Effect of Evobrutinib on Slowly Expanding Lesion Volume in Relapsing Multiple Sclerosis: A Post Hoc Analysis of a Phase 2 Trial.

BACKGROUND AND OBJECTIVES: Chronic active lesions (CALs) are demyelinated multiple sclerosis (MS) lesions with ongoing microglia/macrophage activity, resulting in irreversible neuronal damage and axonal loss. Evobrutinib is a highly selective, covalent, CNS-penetrant, Bruton tyrosine kinase inhibitor. This post hoc analysis evaluated the effect of evobrutinib on slowly expanding lesion (SEL) volume, an MRI marker of CALs, assessed baseline-week 48 in a phase 2, double-blind, randomized trial (NCT02975349) in relapsing MS (RMS). METHODS: In the 48-week, double-blind trial, adult patients received evobrutinib (25 mg once daily [QD], 75 mg QD, or 75 mg twice daily [BID]), placebo (switched to evobrutinib 25 mg QD after week 24), or open-label dimethyl fumarate (DMF) 240 mg BID. SELs were defined as slowly and consistently radially expanding areas of preexisting T2 lesions of ≥10 contiguous voxels (∼30 mm3) over time. SELs were identified by MRI and assessed by the Jacobian determinant of the nonlinear deformation from baseline to week 48. SEL volume analysis, stratified by baseline T2 lesion volume tertiles, was based on week 48/end-of-treatment status (completers/non-completers). Treatment effect was analyzed using the stratified Hodges-Lehmann estimate of shift in distribution and stratified Wilcoxon rank-sum test. Comparisons of evobrutinib and DMF vs placebo/evobrutinib 25 mg QD were made. Subgroup analyses used pooled treatment groups (evobrutinib high dose [75 mg QD/BID] vs low dose [placebo/evobrutinib 25 mg QD]). RESULTS: The SEL analysis set included 223 patients (mean [SD] age: 42.4 [10.7] years; 69.3% female; 87.4% relapsing/remitting MS). Mean (SD) SEL volume was 2,099 (2,981.0) mm3 with evobrutinib 75 mg BID vs 2,681 (3,624.2) mm3 with placebo/evobrutinib 25 mg QD. Median number of SELs/patient ranged from 7 to 11 across treatments. SEL volume decreased with increasing evobrutinib dose vs placebo/evobrutinib 25 mg QD, and no difference with DMF vs placebo/evobrutinib 25 mg QD was noted. SEL volume significantly decreased with evobrutinib 75 mg BID vs placebo/evobrutinib 25 mg QD (-474.5 mm3 [-1,098.0 to -3.0], p = 0.047) and vs DMF (-711.6 [-1,290.0 to -149.0], p = 0.011). SEL volume was significantly reduced for evobrutinib high vs low dose within baseline Expanded Disability Status Scale ≥3.5 and longer disease duration (≥8.5 years) subgroups. DISCUSSION: Evobrutinib reduced SEL volume in a dose-dependent manner in RMS, with a significant reduction with evobrutinib 75 mg BID. This is evident that evobrutinib affects brain lesions associated with chronic inflammation and tissue loss. TRIAL REGISTRATION INFORMATION: ClinicalTrials.gov number: NCT02975349. Submitted to ClinicalTrials.gov on November 29, 2016. First patient enrolled: March 7, 2017. CLASSIFICATION OF EVIDENCE: This study provides Class II evidence that evobrutinib reduces the volume of SELs assessed on MRI comparing baseline with week 48, in patients with RMS.

Imaging chronic active lesions in multiple sclerosis: a consensus statement.

Chronic active lesions (CAL) are an important manifestation of chronic inflammation in multiple sclerosis (MS) and have implications for non-relapsing biological progression. In recent years, the discovery of innovative magnetic resonance imaging (MRI) and PET derived biomarkers has made it possible to detect CAL, and to some extent quantify them, in the brain of persons with MS, in vivo. Paramagnetic rim lesions on susceptibility-sensitive MRI sequences, MRI-defined slowly expanding lesions on T1-weighted (T1-w) and T2-w scans, and 18-kDa translocator protein-positive lesions on PET are promising candidate biomarkers of CAL. While partially overlapping, these biomarkers do not have equivalent sensitivity and specificity to histopathological CAL. Standardization in the use of available imaging measures for CAL identification, quantification, and monitoring is lacking. To fast-forward clinical translation of CAL, the North American Imaging in Multiple Sclerosis Cooperative developed a Consensus Statement, which provides guidance for the radiological definition and measurement of CAL. The proposed manuscript presents this Consensus Statement, summarizes the multistep process leading to it, and identifies the remaining major gaps in knowledge.

