Brain and lesion segmentation in multiple sclerosis using fully convolutional neural networks: A large-scale study.

OBJECTIVE: To investigate the performance of deep learning (DL) based on fully convolutional neural network (FCNN) in segmenting brain tissues in a large cohort of multiple sclerosis (MS) patients. METHODS: We developed a FCNN model to segment brain tissues, including T2-hyperintense MS lesions. The training, validation, and testing of FCNN were based on ~1000 magnetic resonance imaging (MRI) datasets acquired on relapsing-remitting MS patients, as a part of a phase 3 randomized clinical trial. Multimodal MRI data (dual-echo, FLAIR, and T1-weighted images) served as input to the network. Expert validated segmentation was used as the target for training the FCNN. We cross-validated our results using the leave-one-center-out approach. RESULTS: We observed a high average (95% confidence limits) Dice similarity coefficient for all the segmented tissues: 0.95 (0.92-0.98) for white matter, 0.96 (0.93-0.98) for gray matter, 0.99 (0.98-0.99) for cerebrospinal fluid, and 0.82 (0.63-1.0) for T2 lesions. High correlations between the DL segmented tissue volumes and ground truth were observed (R2 > 0.92 for all tissues). The cross validation showed consistent results across the centers for all tissues. CONCLUSION: The results from this large-scale study suggest that deep FCNN can automatically segment MS brain tissues, including lesions, with high accuracy.

Effect of in-painting on cortical thickness measurements in multiple sclerosis: A large cohort study.

A comprehensive analysis of the effect of lesion in-painting on the estimation of cortical thickness using magnetic resonance imaging was performed on a large cohort of 918 relapsing-remitting multiple sclerosis patients who participated in a phase III multicenter clinical trial. An automatic lesion in-painting algorithm was developed and implemented. Cortical thickness was measured using the FreeSurfer pipeline with and without in-painting. The effect of in-painting was evaluated using FreeSurfer's paired analysis pipeline. Multivariate regression analysis was also performed with field strength and lesion load as additional factors. Overall, the estimated cortical thickness was different with in-painting than without. The effect of in-painting was observed to be region dependent, more significant in the left hemisphere compared to the right, was more prominent at 1.5 T relative to 3 T, and was greater at higher lesion volumes. Our results show that even for data acquired at 1.5 T in patients with high lesion load, the mean cortical thickness difference with and without in-painting is ∼2%. Based on these results, it appears that in-painting has only a small effect on the estimated regional and global cortical thickness. Hum Brain Mapp 36:3749-3760, 2015. © 2015 Wiley Periodicals, Inc.

Hypoperfusion and T1-hypointense lesions in white matter in multiple sclerosis.

BACKGROUND: Longitudinal magnetic resonance imaging (MRI) studies show that a fraction of the multiple sclerosis (MS) T2-lesions contain T1-hypointense components that may persist to represent severe, irreversible tissue damage. It is not known why certain lesions convert to persistent T1-hypointense lesions. OBJECTIVE: We hypothesized that the T1-hypointense lesions disproportionately distribute in the more hypoperfused areas of the brain. Here we investigated the association between hypoperfusion and T1-hypointense lesion distributions. METHODS: MRI and cerebral blood flow (CBF) data were acquired on 45 multiple sclerosis (MS) patients and 20 healthy controls. CBF maps were generated using pseudo-continuous arterial spin labeling technique. The lesion probability distribution maps were superimposed on the CBF maps. RESULTS: Two distinct CBF clusters were observed in the white matter (WM) both in healthy controls and MS patients. An overall reduction in CBF was observed in MS patients compared to healthy controls. The majority of the T1-hypointense lesions were concentrated almost exclusively in the WM regions with lower CBF. The T2-hyperintense lesions were more generally distributed in both higher and lower perfused WM. CONCLUSION: This study suggests an association between hypoperfusion and T1-hypointense lesions.

Magnetic resonance imaging outcomes from a phase III trial of teriflunomide.

