within the probable lesion areas) was used to extract areas with high likelihood of being classified as lesions. The final segmentation of the lesion was obtained by thresholding the random forest probabilistic maps. The accuracy of the automated lesion delineation method was assessed in a total of 36 patients (24 male, 12 female, mean age: 64.57±14.23yrs) at 3months after stroke onset and compared with manually segmented lesion volumes by an expert. Accuracy assessment of the automated lesion identification method was performed using the commonly used evaluation metrics. The mean sensitivity of segmentation was measured to be 0.53±0.13 with a mean positive predictive value of 0.75±0.18. The mean lesion volume difference was observed to be 32.32%±21.643% with a high Pearson's correlation of r=0.76 (p<0.0001). The lesion overlap accuracy was measured in terms of Dice similarity coefficient with a mean of 0.60±0.12, while the contour accuracy was observed with a mean surface distance of 3.06mm±3.17mm. The results signify that our method was successful in identifying most of the lesion areas in FLAIR with a low false positive rate., (Copyright © 2014 Elsevier Inc. All rights reserved.)

Deformable models incorporating shape priors have proved to be a successful approach in segmenting anatomical regions and specific structures in medical images. This paper introduces weighted shape priors for deformable models in the context of 3D magnetic resonance (MR) image segmentation of the bony elements of the human hip joint. The fully automated approach allows the focusing of the shape model energy to a priori selected anatomical structures or regions of clinical interest by preferentially ordering the shape representation (or eigen-modes) within this type of model to the highly weighted areas. This focused shape model improves accuracy of the shape constraints in those regions compared to standard approaches. The proposed method achieved femoral head and acetabular bone segmentation mean absolute surface distance errors of 0.55±0.18mm and 0.75±0.20mm respectively in 35 3D unilateral MR datasets from 25 subjects acquired at 3T with different limited field of views for individual bony components of the hip joint., (Copyright © 2014 Elsevier B.V. All rights reserved.)

In the context of Alzheimer's disease, two challenging issues are (1) the characterization of local hippocampal shape changes specific to disease progression and (2) the identification of mild-cognitive impairment patients likely to convert. In the literature, (1) is usually solved first to detect areas potentially related to the disease. These areas are then considered as an input to solve (2). As an alternative to this sequential strategy, we investigate the use of a classification model using logistic regression to address both issues (1) and (2) simultaneously. The classification of the patients therefore does not require any a priori definition of the most representative hippocampal areas potentially related to the disease, as they are automatically detected. We first quantify deformations of patients' hippocampi between two time points using the large deformations by diffeomorphisms framework and transport these deformations to a common template. Since the deformations are expected to be spatially structured, we perform classification combining logistic loss and spatial regularization techniques, which have not been explored so far in this context, as far as we know. The main contribution of this paper is the comparison of regularization techniques enforcing the coefficient maps to be spatially smooth (Sobolev), piecewise constant (total variation) or sparse (fused LASSO) with standard regularization techniques which do not take into account the spatial structure (LASSO, ridge and ElasticNet). On a dataset of 103 patients out of ADNI, the techniques using spatial regularizations lead to the best classification rates. They also find coherent areas related to the disease progression.

Background: β-amyloid (Aβ) plaques in brain's grey matter (GM) are one of the pathological hallmarks of Alzheimer's disease (AD), and can be imaged in vivo using Positron Emission Tomography (PET) with (11)C or (18)F radiotracers. Estimating Aβ burden in cortical GM has been shown to improve diagnosis and monitoring of AD. However, lacking structural information in PET images requires such assessments to be performed with anatomical MRI scans, which may not be available at different clinical settings or being contraindicated for particular reasons. This study aimed to develop an MR-less Aβ imaging quantification method that requires only PET images for reliable Aβ burden estimations., Materials and Methods: The proposed method has been developed using a multi-atlas based approach on (11)C-PiB scans from 143 subjects (75 PiB+ and 68 PiB- subjects) in AIBL study. A subset of 20 subjects (PET and MRI) were used as atlases: 1) MRI images were co-registered with tissue segmentation; 2) 3D surface at the GM-WM interfacing was extracted and registered to a canonical space; 3) Mean PiB retention within GM was estimated and mapped to the surface. For other participants, each atlas PET image (and surface) was registered to the subject's PET image for PiB estimation within GM. The results are combined by subject-specific atlas selection and Bayesian fusion to generate estimated surface values., Results: All PiB+ subjects (N = 75) were highly correlated between the MR-dependent and the PET-only methods with Intraclass Correlation (ICC) of 0.94, and an average relative difference error of 13% (or 0.23 SUVR) per surface vertex. All PiB- subjects (N = 68) revealed visually akin patterns with a relative difference error of 16% (or 0.19 SUVR) per surface vertex., Conclusion: The demonstrated accuracy suggests that the proposed method could be an effective clinical inspection tool for Aβ imaging scans when MRI images are unavailable.