Brain volume increase after discontinuing natalizumab therapy: Evidence for reversible pseudoatrophy.

BACKGROUND: The phenomenon of pseudoatropy after initiation of anti-inflammatory therapy is believed to be reversible, but a rebound in brain volume following cessation of highly-effective therapy has not been reported. OBJECTIVES: To evaluate brain volume change in a treatment interruption study (RESTORE) in which relapsing-remitting multiple sclerosis (RRMS) patients were randomized to switch from natalizumab to placebo, from natalizumab to once-monthly intravenous methylprednisolone (IVMP), or to remain on natalizumab. METHODS: T2 lesion volume (T2LV), baseline normalized brain volumes, and follow-up percent brain volume changes (PBVC) were calculated. Approximate T2 relaxation-time (pT2) was calculated within the brain mask and the T2 lesions to estimate changes in water content. Linear mixed effects models were used to detect differences in T2LV, pT2 in whole brain, pT2 in T2-weighted lesions, and PBVC among the placebo, natalizumab, and IVMP groups. We also estimated contributions of T2LV and pT2 (in whole brain and T2 lesions) to PBVC. RESULTS: T2LV increased in the placebo group (by 0.66 ml/year, p<0.0001) and IVMP (+1.98 ml/year, p = 0.05) groups relative to the natalizumab group. The rates of PBVC were significantly different: -0.239%/year with continued natalizumab and +0.126 %/year after switch to placebo (p = 0.03), while the IVMP group showed brain volume loss (-0.74 %/ year, p = 0.08). pT2 was not statistically different between the groups (p ≥ 0.29) and did not have significant effects on PBVC (p ≥ 0.25). CONCLUSION: The increase in the brain volume in patients witching from natalizumab to placebo is consistent with reversal of so-called pseudoatrophy after starting natalizumab.

Assessing the utility of magnetic resonance imaging-based "SuStaIn" disease subtyping for precision medicine in relapsing-remitting and secondary progressive multiple sclerosis.

BACKGROUND: Patient stratification and individualized treatment decisions based on multiple sclerosis (MS) clinical phenotypes are arbitrary. Subtype and Staging Inference (SuStaIn), a published machine learning algorithm, was developed to identify data-driven disease subtypes with distinct temporal progression patterns using brain magnetic resonance imaging; its clinical utility has not been assessed. The objective of this study was to explore the prognostic capability of SuStaIn subtyping and whether it is a useful personalized predictor of treatment effects of natalizumab and dimethyl fumarate. METHODS: Subtypes were available from the trained SuStaIn model for 3 phase 3 clinical trials in relapsing-remitting and secondary progressive MS. Regression models were used to determine whether baseline SuStaIn subtypes could predict on-study clinical and radiological disease activity and progression. Differences in treatment responses relative to placebo between subtypes were determined using interaction terms between treatment and subtype. RESULTS: Natalizumab and dimethyl fumarate reduced inflammatory disease activity in all SuStaIn subtypes (all p < 0.001). SuStaIn MS subtyping alone did not discriminate responder heterogeneity based on new lesion formation and disease progression (p > 0.05 across subtypes). CONCLUSION: SuStaIn subtypes correlated with disease severity and functional impairment at baseline but were not predictive of disability progression and could not discriminate treatment response heterogeneity.

Glial fibrillary acidic protein and multiple sclerosis progression independent of acute inflammation.