OBJECTIVE: The purpose of this study was to determine the effects of oral teriflunomide on multiple sclerosis (MS) pathology inferred by magnetic resonance imaging (MRI). METHODS: Patients (n=1088) with relapsing MS were randomized to once-daily teriflunomide 7 mg or 14 mg, or placebo, for 108 weeks. MRI was recorded at baseline, 24, 48, 72 and 108 weeks. Annualized relapse rate and confirmed progression of disability (sustained ≥12 weeks) were the primary and key secondary outcomes. The principal MRI outcome was change in total lesion volume. RESULTS: After 108 weeks, increase in total lesion volume was 67.4% (p=0.0003) and 39.4% (p=0.0317) lower in the 14 and 7 mg dose groups versus placebo. Other measures favoring teriflunomide were accumulated enhanced lesions, combined unique activity, T2-hyperintense and T1-hypointense component lesion volumes, white matter volume, and a composite MRI score; all were significant for teriflunomide 14 mg and most significant for 7 mg versus placebo. CONCLUSIONS: Teriflunomide provided benefits on brain MRI activity across multiple measures, with a dose effect evident on several markers. These effects were also consistent across selected subgroups of the study population. These findings complement clinical data showing significant teriflunomide-related reductions in relapse rate and disease progression, and demonstrate containment of MRI-defined disease progression.

Automated brain extraction from T2-weighted magnetic resonance images.

PURPOSE: To develop and implement an automated and robust technique to extract brain from T2-weighted images. MATERIALS AND METHODS: Magnetic resonance imaging (MRI) was performed on 75 adult volunteers to acquire dual fast spin echo (FSE) images with fat-saturation technique on a 3T Philips scanner. Histogram-derived thresholds were derived directly from the original images followed by the application of regional labeling, regional connectivity, and mathematical morphological operations to extract brain from axial late-echo FSE (T2-weighted) images. The proposed technique was evaluated subjectively by an expert and quantitatively using Bland-Altman plot and Jaccard and Dice similarity measures. RESULTS: Excellent agreement between the extracted brain volumes with the proposed technique and manual stripping by an expert was observed based on Bland-Altman plot and also as assessed by high similarity indices (Jaccard: 0.9825 ± 0.0045; Dice: 0.9912 ± 0.0023). CONCLUSION: Brain extraction using the proposed automated methodology is robust and the results are reproducible.

Intracortical lesions by 3T magnetic resonance imaging and correlation with cognitive impairment in multiple sclerosis.

BACKGROUND: Accurate classification of multiple sclerosis (MS) lesions in the brain cortex may be important in understanding their impact on cognitive impairment (CI). Improved accuracy in identification/classification of cortical lesions was demonstrated in a study combining two magnetic resonance imaging (MRI) sequences: double inversion recovery (DIR) and T1-weighted phase-sensitive inversion recovery (PSIR). OBJECTIVE: To evaluate the role of intracortical lesions (IC) in MS-related CI and compare it with the role of mixed (MX), juxtacortical (JX), the sum of IC + MX and with total lesions as detected on DIR/PSIR images. Correlations between CI and brain atrophy, disease severity and disease duration were also sought. METHODS: A total of 39 patients underwent extensive neuropsychological testing and were classified into normal and impaired groups. Images were obtained on a 3T scanner and cortical lesions were assessed blind to the cognitive status of the subjects. RESULTS: Some 238 cortical lesions were identified (130 IC, 108 MX) in 82% of the patients; 39 JX lesions were also identified. Correlations between CI and MX lesions alone (p = 0.010) and with the sum of IC + MX lesions (p = 0.030) were found. A correlation between severity of CI and Expanded Disability Status Scale was also seen (p = 0.009). CONCLUSION: Cortical lesions play an important role in CI. However, our results suggest that lesions that remain contained within the cortical ribbon do not play a more important role than ones extending into the adjacent white matter; furthermore, the size of the cortical lesion, and not the tissue-specific location, may better explain their correlation with CI.

Generalized fuzzy clustering for segmentation of multi-spectral magnetic resonance images.

An integrated approach for multi-spectral segmentation of MR images is presented. This method is based on the fuzzy c-means (FCM) and includes bias field correction and contextual constraints over spatial intensity distribution and accounts for the non-spherical cluster's shape in the feature space. The bias field is modeled as a linear combination of smooth polynomial basis functions for fast computation in the clustering iterations. Regularization terms for the neighborhood continuity of intensity are added into the FCM cost functions. To reduce the computational complexity, the contextual regularizations are separated from the clustering iterations. Since the feature space is not isotropic, distance measure adopted in Gustafson-Kessel (G-K) algorithm is used instead of the Euclidean distance, to account for the non-spherical shape of the clusters in the feature space. These algorithms are quantitatively evaluated on MR brain images using the similarity measures.

The Neurocognitive and MRI Outcomes of West Nile Virus Infection: Preliminary Analysis Using an External Control Group.