Accurate bone segmentation in the hip joint region from magnetic resonance (MR) images can provide quantitative data for examining pathoanatomical conditions such as femoroacetabular impingement through to varying stages of osteoarthritis to monitor bone and associated cartilage morphometry. We evaluate two state-of-the-art methods (multi-atlas and active shape model (ASM) approaches) on bilateral MR images for automatic 3D bone segmentation in the hip region (proximal femur and innominate bone). Bilateral MR images of the hip joints were acquired at 3T from 30 volunteers. Image sequences included water-excitation dual echo stead state (FOV 38.6 × 24.1 cm, matrix 576 × 360, thickness 0.61 mm) in all subjects and multi-echo data image combination (FOV 37.6 × 23.5 cm, matrix 576 × 360, thickness 0.70 mm) for a subset of eight subjects. Following manual segmentation of femoral (head-neck, proximal-shaft) and innominate (ilium+ischium+pubis) bone, automated bone segmentation proceeded via two approaches: (1) multi-atlas segmentation incorporating non-rigid registration and (2) an advanced ASM-based scheme. Mean inter- and intra-rater reliability Dice's similarity coefficients (DSC) for manual segmentation of femoral and innominate bone were (0.970, 0.963) and (0.971, 0.965). Compared with manual data, mean DSC values for femoral and innominate bone volumes using automated multi-atlas and ASM-based methods were (0.950, 0.922) and (0.946, 0.917), respectively. Both approaches delivered accurate (high DSC values) segmentation results; notably, ASM data were generated in substantially less computational time (12 min versus 10 h). Both automated algorithms provided accurate 3D bone volumetric descriptions for MR-based measures in the hip region. The highly computational efficient ASM-based approach is more likely suitable for future clinical applications such as extracting bone-cartilage interfaces for potential cartilage segmentation.

Support vector machines (SVM) are machine learning techniques that have been used for segmentation and classification of medical images, including segmentation of white matter hyper-intensities (WMH). Current approaches using SVM for WMH segmentation extract features from the brain and classify these followed by complex post-processing steps to remove false positives. The method presented in this paper combines advanced pre-processing, tissue-based feature selection and SVM classification to obtain efficient and accurate WMH segmentation. Features from 125 patients, generated from up to four MR modalities [T1-w, T2-w, proton-density and fluid attenuated inversion recovery(FLAIR)], differing neighbourhood sizes and the use of multi-scale features were compared. We found that although using all four modalities gave the best overall classification (average Dice scores of 0.54  ±  0.12, 0.72  ±  0.06 and 0.82  ±  0.06 respectively for small, moderate and severe lesion loads); this was not significantly different (p = 0.50) from using just T1-w and FLAIR sequences (Dice scores of 0.52  ±  0.13, 0.71  ±  0.08 and 0.81  ±  0.07). Furthermore, there was a negligible difference between using 5 × 5 × 5 and 3 × 3 × 3 features (p = 0.93). Finally, we show that careful consideration of features and pre-processing techniques not only saves storage space and computation time but also leads to more efficient classification, which outperforms the one based on all features with post-processing., (Copyright © 2013 John Wiley & Sons, Ltd.)

Importance: β-amyloid (Aβ) deposition is one of the hallmarks of Alzheimer disease. Aβ deposition accelerates gray matter atrophy at early stages of the disease even before objective cognitive impairment is manifested. Identification of at-risk individuals at the presymptomatic stage has become a major research interest because it will allow early therapeutic interventions before irreversible synaptic and neuronal loss occur. We aimed to further characterize the cross-sectional and longitudinal relationship between Aβ deposition, gray matter atrophy, and cognitive impairment., Objective: To investigate the topographical relationship of Aβ deposition, gray matter atrophy, and memory impairment in asymptomatic individuals with Alzheimer disease pathology as assessed by Pittsburgh compound B positron emission tomography (PiB-PET)., Design: Regional analysis was performed on the cortical surface to relate cortical thickness to PiB retention and episodic memory., Setting: The Australian Imaging, Biomarkers, and Lifestyle Study of Aging, Austin Hospital, Melbourne, Australia., Participants: Ninety-three healthy elderly control subjects (NCs) and 40 patients with Alzheimer disease from the Australian Imaging, Biomarkers, and Lifestyle Study of Aging cohort., Intervention: Participants underwent neuropsychological evaluation as well as magnetic resonance imaging and PiB-PET scans. Fifty-four NCs underwent repeated scans and neuropsychological evaluation 18 and 36 months later., Main Outcomes and Measures: Correlations between cortical thickness, PiB retention, and episodic memory. RESULTS There was a significant reduction in cortical thickness in the precuneus and hippocampus associated with episodic memory impairment in the NC PiB-positive (NC+) group when compared with the NC- group. Cortical thickness was also correlated negatively with neocortical PiB in the NC+ group. Longitudinal analysis showed a faster rate of gray matter (GM) atrophy in the temporal lobe and the hippocampi of the NC+ group. Over time, GM atrophy became more extensive in the NC+ group, especially in the temporal lobe., Conclusions and Relevance: In asymptomatic individuals, Aβ deposition is associated with GM atrophy and memory impairment. The earliest signs of GM atrophy were detected in the hippocampus and the posterior cingulate and precuneus regions, and with disease progression, atrophy became more extensive in the temporal lobes. These findings support the notion that Aβ deposition is not a benign process and that interventions with anti-Aβ therapy at these early stages have a higher chance to be effective.