BACKGROUND: The clinical relevance of serum glial fibrillary acidic protein (sGFAP) concentration as a biomarker of MS disability progression independent of acute inflammation has yet to be quantified. OBJECTIVE: To test whether baseline values and longitudinal changes in sGFAP concentration are associated with disability progression without detectable relapse of magnetic resonance imaging (MRI) inflammatory activity in participants with secondary-progressive multiple sclerosis (SPMS). METHODS: We retrospectively analyzed longitudinal sGFAP concentration and clinical outcome data from the Phase 3 ASCEND trial of participants with SPMS, with no detectable relapse or MRI signs of inflammatory activity at baseline nor during the study (n = 264). Serum neurofilament (sNfL), sGFAP, T2 lesion volume, Expanded Disability Status Scale (EDSS), Timed 25-Foot Walk (T25FW), 9-Hole Peg Test (9HPT), and composite confirmed disability progression (CDP) were measured. Linear and logistic regressions and generalized estimating equations were used in the prognostic and dynamic analyses. RESULTS: We found a significant cross-sectional association between baseline sGFAP and sNfL concentrations and T2 lesion volume. No or weak correlations between sGFAP concentration and changes in EDSS, T25FW, and 9HPT, or CDP were observed. CONCLUSION: Without inflammatory activity, changes in sGFAP concentration in participants with SPMS were neither associated with current nor predictive of future disability progression.

Ocrelizumab-treated patients with relapsing multiple sclerosis show volume loss rates similar to healthy aging.

BACKGROUND: Multiple sclerosis (MS) is a chronic autoimmune disease of the central nervous system characterized by two major and interconnected hallmarks: inflammation and progressive neurodegeneration. OBJECTIVE: The aim of this work was to compare neurodegenerative processes, in the form of global and regional brain volume loss rates, in healthy controls (HCs) and in patients with relapsing MS (RMS) treated with ocrelizumab, which suppresses acute inflammation. METHODS: Whole brain, white matter, cortical gray matter, thalamic, and cerebellar volume loss rates were assessed in 44 HCs that were part of a substudy in the OPERA II randomized controlled trial (NCT01412333) and 59 patients with RMS enrolled in the same substudy as well as age- and sex-matched patients in OPERA I (NCT01247324) and II. Volume loss rates were computed using random coefficients models over a period of 2 years. RESULTS: Ocrelizumab-treated patients showed global and regional brain volume loss rates that were approaching that of HCs. CONCLUSION: These findings are consistent with an important role of inflammation on overall tissue loss and the role of ocrelizumab in reducing this phenomenon.

Lesion-level correspondence and longitudinal properties of paramagnetic rim and slowly expanding lesions in multiple sclerosis.

BACKGROUND: Paramagnetic rim lesions (PRLs) and slowly expanding lesions (SELs) have been posited as markers of chronic active lesions (CALs). OBJECTIVE: To assess the lesion-level concordance of PRLs and SELs in MS and to characterize changes in brain tissue integrity in CALs over time. METHODS: MRIs were analyzed from a substudy of AFFINITY [NCT03222973], a phase 2 trial of opicinumab in relapsing MS. Assessments included (1) identification of SELs based on longitudinal MRIs over 72 weeks, and identification of PRLs on susceptibility-weighted imaging (SWI) filtered phase images at week 72; (2) evaluation of subject-level correlation of SEL and PRL counts, volumes, and degree of lesion-level overlap between SELs and PRLs; and (3) characterization of tissue integrity over time in overlapping and non-overlapping SELs and PRLs. RESULTS: In 41 subjects, 119 chronic PRLs and 267 SELs were detected. Of 119 (39.5%) chronic PRLs, 47 co-localized with a SEL; 46/267 (17.2%) SELs co-localized with a PRL. PRLs co-localized with SELs showed expansion and worsening microstructural damage over time. SELs with and without co-localization with PRLs showed ongoing tissue damage. CONCLUSIONS: Chronic MS lesions identified as both PRL and SEL were associated with the most severe accumulation of tissue damage. TRIAL REGISTRATION: AFFINITY [NCT03222973].

Single-timepoint low-dimensional characterization and classification of acute versus chronic multiple sclerosis lesions using machine learning.