To understand the long-term neurological outcomes resultant of West Nile virus (WNV) infection, participants from a previously established, prospective WNV cohort were invited to take part in a comprehensive neurologic and neurocognitive examination. Those with an abnormal exam finding were invited for MRI to evaluate cortical thinning and regional brain atrophy following infection. Correlations of presenting clinical syndrome with neurologic and neurocognitive dysfunctions were evaluated, as well as correlations of neurocognitive outcomes with MRI results. From 2002 to 2012, a total of 262 participants with a history of WNV infection were enrolled as research participants in a longitudinal cohort study, and 117 completed comprehensive neurologic and neurocognitive evaluations. Abnormal neurological exam findings were identified in 49% (57/117) of participants, with most abnormalities being unilateral. The most common abnormalities included decreased strength (26%; 30/117), abnormal reflexes (14%; 16/117), and tremors (10%; 12/117). Weakness and decreased reflexes were consistent with lower motor neuron damage in a significant proportion of patients. We observed a 22% overall rate of impairment on the Repeatable Battery for the Assessment of Neuropsychological Status (RBANS), with impairments observed in immediate (31%) and delayed memory (25%). On MRI, participants showed significant cortical thinning as compared to age- and gender-matched controls in both hemispheres, with affected regions primarily occurring in the frontal and limbic cortices. Regional atrophy occurred in the cerebellum, brain stem, thalamus, putamen, and globus pallidus. This study provides valuable new information regarding the neurological outcomes following WNV infection, with MRI evidence of significant cortical thinning and regional atrophy; however, it is important to note that the results may include systemic bias due to the external control group. Considering no effective treatment measures are available, strategies to prevent infection are key.

Regional gray matter atrophy in relapsing remitting multiple sclerosis: baseline analysis of multi-center data.

Regional gray matter (GM) atrophy in multiple sclerosis (MS) at disease onset and its temporal variation can provide objective information regarding disease evolution. An automated pipeline for estimating atrophy of various GM structures was developed using tensor based morphometry (TBM) and implemented on a multi-center sub-cohort of 1008 relapsing remitting MS (RRMS) patients enrolled in a Phase 3 clinical trial. Four hundred age and gender matched healthy controls were used for comparison. Using the analysis of covariance, atrophy differences between MS patients and healthy controls were assessed on a voxel-by-voxel analysis. Regional GM atrophy was observed in a number of deep GM structures that included thalamus, caudate nucleus, putamen, and cortical GM regions. General linear regression analysis was performed to analyze the effects of age, gender, and scanner field strength, and imaging sequence on the regional atrophy. Correlations between regional GM volumes and expanded disability status scale (EDSS) scores, disease duration (DD), T2 lesion load (T2 LL), T1 lesion load (T1 LL), and normalized cerebrospinal fluid (nCSF) were analyzed using Pearson׳s correlation coefficient. Thalamic atrophy observed in MS patients compared to healthy controls remained consistent within subgroups based on gender and scanner field strength. Weak correlations between thalamic volume and EDSS (r=-0.133; p<0.001) and DD (r=-0.098; p=0.003) were observed. Of all the structures, thalamic volume moderately correlated with T2 LL (r=-0.492; P-value<0.001), T1 LL (r=-0.473; P-value<0.001) and nCSF (r=-0.367; P-value<0.001).

Is 3D MPRAGE better than the combination DIR/PSIR for cortical lesion detection at 3T MRI?

BACKGROUND AND OBJECTIVES: Based on the application of newer magnetic resonance imaging (MRI) acquisition sequences, the detection of cortical lesions (CL) in multiple sclerosis (MS) has significantly improved. Double inversion recovery (DIR) at 3T has increased the detection sensitivity and classification specificity when combined with phase sensitive inversion recovery (PSIR). Previous findings with 3D magnetization prepared rapid acquisition with gradient echo (MPRAGE) sequences, showed improved classification specificity of purely intracortical (IC) and mixed (MX) lesions, compared to the classification based on DIR/PSIR. Direct comparison between the detection of CL by 3D MPRAGE and by DIR/PSIR at 3T has not been evaluated. METHODS: Eleven subjects were imaged on a 3T magnet. DIR/PSIR and 3D MPRAGE images were reviewed independently. Each image set was reviewed twice; only lesions detected on both sessions were scored. Review time per scan was ~5min for DIR/PSIR and ~15min for 3D MPRAGE. RESULTS: We identified 141 CL (62 IC+79 MX) based on DIR/PSIR images vs. 93 (38 IC+55 MX) based on MPRAGE from all eleven patients. MPRAGE under-detected the number of CL in seven cases and over-detected the number of CL in three, only one case had the same number of CL on both sets of images. CONCLUSIONS: Combination DIR/PSIR at 3T is superior to 3D MPRAGE for detection of cortical gray matter lesions in MS. The contrast-to-noise ratio of CL appears to be inferior on the MPRAGE images relative to DIR/PSIR.