Background: In recent years, imaging based, automated, non-invasive, and non-destructive high-throughput plant phenotyping platforms have become popular tools for plant biology, underpinning the field of plant phenomics. Such platforms acquire and record large amounts of raw data that must be accurately and robustly calibrated, reconstructed, and analysed, requiring the development of sophisticated image understanding and quantification algorithms. The raw data can be processed in different ways, and the past few years have seen the emergence of two main approaches: 2D image processing and 3D mesh processing algorithms. Direct image quantification methods (usually 2D) dominate the current literature due to comparative simplicity. However, 3D mesh analysis provides the tremendous potential to accurately estimate specific morphological features cross-sectionally and monitor them over-time., Result: In this paper, we present a novel 3D mesh based technique developed for temporal high-throughput plant phenomics and perform initial tests for the analysis of Gossypium hirsutum vegetative growth. Based on plant meshes previously reconstructed from multi-view images, the methodology involves several stages, including morphological mesh segmentation, phenotypic parameters estimation, and plant organs tracking over time. The initial study focuses on presenting and validating the accuracy of the methodology on dicotyledons such as cotton but we believe the approach will be more broadly applicable. This study involved applying our technique to a set of six Gossypium hirsutum (cotton) plants studied over four time-points. Manual measurements, performed for each plant at every time-point, were used to assess the accuracy of our pipeline and quantify the error on the morphological parameters estimated., Conclusion: By directly comparing our automated mesh based quantitative data with manual measurements of individual stem height, leaf width and leaf length, we obtained the mean absolute errors of 9.34%, 5.75%, 8.78%, and correlation coefficients 0.88, 0.96, and 0.95 respectively. The temporal matching of leaves was accurate in 95% of the cases and the average execution time required to analyse a plant over four time-points was 4.9 minutes. The mesh processing based methodology is thus considered suitable for quantitative 4D monitoring of plant phenotypic features.

Purpose: Prostate radiation therapy dose planning directly on magnetic resonance imaging (MRI) scans would reduce costs and uncertainties due to multimodality image registration. Adaptive planning using a combined MRI-linear accelerator approach will also require dose calculations to be performed using MRI data. The aim of this work was to develop an atlas-based method to map realistic electron densities to MRI scans for dose calculations and digitally reconstructed radiograph (DRR) generation., Methods and Materials: Whole-pelvis MRI and CT scan data were collected from 39 prostate patients. Scans from 2 patients showed significantly different anatomy from that of the remaining patient population, and these patients were excluded. A whole-pelvis MRI atlas was generated based on the manually delineated MRI scans. In addition, a conjugate electron-density atlas was generated from the coregistered computed tomography (CT)-MRI scans. Pseudo-CT scans for each patient were automatically generated by global and nonrigid registration of the MRI atlas to the patient MRI scan, followed by application of the same transformations to the electron-density atlas. Comparisons were made between organ segmentations by using the Dice similarity coefficient (DSC) and point dose calculations for 26 patients on planning CT and pseudo-CT scans., Results: The agreement between pseudo-CT and planning CT was quantified by differences in the point dose at isocenter and distance to agreement in corresponding voxels. Dose differences were found to be less than 2%. Chi-squared values indicated that the planning CT and pseudo-CT dose distributions were equivalent. No significant differences (p > 0.9) were found between CT and pseudo-CT Hounsfield units for organs of interest. Mean ± standard deviation DSC scores for the atlas-based segmentation of the pelvic bones were 0.79 ± 0.12, 0.70 ± 0.14 for the prostate, 0.64 ± 0.16 for the bladder, and 0.63 ± 0.16 for the rectum., Conclusions: The electron-density atlas method provides the ability to automatically define organs and map realistic electron densities to MRI scans for radiotherapy dose planning and DRR generation. This method provides the necessary tools for MRI-alone treatment planning and adaptive MRI-based prostate radiation therapy., (Crown Copyright © 2012. Published by Elsevier Inc. All rights reserved.)

Magnetic resonance (MR) provides a non-invasive way to investigate changes in the brain resulting from aging or neurodegenerative disorders such as Alzheimer's disease (AD). Performing accurate analysis for population studies is challenging because of the interindividual anatomical variability. A large set of tools is found to perform studies of brain anatomy and population analysis (FreeSurfer, SPM, FSL). In this paper we present a newly developed surface-based processing pipeline (MILXCTE) that allows accurate vertex-wise statistical comparisons of brain modifications, such as cortical thickness (CTE). The brain is first segmented into the three main tissues: white matter, gray matter and cerebrospinal fluid, after CTE is computed, a topology corrected mesh is generated. Partial inflation and non-rigid registration of cortical surfaces to a common space using shape context are then performed. Each of the steps was firstly validated using MR images from the OASIS database. We then applied the pipeline to a sample of individuals randomly selected from the AIBL study on AD and compared with FreeSurfer. For a population of 50 individuals we found correlation of cortical thickness in all the regions of the brain (average r=0.62 left and r=0.64 right hemispheres). We finally computed changes in atrophy in 32 AD patients and 81 healthy elderly individuals. Significant differences were found in regions known to be affected in AD. We demonstrated the validity of the method for use in clinical studies which provides an alternative to well established techniques to compare different imaging biomarkers for the study of neurodegenerative diseases., (Copyright © 2012 Elsevier B.V. All rights reserved.)