Multiple sclerosis (MS) is a chronic inflammatory and neurodegenerative disease characterized by the appearance of focal lesions across the central nervous system. The discrimination of acute from chronic MS lesions may yield novel biomarkers of inflammatory disease activity which may support patient management in the clinical setting and provide endpoints in clinical trials. On a single timepoint and in the absence of a prior reference scan, existing methods for acute lesion detection rely on the segmentation of hyperintense foci on post-gadolinium T1-weighted magnetic resonance imaging (MRI), which may underestimate recent acute lesion activity. In this paper, we aim to improve the sensitivity of acute MS lesion detection in the single-timepoint setting, by developing a novel machine learning approach for the automatic detection of acute MS lesions, using single-timepoint conventional non-contrast T1- and T2-weighted brain MRI. The MRI input data are supplemented via the use of a convolutional neural network generating "lesion-free" reconstructions from original "lesion-present" scans using image inpainting. A multi-objective statistical ranking module evaluates the relevance of textural radiomic features from the core and periphery of lesion sites, compared within "lesion-free" versus "lesion-present" image pairs. Then, an ensemble classifier is optimized through a recursive loop seeking consensus both in the feature space (via a greedy feature-pruning approach) and in the classifier space (via model selection repeated after each pruning operation). This leads to the identification of a compact textural signature characterizing lesion phenotype. On the patch-level task of acute versus chronic MS lesion classification, our method achieves a balanced accuracy in the range of 74.3-74.6% on fully external validation cohorts.

Chronic lesion activity and disability progression in secondary progressive multiple sclerosis.

Objective: Slowly expanding lesions (SELs), a subgroup of chronic white matter lesions that gradually expand over time, have been shown to predict disability accumulation in primary progressive multiple sclerosis (MS) disease. However, the relationships between SELs, acute lesion activity (ALA), overall chronic lesion activity (CLA) and disability progression are not well understood. In this study, we examined the ASCEND phase III clinical trial, which compared natalizumab with placebo in secondary progressive MS (SPMS). Methods: Patients with complete imaging datasets between baseline and week 108 (N=600) were analysed for SEL prevalence (the number and volume of SELs), disability progression, ALA (assessed by gadolinium-enhancing lesions and new T2-hyperintense lesions) and CLA (assessed by T1-hypointense lesion volume increase within baseline T2-non-enhancing lesions identified as SELs and non-SELs). Results: CLA in both SELs and non-SELs was greater in patients with SPMS with confirmed disability progression than in those with no progression. In the complete absence of ALA at baseline and on study, SEL prevalence was significantly lower, while CLA within non-SELs remained associated with disability progression. Natalizumab decreased SEL prevalence and CLA in SELs and non-SELs compared with placebo. Conclusions: This study shows that CLA in patients with SPMS is decreased but persists in the absence of ALA and is associated with disability progression, highlighting the need for therapeutics targeting all mechanisms of CLA, including smouldering inflammation and neurodegeneration. Trial registration number: NCT01416181.

Abnormalities in normal-appearing white matter from which multiple sclerosis lesions arise.