A comprehensive approach to the segmentation of multichannel three-dimensional MR brain images in multiple sclerosis.

Accurate classification and quantification of brain tissues is important for monitoring disease progression, measurement of atrophy, and correlating magnetic resonance (MR) measures with clinical disability. Classification of MR brain images in the presence of lesions, such as multiple sclerosis (MS), is particularly challenging. Images obtained with lower resolution often suffer from partial volume averaging leading to false classifications. While partial volume averaging can be reduced by acquiring volumetric images at high resolution, image segmentation and quantification can be technically challenging. In this study, we integrated the brain anatomical knowledge with non-parametric and parametric statistical classifiers for automatically classifying tissues and lesions on high resolution multichannel three-dimensional images acquired on 60 MS brains. The results of automatic lesion segmentation were reviewed by the expert. The agreement between results obtained by the automated analysis and the expert was excellent as assessed by the quantitative metrics, low absolute volume difference percent (36.18 ± 34.90), low average symmetric surface distance (1.64 mm ± 1.30 mm), high true positive rate (84.75 ± 12.69), and low false positive rate (34.10 ± 16.00). The segmented results were also in close agreement with the corrected results as assessed by Bland-Altman and regression analyses. Finally, our lesion segmentation was validated using the MS lesion segmentation grand challenge dataset (MICCAI 2008).

Human brain atlas-based multimodal MRI analysis of volumetry, diffusimetry, relaxometry and lesion distribution in multiple sclerosis patients and healthy adult controls: implications for understanding the pathogenesis of multiple sclerosis and consolidation of quantitative MRI results in MS.

Multiple sclerosis (MS) is the most common immune-mediated disabling neurological disease of the central nervous system. The pathogenesis of MS is not fully understood. Histopathology implicates both demyelination and axonal degeneration as the major contributors to the accumulation of disability. The application of several in vivo quantitative magnetic resonance imaging (MRI) methods to both lesioned and normal-appearing brain tissue has not yet provided a solid conclusive support of the hypothesis that MS might be a diffuse disease. In this work, we adopted FreeSurfer to provide standardized macrostructure or volumetry of lesion free normal-appearing brain tissue in combination with multiple quantitative MRI metrics (T(2) relaxation time, diffusion tensor anisotropy and diffusivities) that characterize tissue microstructural integrity. By incorporating a large number of healthy controls, we have attempted to separate the natural age-related change from the disease-induced effects. Our work shows elevation in diffusivity and relaxation times and reduction in volume in a number of normal-appearing white matter and gray matter structures in relapsing-remitting multiple sclerosis patients. These changes were related in part with the spatial distribution of lesions. The whole brain lesion load and age-adjusted expanded disability status score showed strongest correlations in regions such as corpus callosum with qMRI metrics that are believed to be specific markers of axonal dysfunction, consistent with histologic data of others indicating axonal loss that is independent of focal lesions. Our results support that MS at least in part has a neurodegenerative component.

Regional cortical thickness in relapsing remitting multiple sclerosis: A multi-center study.

A comprehensive analysis of the global and regional values of cortical thickness based on 3D magnetic resonance images was performed on 250 relapsing remitting multiple sclerosis (MS) patients who participated in a multi-center, randomized, phase III clinical trial (the CombiRx Trial) and 125 normal controls. The MS cohort was characterized by relatively low clinical disability and short disease duration. An automatic pipeline was developed for identifying images with poor quality and artifacts. The global and regional cortical thicknesses were determined using FreeSurfer software. Our results indicate significant cortical thinning in multiple regions in the MS patient cohort relative to the controls. Both global cortical thinning and regional cortical thinning were more prominent in the left hemisphere relative to the right hemisphere. Modest correlation was observed between cortical thickness and clinical measures that included the extended disability status scale and disease duration. Modest correlation was also observed between cortical thickness and T1-hypointense and T2-hyperintense lesions. These correlations were very similar at 1.5 T and 3 T field strengths. A much weaker inverse correlation between cortical thickness and age was observed among the MS subjects compared to normal controls. This age-dependent correlation was also stronger in males than in females. The values of cortical thickness were very similar at 1.5 T and 3 T field strengths. However, the age-dependent changes in both global and regional cortical thicknesses were observed to be stronger at 3 T relative to 1.5 T.