Due to physical limitations inherent in magnetic resonance imaging scanners, three dimensional volumetric scans are often acquired with anisotropic voxel resolution. We investigate several interpolation approaches to reduce the anisotropy and present a novel approach - constrained reverse diffusion for thick slice interpolation. This technique was compared to common methods: linear and cubic B-Spline interpolation and a technique based on non-rigid registration of neighboring slices. The methods were evaluated on artificial MR phantoms and real MR scans of human brain. The constrained reverse diffusion approach delivered promising results and provides an alternative for thick slice interpolation, especially for higher anisotropy factors., (Copyright © 2011 Elsevier Ltd. All rights reserved.)

The hippocampus is affected at an early stage in the development of Alzheimer's disease (AD). With the use of structural magnetic resonance (MR) imaging, we can investigate the effect of AD on the morphology of the hippocampus. The hippocampal shape variations among a population can be usually described using statistical shape models (SSMs). Conventional SSMs model the modes of variations among the population via principal component analysis (PCA). Although these modes are representative of variations within the training data, they are not necessarily discriminative on labeled data or relevant to the differences between the subpopulations. We use the shape descriptors from SSM as features to classify AD from normal control (NC) cases. In this study, a Hotelling's T2 test is performed to select a subset of landmarks which are used in PCA. The resulting variation modes are used as predictors of AD from NC. The discrimination ability of these predictors is evaluated in terms of their classification performances with bagged support vector machines (SVMs). Restricting the model to landmarks with better separation between AD and NC increases the discrimination power of SSM. The predictors extracted on the subregions also showed stronger correlation with the memory-related measurements such as Logical Memory, Auditory Verbal Learning Test (AVLT) and the memory subscores of Alzheimer Disease Assessment Scale (ADAS)., (Crown Copyright © 2011. Published by Elsevier Inc. All rights reserved.)

For clinical evaluation, assessing amyloid deposition with PiB-PET is desirable without requiring MR acquisition and associated fusion/segmentation techniques. A useful clinical tool is to estimate PiB-PET against the brain surface, which is however challenging using PET alone because of the lack of structural information. We propose a method to generate such estimate, where multiple atlases are selected and combined with local weights in a Bayesian framework. Qualitative and quantitative comparison with and without MRI are presented. Using PET only, the average error on the brain surface was around 13% compared to MRI-dependant method.

Registration of diffusion-weighted images is an important step in comparing white matter fibre bundles across subjects, or in the same subject at different time points. Using diffusion-weighted imaging, Spherical Deconvolution enables multiple fibre populations within a voxel to be resolved by computing the fibre orientation distribution (FOD). In this paper, we present a novel method that employs FODs for the registration of diffusion-weighted images. Registration was performed by optimising a symmetric diffeomorphic non-linear transformation model, using image metrics based on the mean squared difference, and cross-correlation of the FOD spherical harmonic coefficients. The proposed method was validated by recovering known displacement fields using FODs represented with maximum harmonic degrees (l(max)) of 2, 4 and 6. Results demonstrate a benefit in using FODs at l(max)=4 compared to l(max)=2. However, a decrease in registration accuracy was observed when l(max)=6 was used; this was likely caused by noise in higher harmonic degrees. We compared our proposed method to fractional anisotropy driven registration using an identical code base and parameters. FOD registration was observed to perform significantly better than FA in all experiments. The cross-correlation metric performed significantly better than the mean squared difference. Finally, we demonstrated the utility of this method by computing an unbiased group average FOD template that was used for probabilistic fibre tractography. This work suggests that using crossing fibre information aids in the alignment of white matter and could therefore benefit several methods for investigating population differences in white matter, including voxel based analysis, tensor based morphometry, atlas based segmentation and labelling, and group average fibre tractography., (Crown Copyright © 2010. Published by Elsevier Inc. All rights reserved.)

Purpose: To compare automated segmentation of the quadratus lumborum (QL) based on statistical shape modeling (SSM) with conventional manual processing of magnetic resonance (MR) images for segmentation of this paraspinal muscle., Materials and Methods: The automated SSM scheme for QL segmentation was developed using an MR database of 7 mm axial images of the lumbar region from 20 subjects (cricket fast bowlers and athletic controls). Specifically, a hierarchical 3D-SSM scheme for segmentation of the QL, and surrounding psoas major (PS) and erector spinae+multifidus (ES+MT) musculature, was implemented after image preprocessing (bias field correction, partial volume interpolation) followed by image registration procedures to develop average and probabilistic MR atlases for initializing and constraining the SSM segmentation of the QL. The automated and manual QL segmentations were compared using spatial overlap and average surface distance metrics., Results: The spatial overlap between the automated SSM and manual segmentations had a median Dice similarity metric of 0.87 (mean = 0.86, SD = 0.08) and mean average surface distance of 1.26 mm (SD = 0.61) and 1.32 mm (SD = 0.60) for the right and left QL muscles, respectively., Conclusion: The current SSM scheme represents a promising approach for future automated morphometric analyses of the QL and other paraspinal muscles from MR images., (Copyright © 2011 Wiley-Liss, Inc.)