Normal-appearing white matter is far from normal in multiple sclerosis; little is known about the precise pathology or spatial pattern of this alteration and its relation to subsequent lesion formation. This study was undertaken to evaluate normal-appearing white matter abnormalities in brain areas where multiple sclerosis lesions subsequently form, and to investigate the spatial distribution of normal-appearing white matter abnormalities in persons with multiple sclerosis. Brain MRIs of pre-lesion normal-appearing white matter were analysed in participants with new T2 lesions, pooled from three clinical trials: SYNERGY (NCT01864148; n = 85 with relapsing multiple sclerosis) was the test data set; ASCEND (NCT01416181; n = 154 with secondary progressive multiple sclerosis) and ADVANCE (NCT00906399; n = 261 with relapsing-remitting multiple sclerosis) were used as validation data sets. Focal normal-appearing white matter tissue state was analysed prior to lesion formation in areas where new T2 lesions later formed (pre-lesion normal-appearing white matter) using normalized magnetization transfer ratio and T2-weighted (nT2) intensities, and compared with overall normal-appearing white matter and spatially matched contralateral normal-appearing white matter. Each outcome was analysed using linear mixed-effects models. Follow-up time (as a categorical variable), patient-level characteristics (including treatment group) and other baseline variables were treated as fixed effects. In SYNERGY, nT2 intensity was significantly higher, and normalized magnetization transfer ratio was lower in pre-lesion normal-appearing white matter versus overall and contralateral normal-appearing white matter at all time points up to 24 weeks before new T2 lesion onset. In ASCEND and ADVANCE (for which normalized magnetization transfer ratio was not available), nT2 intensity in pre-lesion normal-appearing white matter was significantly higher compared to both overall and contralateral normal-appearing white matter at all pre-lesion time points extending up to 2 years prior to lesion formation. In all trials, nT2 intensity in the contralateral normal-appearing white matter was also significantly higher at all pre-lesion time points compared to overall normal-appearing white matter. Brain atlases of normal-appearing white matter abnormalities were generated using measures of voxel-wise differences in normalized magnetization transfer ratio of normal-appearing white matter in persons with multiple sclerosis compared to scanner-matched healthy controls. We observed that overall spatial distribution of normal-appearing white matter abnormalities in persons with multiple sclerosis largely recapitulated the anatomical distribution of probabilities of T2 hyperintense lesions. Overall, these findings suggest that intrinsic spatial properties and/or longstanding precursory abnormalities of normal-appearing white matter tissue may contribute to the risk of autoimmune acute demyelination in multiple sclerosis.

Chronic white matter lesion activity predicts clinical progression in primary progressive multiple sclerosis.

Chronic active and slowly expanding lesions with smouldering inflammation are neuropathological correlates of progressive multiple sclerosis pathology. T1 hypointense volume and signal intensity on T1-weighted MRI reflect brain tissue damage that may develop within newly formed acute focal inflammatory lesions or in chronic pre-existing lesions without signs of acute inflammation. Using a recently developed method to identify slowly expanding/evolving lesions in vivo from longitudinal conventional T2- and T1-weighted brain MRI scans, we measured the relative amount of chronic lesion activity as measured by change in T1 volume and intensity within slowly expanding/evolving lesions and non-slowly expanding/evolving lesion areas of baseline pre-existing T2 lesions, and assessed the effect of ocrelizumab on this outcome in patients with primary progressive multiple sclerosis participating in the phase III, randomized, placebo-controlled, double-blind ORATORIO study (n = 732, NCT01194570). We also assessed the predictive value of T1-weighted measures of chronic lesion activity for clinical multiple sclerosis progression as reflected by a composite disability measure including the Expanded Disability Status Scale, Timed 25-Foot Walk and 9-Hole Peg Test. We observed in this clinical trial population that most of total brain non-enhancing T1 hypointense lesion volume accumulation was derived from chronic lesion activity within pre-existing T2 lesions rather than new T2 lesion formation. There was a larger decrease in mean normalized T1 signal intensity and greater relative accumulation of T1 hypointense volume in slowly expanding/evolving lesions compared with non-slowly expanding/evolving lesions. Chronic white matter lesion activity measured by longitudinal T1 hypointense lesion volume accumulation in slowly expanding/evolving lesions and in non-slowly expanding/evolving lesion areas of pre-existing lesions predicted subsequent composite disability progression with consistent trends on all components of the composite. In contrast, whole brain volume loss and acute lesion activity measured by longitudinal T1 hypointense lesion volume accumulation in new focal T2 lesions did not predict subsequent composite disability progression in this trial at the population level. Ocrelizumab reduced longitudinal measures of chronic lesion activity such as T1 hypointense lesion volume accumulation and mean normalized T1 signal intensity decrease both within regions of pre-existing T2 lesions identified as slowly expanding/evolving and in non-slowly expanding/evolving lesions. Using conventional brain MRI, T1-weighted intensity-based measures of chronic white matter lesion activity predict clinical progression in primary progressive multiple sclerosis and may qualify as a longitudinal in vivo neuroimaging correlate of smouldering demyelination and axonal loss in chronic active lesions due to CNS-resident inflammation and/or secondary neurodegeneration across the multiple sclerosis disease continuum.

Using Deep Learning Algorithms to Automatically Identify the Brain MRI Contrast: Implications for Managing Large Databases.