Comprehensive brain MRI segmentation in high risk preterm newborns.

Most extremely preterm newborns exhibit cerebral atrophy/growth disturbances and white matter signal abnormalities on MRI at term-equivalent age. MRI brain volumes could serve as biomarkers for evaluating the effects of neonatal intensive care and predicting neurodevelopmental outcomes. This requires detailed, accurate, and reliable brain MRI segmentation methods. We describe our efforts to develop such methods in high risk newborns using a combination of manual and automated segmentation tools. After intensive efforts to accurately define structural boundaries, two trained raters independently performed manual segmentation of nine subcortical structures using axial T2-weighted MRI scans from 20 randomly selected extremely preterm infants. All scans were re-segmented by both raters to assess reliability. High intra-rater reliability was achieved, as assessed by repeatability and intra-class correlation coefficients (ICC range: 0.97 to 0.99) for all manually segmented regions. Inter-rater reliability was slightly lower (ICC range: 0.93 to 0.99). A semi-automated segmentation approach was developed that combined the parametric strengths of the Hidden Markov Random Field Expectation Maximization algorithm with non-parametric Parzen window classifier resulting in accurate white matter, gray matter, and CSF segmentation. Final manual correction of misclassification errors improved accuracy (similarity index range: 0.87 to 0.89) and facilitated objective quantification of white matter signal abnormalities. The semi-automated and manual methods were seamlessly integrated to generate full brain segmentation within two hours. This comprehensive approach can facilitate the evaluation of large cohorts to rigorously evaluate the utility of regional brain volumes as biomarkers of neonatal care and surrogate endpoints for neurodevelopmental outcomes.

Effect of cocaine on structural changes in brain: MRI volumetry using tensor-based morphometry.

Magnetic resonance imaging (MRI) was performed in cocaine-dependent subjects to determine the structural changes in brain compared to non-drug using controls. Cocaine-dependent subjects and controls were carefully screened to rule out brain pathology of undetermined origin. Magnetic resonance images were analyzed using tensor-based morphometry (TBM) and voxel-based morphometry (VBM) without and with modulation to adjust for volume changes during normalization. For TBM analysis, unbiased atlases were generated using two different inverse consistent and diffeomorphic nonlinear registration techniques. Two different control groups were used for generating unbiased atlases. Independent of the nonlinear registration technique and normal cohorts used for creating the unbiased atlases, our analysis failed to detect any statistically significant effect of cocaine on brain volumes. These results show that cocaine-dependent subjects do not show differences in regional brain volumes compared to non-drug using controls.

Symmetric inverse consistent nonlinear registration driven by mutual information.

A nonlinear viscoelastic image registration algorithm based on the demons paradigm and incorporating inverse consistent constraint (ICC) is implemented. An inverse consistent and symmetric cost function using mutual information (MI) as a similarity measure is employed. The cost function also includes regularization of transformation and inverse consistent error (ICE). The uncertainties in balancing various terms in the cost function are avoided by alternatively minimizing the similarity measure, the regularization of the transformation, and the ICE terms. The diffeomorphism of registration for preventing folding and/or tearing in the deformation is achieved by the composition scheme. The quality of image registration is first demonstrated by constructing brain atlas from 20 adult brains (age range 30-60). It is shown that with this registration technique: (1) the Jacobian determinant is positive for all voxels and (2) the average ICE is around 0.004 voxels with a maximum value below 0.1 voxels. Further, the deformation-based segmentation on Internet Brain Segmentation Repository, a publicly available dataset, has yielded high Dice similarity index (DSI) of 94.7% for the cerebellum and 74.7% for the hippocampus, attesting to the quality of our registration method.

Improved cerebellar tissue classification on magnetic resonance images of brain.

PURPOSE: To develop and implement a method for improved cerebellar tissue classification on the MRI of brain by automatically isolating the cerebellum prior to segmentation. MATERIALS AND METHODS: Dual fast spin echo (FSE) and fluid attenuation inversion recovery (FLAIR) images were acquired on 18 normal volunteers on a 3 T Philips scanner. The cerebellum was isolated from the rest of the brain using a symmetric inverse consistent nonlinear registration of individual brain with the parcellated template. The cerebellum was then separated by masking the anatomical image with individual FLAIR images. Tissues in both the cerebellum and rest of the brain were separately classified using hidden Markov random field (HMRF), a parametric method, and then combined to obtain tissue classification of the whole brain. The proposed method for tissue classification on real MR brain images was evaluated subjectively by two experts. The segmentation results on Brainweb images with varying noise and intensity nonuniformity levels were quantitatively compared with the ground truth by computing the Dice similarity indices. RESULTS: The proposed method significantly improved the cerebellar tissue classification on all normal volunteers included in this study without compromising the classification in remaining part of the brain. The average similarity indices for gray matter (GM) and white matter (WM) in the cerebellum are 89.81 (+/-2.34) and 93.04 (+/-2.41), demonstrating excellent performance of the proposed methodology. CONCLUSION: The proposed method significantly improved tissue classification in the cerebellum. The GM was overestimated when segmentation was performed on the whole brain as a single object.