Dose planning for prostate radiation therapy is performed using computed tomography (CT) scans that provide the electron density information needed for individual patients' radiation dose calculations. For visualising the prostate and determining the target volume for radiation treatment, magnetic resonance imaging (MRI) gives vastly superior soft-tissue contrast. However, currently, MRI scans cannot be used for dose planning, as they do not provide the electron density information. We aimed to develop an alternative and efficient MRI-only image-based workflow, enabling both organ delineation and dose planning to be performed using MRI, with "pseudo-CT scans" generated from MRI scans supplying the information for dose planning. The feasibility of implementing MRI-based prostate radiation therapy planning is being investigated through collaboration between the clinical and medical physics group at the Calvary Mater Newcastle Hospital/University of Newcastle and the biomedical imaging processing group at the CSIRO (Commonwealth Scientific and Industrial Research Organisation) Australian e-Health Research Centre. Results comparing Hounsfield units calculated from CT scans and from MRI-based pseudo-CT scans for 39 patients showed very similar average values for the prostate, bladder, bones and rectum, confirming that pseudo-CT scans can replace CT scans for accurate radiation dose calculations. MRI-based radiotherapy planning can also be used for tumours in other locations, such as head and neck, and breast cancers.

Longer life expectancies lead to increases in the prevalence of age-associated illnesses. The number of Australians with dementia is predicted to rise, from 234,000 in 2009 to over 1 million by 2050, as a result of the increased prevalence of Alzheimer's disease (AD), the leading cause of dementia in the elderly. Early diagnosis of AD will become more important as disease-modifying therapies emerge within the next decade. Advances in molecular neuroimaging with amyloid-β-specific radioligands for positron emission tomography, aided by magnetic resonance imaging techniques, allow detection of AD years before symptoms of dementia develop. Longitudinal prospective studies, such as the Australian Imaging Biomarkers and Lifestyle (AIBL) study of ageing, will determine the sensitivity and specificity of these analysis techniques for diagnosing AD and predicting cognitive decline.

The Australian Imaging, Biomarkers and Lifestyle (AIBL) study of aging, a participant of the worldwide Alzheimer's Disease Neuroimaging Initiative (ADNI), performed (11)C-Pittsburgh Compound B (PiB) scans in 177 healthy controls (HC), 57 mild cognitive impairment (MCI) subjects, and 53 mild Alzheimer's disease (AD) patients. High PiB binding was present in 33% of HC (49% in ApoE-epsilon4 carriers vs 21% in noncarriers) and increased with age, most strongly in epsilon4 carriers. 18% of HC aged 60-69 had high PiB binding rising to 65% in those over 80 years. Subjective memory complaint was only associated with elevated PiB binding in epsilon4 carriers. There was no correlation with cognition in HC or MCI. PiB binding in AD was unrelated to age, hippocampal volume or memory. Beta-amyloid (Abeta) deposition seems almost inevitable with advanced age, amyloid burden is similar at all ages in AD, and secondary factors or downstream events appear to play a more direct role than total beta amyloid burden in hippocampal atrophy and cognitive decline., (Crown Copyright 2010. Published by Elsevier Inc. All rights reserved.)

In magnetic resonance imaging (MRI), accuracy and precision with which brain structures may be quantified are frequently affected by the partial volume (PV) effect. PV is due to the limited spatial resolution of MRI compared to the size of anatomical structures. Accurate classification of mixed voxels and correct estimation of the proportion of each pure tissue (fractional content) may help to increase the precision of cortical thickness estimation in regions where this measure is particularly difficult, such as deep sulci. The contribution of this work is twofold: on the one hand, we propose a new method to label voxels and compute tissue fractional content, integrating a mechanism for detecting sulci with topology preserving operators. On the other hand, we improve the computation of the fractional content of mixed voxels using local estimation of pure tissue intensity means. Accuracy and precision were assessed using simulated and real MR data and comparison with other existing approaches demonstrated the benefits of our method. Significant improvements in gray matter (GM) classification and cortical thickness estimation were brought by the topology correction. The fractional content root mean squared error diminished by 6.3% (p<0.01) on simulated data. The reproducibility error decreased by 8.8% (p<0.001) and the Jaccard similarity measure increased by 3.5% on real data. Furthermore, compared with manually guided expert segmentations, the similarity measure was improved by 12.0% (p<0.001). Thickness estimation with the proposed method showed a higher reproducibility compared with the measure performed after partial volume classification using other methods., (Copyright (c) 2010 Elsevier B.V. All rights reserved.)

Objective: To investigate whether global and regional beta-amyloid (Abeta) burden as measured with 11C Pittsburgh compound B (PIB) PET is associated with hippocampal atrophy characterized using MRI in healthy controls and patients with amnestic mild cognitive impairment (aMCI) or Alzheimer disease (AD)., Methods: Ninety-two elderly healthy controls, 32 subjects with aMCI, and 35 patients with AD were imaged using 11C-PIB PET and MRI. Hippocampal volume was measured and PIB standardized uptake value ratio was extracted after partial volume correction within 41 regions of interest. Global, regional, and voxel-based correlations between PIB and hippocampal volume were computed for each group., Results: In healthy control participants with elevated neocortex PIB retention, significant correlation was found between PIB retention in the inferior temporal region and hippocampal volume using both region-based and voxel-based approaches. No correlation was found in any other group., Conclusions: The strong correlation between hippocampal atrophy and beta-amyloid (Abeta) burden in the Pittsburgh compound B-positive healthy control group suggests that Abeta deposition in the inferior temporal neocortex is related to hippocampal synaptic and neuronal degeneration.