Neuroimaging science has seen a recent explosion in dataset size driving the need to develop database management with efficient processing pipelines. Multi-center neuroimaging databases consistently receive magnetic resonance imaging (MRI) data with unlabeled or incorrectly labeled contrast. There is a need to automatically identify the contrast of MRI scans to save database-managing facilities valuable resources spent by trained technicians required for visual inspection. We developed a deep learning (DL) algorithm with convolution neural network architecture to automatically infer the contrast of MRI scans based on the image intensity of multiple slices. For comparison, we developed a random forest (RF) algorithm to automatically infer the contrast of MRI scans based on acquisition parameters. The DL algorithm was able to automatically identify the MRI contrast of an unseen dataset with <0.2% error rate. The RF algorithm was able to identify the MRI contrast of the same dataset with 1.74% error rate. Our analysis showed that reduced dataset sizes caused the DL algorithm to lose generalizability. Finally, we developed a confidence measure, which made it possible to detect, with 100% specificity, all MRI volumes that were misclassified by the DL algorithm. This confidence measure can be used to alert the user on the need to inspect the small fraction of MRI volumes that are prone to misclassification. Our study introduces a practical solution for automatically identifying the MRI contrast. Furthermore, it demonstrates the powerful combination of convolution neural networks and DL for analyzing large MRI datasets.

Slowly expanding/evolving lesions as a magnetic resonance imaging marker of chronic active multiple sclerosis lesions.

BACKGROUND: Chronic lesion activity driven by smoldering inflammation is a pathological hallmark of progressive forms of multiple sclerosis (MS). OBJECTIVE: To develop a method for automatic detection of slowly expanding/evolving lesions (SELs) on conventional brain magnetic resonance imaging (MRI) and characterize such SELs in primary progressive MS (PPMS) and relapsing MS (RMS) populations. METHODS: We defined SELs as contiguous regions of existing T2 lesions showing local expansion assessed by the Jacobian determinant of the deformation between reference and follow-up scans. SEL candidates were assigned a heuristic score based on concentricity and constancy of change in T2- and T1-weighted MRIs. SELs were examined in 1334 RMS patients and 555 PPMS patients. RESULTS: Compared with RMS patients, PPMS patients had higher numbers of SELs (p = 0.002) and higher T2 volumes of SELs (p < 0.001). SELs were devoid of gadolinium enhancement. Compared with areas of T2 lesions not classified as SEL, SELs had significantly lower T1 intensity at baseline and larger decrease in T1 intensity over time. CONCLUSION: We suggest that SELs reflect chronic tissue loss in the absence of ongoing acute inflammation. SELs may represent a conventional brain MRI correlate of chronic active MS lesions and a candidate biomarker for smoldering inflammation in MS.

White matter changes in paediatric multiple sclerosis and monophasic demyelinating disorders.

See Hacohen et al. (doi:10.1093/awx075) for a scientific commentary on this article. Most children who experience an acquired demyelinating syndrome of the central nervous system will have a monophasic disease course, with no further clinical or radiological symptoms. A subset will be diagnosed with multiple sclerosis, a life-long disorder. Using linear mixed effects models we examined longitudinal diffusion properties of normal-appearing white matter in 505 serial scans of 132 paediatric participants with acquired demyelinating syndromes followed for a median of 4.4 years, many from first clinical presentation, and 106 scans of 80 healthy paediatric participants. Fifty-three participants with demyelinating syndromes eventually received a diagnosis of paediatric-onset multiple sclerosis. Diffusion tensor imaging measures properties of water diffusion through tissue, which normally becomes increasingly restricted and anisotropic in the brain during childhood and adolescence, as fibre bundles develop and myelinate. In the healthy paediatric participants, our data demonstrate the expected trajectory of more restricted and anisotropic white matter diffusivity with increasing age. However, in participants with multiple sclerosis, fractional anisotropy decreased and mean diffusivity of non-lesional, normal-appearing white matter progressively increased after clinical presentation, suggesting not only a failure of age-expected white matter development but also a progressive loss of tissue integrity. Surprisingly, patients with monophasic disease failed to show age-expected changes in diffusion parameters in normal-appearing white matter, although they did not show progressive loss of integrity over time. Further analysis demonstrated that participants with monophasic disease experienced different post-onset trajectories in normal-appearing white matter depending on their presenting phenotype: those with acute disseminated encephalomyelitis demonstrated abnormal trajectories of diffusion parameters compared to healthy paediatric participants, as did patients with non-acute disseminated encephalomyelitis presentations associated with lesions in the brain at onset. Patients with monofocal syndromes such as optic neuritis, transverse myelitis, or isolated brainstem syndromes in whom multifocal brain lesions were absent, showed trajectories more closely approximating normal-appearing white matter development. Our findings also suggest the existence of sexual dimorphism in the effects of demyelinating syndromes on normal-appearing white matter development. Overall, we demonstrate failure of white matter maturational changes and progressive loss of white matter integrity in paediatric-onset multiple sclerosis, but also show that even a single demyelinating attack-when associated with white matter lesions in the brain-negatively impacts subsequent normal-appearing white matter development.