Deep gray matter atrophy in multiple sclerosis: a tensor based morphometry.

Tensor based morphometry (TBM) was applied to determine the atrophy of deep gray matter (DGM) structures in 88 relapsing multiple sclerosis (MS) patients. For group analysis of atrophy, an unbiased atlas was constructed from 20 normal brains. The MS brain images were co-registered with the unbiased atlas using a symmetric inverse consistent nonlinear registration. These studies demonstrate significant atrophy of thalamus, caudate nucleus, and putamen even at a modest clinical disability, as assessed by the expanded disability status score (EDSS). A significant correlation between atrophy and EDSS was observed for different DGM structures: (thalamus: r=-0.51, p=3.85 x 10(-7); caudate nucleus: r=-0.43, p=2.35 x 10(-5); putamen: r=-0.36, p=6.12 x 10(-6)). Atrophy of these structures also correlated with 1) T2 hyperintense lesion volumes (thalamus: r=-0.56, p=9.96 x 10(-9); caudate nucleus: r=-0.31, p=3.10 x 10(-3); putamen: r=-0.50, p=6.06 x 10(-7)), 2) T1 hypointense lesion volumes (thalamus: r=-0.61, p=2.29 x 10(-10); caudate nucleus: r=-0.35, p=9.51 x 10(-4); putamen: r=-0.43, p=3.51 x 10(-5)), and 3) normalized CSF volume (thalamus: r=-0.66, p=3.55 x 10(-12); caudate nucleus: r=-0.52, p=2.31 x 10(-7), and putamen: r=-0.66, r=2.13 x 10(-12)). More severe atrophy was observed mainly in thalamus at higher EDSS. These studies appear to suggest a link between the white matter damage and DGM atrophy in MS.

Volume and shape in feature space on adaptive FCM in MRI segmentation.

Intensity non-uniformity (bias field) correction, contextual constraints over spatial intensity distribution and non-spherical cluster's shape in the feature space are incorporated into the fuzzy c-means (FCM) for segmentation of three-dimensional multi-spectral MR images. The bias field is modeled by a linear combination of smooth polynomial basis functions for fast computation in the clustering iterations. Regularization terms for the neighborhood continuity of either intensity or membership are added into the FCM cost functions. Since the feature space is not isotropic, distance measures, other than the Euclidean distance, are used to account for the shape and volumetric effects of clusters in the feature space. The performance of segmentation is improved by combining the adaptive FCM scheme with the criteria used in Gustafson-Kessel (G-K) and Gath-Geva (G-G) algorithms through the inclusion of the cluster scatter measure. The performance of this integrated approach is quantitatively evaluated on normal MR brain images using the similarity measures. The improvement in the quality of segmentation obtained with our method is also demonstrated by comparing our results with those produced by FSL (FMRIB Software Library), a software package that is commonly used for tissue classification.

Information measures-based intensity standardization of MRI.

Scan-to-scan intensity variation, even with the same imaging modality, affects a number of intensity-based image processing methods such as feature map based segmentation and non-rigid registration techniques that minimize sum of squared differences (SSD). Current intensity standardization techniques based on either percentile alignment or polynomial mapping suffer from a number of limitations. We present a novel intensity standardization techniques that exploits information measures obtained from the images. A probability similarity measure obtained by using polynomial mapping with Kullback-Leibler (KL) divergence is used for intensity standardization of pair-wise magnetic resonance (MR) images. For standardization of group-wise MR images, polynomial mapping with minimum entropy as a group probability similarity measure is used for attaining standardization in a group to attain common feature without bias. Our method is more flexible, particularly in mapping high intensity regions, such as lesions, since it does not set any hard limit. The mappings were realized through optimization of cost functions with Powell's search. The performance of the proposed method is demonstrated for non-rigid registration and feature map-based image segmentation of MR brain images.