Identifying mild cognitive impairment (MCI) subjects who will convert to clinical Alzheimer's disease (AD) is important for therapeutic decisions, patient counselling and clinical trials. Hippocampal volume and rate of atrophy predict clinical decline at the MCI stage and progression to AD. In this paper, we create p-maps from the differences in the shape of the hippocampus between 60 normal controls and 60 AD subjects using statistical shape models, and generate different regions of interest (ROI) by thresholding the p-maps at different significance levels. We demonstrate increased statistical power to classify 86 MCI converters and 128 MCI stable subjects using the hippocampal atrophy rates calculated by the boundary shift integral within these ROIs.

In this paper, we present a segmentation scheme that automatically and accurately segments all the cartilages from magnetic resonance (MR) images of nonpathological knees. Our scheme involves the automatic segmentation of the bones using a three-dimensional active shape model, the extraction of the expected bone-cartilage interface (BCI), and cartilage segmentation from the BCI using a deformable model that utilizes localization, patient specific tissue estimation and a model of the thickness variation. The accuracy of this scheme was experimentally validated using leave one out experiments on a database of fat suppressed spoiled gradient recall MR images. The scheme was compared to three state of the art approaches, tissue classification, a modified semi-automatic watershed algorithm and nonrigid registration (B-spline based free form deformation). Our scheme obtained an average Dice similarity coefficient (DSC) of (0.83, 0.83, 0.85) for the (patellar, tibial, femoral) cartilages, while (0.82, 0.81, 0.86) was obtained with a tissue classifier and (0.73, 0.79, 0.76) was obtained with nonrigid registration. The average DSC obtained for all the cartilages using a semi-automatic watershed algorithm (0.90) was slightly higher than our approach (0.89), however unlike this approach we segment each cartilage as a separate object. The effectiveness of our approach for quantitative analysis was evaluated using volume and thickness measures with a median volume difference error of (5.92, 4.65, 5.69) and absolute Laplacian thickness difference of (0.13, 0.24, 0.12) mm.

Accurate cortical thickness estimation is important for the study of many neurodegenerative diseases. Many approaches have been previously proposed, which can be broadly categorised as mesh-based and voxel-based. While the mesh-based approaches can potentially achieve subvoxel resolution, they usually lack the computational efficiency needed for clinical applications and large database studies. In contrast, voxel-based approaches, are computationally efficient, but lack accuracy. The aim of this paper is to propose a novel voxel-based method based upon the Laplacian definition of thickness that is both accurate and computationally efficient. A framework was developed to estimate and integrate the partial volume information within the thickness estimation process. Firstly, in a Lagrangian step, the boundaries are initialized using the partial volume information. Subsequently, in an Eulerian step, a pair of partial differential equations are solved on the remaining voxels to finally compute the thickness. Using partial volume information significantly improved the accuracy of the thickness estimation on synthetic phantoms, and improved reproducibility on real data. Significant differences in the hippocampus and temporal lobe between healthy controls (NC), mild cognitive impaired (MCI) and Alzheimer's disease (AD) patients were found on clinical data from the ADNI database. We compared our method in terms of precision, computational speed and statistical power against the Eulerian approach. With a slight increase in computation time, accuracy and precision were greatly improved. Power analysis demonstrated the ability of our method to yield statistically significant results when comparing AD and NC. Overall, with our method the number of samples is reduced by 25% to find significant differences between the two groups.

Beta-amyloid (Abeta) deposition is one of the neuropathological hallmarks of Alzheimer's disease (AD), Abeta burden can be quantified using (11)C PiB PET. Neuropathological studies have shown that the initial plaques are located in the temporal and orbitofrontal cortices, extending later to the cingulate, frontal and parietal cortices (Braak and Braak, 1997). Previous studies have shown an overlap in (11)C PiB PET retention between AD, mild cognitive impairment (MCI) patients and normal elderly control (NC) participants. It has also been shown that there is a relationship between Abeta deposition and memory impairment in MCI patients. In this paper we explored the variability seen in 15 AD, 15 MCI and 18 NC by modeling the voxel data from spatially and uptake normalized PiB images using principal component analysis. The first two principal components accounted for 80% of the variability seen in the data, providing a clear separation between AD and NC, and allowing subsequent classification. The MCI cases were distributed along an apparent axis between the AD and NC group, closely aligned with the first principal component axis. The NC cases that were PiB(+) formed a distinct cluster that was between, but separated from the AD and PiB(-) NC clusters. The PiB(+) MCI were found to cluster with the AD cases, and exhibited a similar deposition pattern. The primary principal component score was found to correlate with episodic memory scores and mini mental status examination and it was observed that by varying the first principal component, a change in amyloid deposition could be derived that is similar to the expected progression of amyloid deposition observed from post mortem studies.