Temporally consistent probabilistic detection of new multiple sclerosis lesions in brain MRI.

Detection of new Multiple Sclerosis (MS) lesions on magnetic resonance imaging (MRI) is important as a marker of disease activity and as a potential surrogate for relapses. We propose an approach where sequential scans are jointly segmented, to provide a temporally consistent tissue segmentation while remaining sensitive to newly appearing lesions. The method uses a two-stage classification process: 1) a Bayesian classifier provides a probabilistic brain tissue classification at each voxel of reference and follow-up scans, and 2) a random-forest based lesion-level classification provides a final identification of new lesions. Generative models are learned based on 364 scans from 95 subjects from a multi-center clinical trial. The method is evaluated on sequential brain MRI of 160 subjects from a separate multi-center clinical trial, and is compared to 1) semi-automatically generated ground truth segmentations and 2) fully manual identification of new lesions generated independently by nine expert raters on a subset of 60 subjects. For new lesions greater than 0.15 cc in size, the classifier has near perfect performance (99% sensitivity, 2% false detection rate), as compared to ground truth. The proposed method was also shown to exceed the performance of any one of the nine expert manual identifications.

Bayesian classification of multiple sclerosis lesions in longitudinal MRI using subtraction images.

Accurate and precise identification of multiple sclerosis (MS) lesions in longitudinal MRI is important for monitoring disease progression and for assessing treatment effects. We present a probabilistic framework to automatically detect new, enlarging and resolving lesions in longitudinal scans of MS patients based on multimodal subtraction magnetic resonance (MR) images. Our Bayesian framework overcomes registration artifact by explicitly modeling the variability in the difference images, the tissue transitions, and the neighbourhood classes in the form of likelihoods, and by embedding a classification of a reference scan as a prior. Our method was evaluated on (a) a scan-rescan data set consisting of 3 MS patients and (b) a multicenter clinical data set consisting of 212 scans from 89 RRMS (relapsing-remitting MS) patients. The proposed method is shown to identify MS lesions in longitudinal MRI with a high degree of precision while remaining sensitive to lesion activity.

Graded classification of fetal heart rate tracings: association with neonatal metabolic acidosis and neurologic morbidity.

OBJECTIVE: The objective of the study was to measure the performance of a 5-tier, color-coded graded classification of electronic fetal monitoring (EFM). STUDY DESIGN: We used specialized software to analyze and categorize 7416 hours of EFM from term pregnancies. We measured how often and for how long each of the color-coded levels appeared in 3 groups of babies: (A) 60 babies with neonatal encephalopathy (NE) and umbilical artery base deficit (BD) levels were greater than 12 mmol/L; (I) 280 babies without NE but with BD greater than 12 mmol/L; and (N) 2132 babies with normal gases. RESULTS: The frequency and duration of EFM abnormalities considered more severe in the classification method were highest in group A and lowest in group N. Detecting an equivalent percentage of cases with adverse outcomes required only minutes spent with marked EFM abnormalities compared with much longer periods with lesser abnormalities. CONCLUSION: Both degree and duration of tracing abnormality are related to outcome. We present empirical data quantifying that relationship in a systematic fashion.