Rationale and Objectives: Radiotracers such as (11)C-PiB have enabled the in vivo imaging of amyloid-beta plaques in the brain, one of the histopathologic hallmarks of Alzheimer's disease (AD). Standardized uptake value ratio (SUVR) has become the most common normalization for (11)C-PiB as it does not require dynamic scans or blood sampling. Normalization is performed by computing the ratio of (11)C-PiB retention in the whole brain to that in cerebellar gray matter. However, SUVR is still conducted manually and is time consuming. An automated normalization algorithm is proposed., Materials and Methods: Sixty participants from the Australian Imaging Biomarkers and Lifestyle (AIBL) study were used to test the developed algorithm and compare it against manual SUVR. The cohort consisted of participants likely to have AD (n = 20), those with mild cognitive impairment (MCI; n = 20), and normal controls (NC; n = 20). The participants underwent (11)C-PiB PET scans. A subset (n = 15) also underwent magnetic resonance imaging scans. (11)C-PET scans were segmented using an expectation maximization approach with inhomogeneity correction using three-dimensional cubic B-Splines. A cerebellar region was propagated and constrained by segmentation. Comparisons were made between manual and automated SUVR using regional analysis. Receiver-operating characteristic curves were computed for the task of AD-NC classification. Positron emission tomographic segmentations were also compared to co-registered magnetic resonance images of the same patient., Results: Significant differences in regional means were observed between manual and automated SUVR. However, these changes were highly correlated (r > 0.8 for most regions). Significant differences (P < .05) in regional variances were also observed for the AD and NC subgroups. Area under the curve was 0.84 and 0.89 for manual and automated SUVR, respectively., Conclusions: The automated normalization technique results in less within-group variance and better discrimination between AD and NC participants.

This study presents a novel method for the automatic segmentation of the quadratus lumborum (QL) muscle from axial magnetic resonance (MR) images using a hybrid scheme incorporating the use of non-rigid registration with probabilistic atlases (PAs) and geodesic active contours (GACs). The scheme was evaluated on an MR database of 7mm axial images of the lumbar spine from 20 subjects (fast bowlers and athletic controls). This scheme involved several steps, including (i) image pre-processing, (ii) generation of PAs for the QL, psoas (PS) and erector spinae+multifidus (ES+MT) muscles and (iii) segmentation, using 3D GACs initialized and constrained by the propagation of the PAs using non-rigid registration. Pre-processing of the images involved bias field correction based on local entropy minimization with a bicubic spline model and a reverse diffusion interpolation algorithm to increase the slice resolution to 0.98 x 0.98 x 1.75mm. The processed images were then registered (affine and non-rigid) and used to generate an average atlas. The PAs for the QL, PS and ES+MT were then generated by propagation of manual segmentations. These atlases were further analysed with specialised filtering to constrain the QL segmentation from adjacent non-muscle tissues (kidney, fat). This information was then used in 3D GACs to obtain the final segmentation of the QL. The automatic segmentation results were compared with the manual segmentations using the Dice similarity metric (DSC), with a median DSC for the right and left QL muscles of 0.78 (mean = 0.77, sd=0.07) and 0.75 (mean =0.74, sd=0.07), respectively.

Accurate cortical thickness estimation in-vivo is important for the study of many neurodegenerative diseases. When using magnetic resonance images (MRI), accuracy may be hampered by artifacts such as partial volume (PV) as the cortex spans only a few voxels. In zones of opposed sulcal banks (tight sulci) the measurement can be even more difficult. The aim of this work is to propose a voxel-based cortical thickness estimation method from MR by integrating a mechanism for correcting sulci delineation after an improved partial volume classification. First, an efficient and accurate framework was developed to enhance partial volume classification with structural information. Then, the correction of sulci delineation is performed after a homotopic thinning of a cost function image. Integrated to our voxel-based cortical thickness estimation pipeline, the overall method showed a better estimate of thickness and a high reproducibility on real data (R2 > 0.9). A quantitative analysis on clinical data from an Alzheimer's disease study showed significant differences between normal controls and Alzheimer's disease patients.

Beta-amyloid (Abeta) plaques are one of the neuropathological hallmarks of Alzheimer's disease (AD) and can be quantified using the marker 11C PiB. As l1C PiB PET images have limited anatomical information, an Magnetic Resonance Image (MRI) is usually acquired to perform the spatial normalization needed for population analysis. We designed and evaluated a high dimensional spatial normalization approach that only uses the 11C PiB PET image. The non-rigid registration (NRR) is based on free form deformation (FFD) modelled using B-splines. To compensate for the limited anatomical information, the FFD is constrained to an allowable transform space using a model trained from MR registrations. Abeta deposition is dependent on disease staging, so a spatially normalized 11C PiB PET appearance model selects and refines the atlas. The approach was compared with MR NRR using data from healthy elderly, mild cognitive impaired and Alzheimer disease participants. Using segmentation propagation, an average Dice similarity coefficient of 0.64 and 0.73 was obtained for white and gray matter. The R-squared correlation between the uptake obtained in the frontal, parietal, occipital and temporal was 0.789, 0.843, 0.871 and 0.964. These are very promising results, considering the low resolution of 11C PiB PET images.

Rationale and Objectives: The segmentation of textured anatomy from magnetic resonance images (MRI) is a difficult problem. We present an approach that uses features extracted from the magnitude and phase of the MRI signal to segment the bones in the knee. Moreover, we show that by incorporating shape information, more accurate and anatomically valid segmentations are obtained., Materials and Methods: Eighteen volunteers were scanned in a whole-body 3T clinical scanner using a transmit-receive quadrature extremity coil. A gradient-echo sequence was used to acquire three-dimensional (3D) volumes of raw complex image data consisting of phase and magnitude information. These images were manually segmented and features were extracted using a bank of Gabor filters. The extracted features were then used to train a support vector machine (SVM) classifier. Each image was then automatically segmented using both the SVM classifier and a 3D active shape model (ASM) driven by the classifier., Results: The use of phase and magnitude information from both echoes obtained the most accurate classifier results with an average dice similarity coefficient of 0.907. The use of 3D ASMs further improved the robustness, accuracy and anatomic validity of the segmentations with an overall DSC of 0.922 and an average point to surface error along the bone-cartilage interface of 0.73 mm., Conclusions: Our results demonstrate that the incorporation of phase and multiple echoes improve the results obtained by the classifier. Moreover, we show that 3D ASMs provide a robust and accurate way of using the classifier to obtain anatomically valid segmentation results.

Magnetic resonance (MR) imaging is a widely available and well accepted non invasive imaging technique. Development of automatic and semi-automatic techniques to analyse MR images has been the focus of much research and numerous publications. However, most of this research only uses the magnitude of the acquired complex MR signal, discarding the phase information. In MR, the phase relates to the magnetic properties of tissues, information which is not found in the magnitude signal. As a result, phase is a complement to the magnitude signal and can improve the segmentation and analysis of MR images. In this paper, we consider the automatic classification of textured tissues in 3D MRI. Specifically, we include features extracted from the phase of the MR signal to improve texture discrimination in the bone segmentation. Our approach does not require phase unwrapping, with the MR signal processed in its complex form. The extra information extracted from the phase provides better segmentation, compared to only using magnitude features. The segmentation approach is integrated within a novel multiscale scheme, designed to improve the speed of pixel based classification algorithms, such as support vector machines. An order of magnitude increase is obtained, by reducing the number of pixels that need to be classified.

The accurate segmentation of the articular cartilages from magnetic resonance (MR) images of the knee is important for clinical studies and drug trials into conditions like osteoarthritis. Currently, segmentations are obtained using time-consuming manual or semi-automatic algorithms which have high inter- and intra-observer variabilities. This paper presents an important step towards obtaining automatic and accurate segmentations of the cartilages, namely an approach to automatically segment the bones and extract the bone-cartilage interfaces (BCI) in the knee. The segmentation is performed using three-dimensional active shape models, which are initialized using an affine registration to an atlas. The BCI are then extracted using image information and prior knowledge about the likelihood of each point belonging to the interface. The accuracy and robustness of the approach was experimentally validated using an MR database of fat suppressed spoiled gradient recall images. The (femur, tibia, patella) bone segmentation had a median Dice similarity coefficient of (0.96, 0.96, 0.89) and an average point-to-surface error of 0.16 mm on the BCI. The extracted BCI had a median surface overlap of 0.94 with the real interface, demonstrating its usefulness for subsequent cartilage segmentation or quantitative analysis.

To perform cartilage quantitative analysis requires the accurate segmentation of each individual cartilage. In this paper we present a model based scheme that can automatically and accurately segment each individual cartilage in healthy knees from a clinical MR sequence (fat suppressed spoiled gradient recall). This scheme consists of three stages; the automatic segmentation of the bones, the extraction of the bone-cartilage interfaces (BCI) and segmentation of the cartilages. The bone segmentation is performed using three-dimensional active shape models. The BCI is extracted using image information and prior knowledge about the likelihood of each point belonging to the interface. A cartilage thickness model then provides constraints and regularizes the cartilage segmentation performed from the BCI. The accuracy and robustness of the approach was experimentally validated, with (patellar, tibial and femoral) cartilage segmentations having a median DSC of (0.870, 0.855, 0.870), performing significantly better than non-rigid registration (0.787, 0.814, 0.795). The total cartilage segmentation had an average DSC of (0.891), close to the (0.896) obtained using a semi-automatic watershed algorithm. The error in quantitative volume and thickness measures was (8.29, 4.94, 5.56)% and (0.19, 0.33, 0.10) mm respectively.

This paper considers the problem of automatic classification of textured tissues in 3D MRI. More specifically, it aims at validating the use of features extracted from the phase of the MR signal to improve texture discrimination in bone segmentation. This extra information provides better segmentation, compared to using magnitude only features. We also present a novel multiscale scheme to improve the speed of pixel based classification algorithm, such as support vector machines. This algorithm dramatically increases the speed of the segmentation process by an order of magnitude through a reduction of the number of pixels that needs to be classified in the image.

This paper considers the problem of tissue classification in 3D MRI. More specifically, a new set of texture features, based on phase information, is used to perform the segmentation of the bones of the knee. The phase information provides a very good discrimination between the bone and the surrounding tissues, but is usually not used due to phase unwrapping problems. We present a method to extract textural information from the phase that does not require phase unwrapping. The textural information extracted from the magnitude and the phase can be combined to perform tissue classification, and used to initialise an active shape model, leading to a more precise segmentation.