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

A Systematic Review on the Use of Registration-Based Change Tracking Methods in Longitudinal Radiological Images

Registration is the process of spatially and/or temporally aligning different images. It is a critical tool that can facilitate the automatic tracking of pathological changes detected in radiological images and align images captured by different imaging systems and/or those acquired using different acquisition parameters. The longitudinal analysis of clinical changes has a significant role in helping clinicians evaluate disease progression and determine the most suitable course of treatment for patients. This study provides a comprehensive review of the role registration-based approaches play in automated change tracking in radiological imaging and explores the three types of registration approaches which include rigid, affine, and nonrigid registration, as well as methods of detecting and quantifying changes in registered longitudinal images: the intensity-based approach and the deformation-based approach. After providing an overview and background, we highlight the clinical applications of these methods, specifically focusing on computed tomography (CT) and magnetic resonance imaging (MRI) in tumors and multiple sclerosis (MS), two of the most heavily studied areas in automated change tracking. We conclude with a discussion and recommendation for future directions.

Image harmonization improves consistency of intra-rater delineations of MS lesions in heterogeneous MRI

Clinical magnetic resonance images (MRIs) lack a standard intensity scale due to differences in scanner hardware and the pulse sequences used to acquire the images. When MRIs are used for quantification, as in the evaluation of white matter lesions (WMLs) in multiple sclerosis, this lack of intensity standardization becomes a critical problem affecting both the staging and tracking of the disease and its treatment. This paper presents a study of harmonization on WML segmentation consistency, which is evaluated using an object detection classification scheme that incorporates manual delineations from both the original and harmonized MRIs. A cohort of ten people scanned on two different imaging platforms was studied. An expert rater, blinded to the image source, manually delineated WMLs on images from both scanners before and after harmonization. It was found that there is closer agreement in both global and per-lesion WML volume and spatial distribution after harmonization, demonstrating the importance of image harmonization prior to the creation of manual delineations. These results could lead to better truth models in both the development and evaluation of automated lesion segmentation algorithms.

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.

How far MS lesion detection and segmentation are integrated into the clinical workflow? A systematic review

INTRODUCTION

Over the past few years, the deep learning community has developed and validated a plethora of tools for lesion detection and segmentation in Multiple Sclerosis (MS). However, there is an important gap between validating models technically and clinically. To this end, a six-step framework necessary for the development, validation, and integration of quantitative tools in the clinic was recently proposed under the name of the Quantitative Neuroradiology Initiative (QNI).

AIMS

Investigate to what extent automatic tools in MS fulfill the QNI framework necessary to integrate automated detection and segmentation into the clinical neuroradiology workflow.

METHODS

Adopting the systematic Cochrane literature review methodology, we screened and summarised published scientific articles that perform automatic MS lesions detection and segmentation. We categorised the retrieved studies based on their degree of fulfillment of QNI's six-steps, which include a tool's technical assessment, clinical validation, and integration.

RESULTS

We found 156 studies; 146/156 (94%) fullfilled the first QNI step, 155/156 (99%) the second, 8/156 (5%) the third, 3/156 (2%) the fourth, 5/156 (3%) the fifth and only one the sixth.

CONCLUSIONS

To date, little has been done to evaluate the clinical performance and the integration in the clinical workflow of available methods for MS lesion detection/segmentation. In addition, the socio-economic effects and the impact on patients' management of such tools remain almost unexplored.

An open-source tool for longitudinal whole-brain and white matter lesion segmentation

In this paper we describe and validate a longitudinal method for whole-brain segmentation of longitudinal MRI scans. It builds upon an existing whole-brain segmentation method that can handle multi-contrast data and robustly analyze images with white matter lesions. This method is here extended with subject-specific latent variables that encourage temporal consistency between its segmentation results, enabling it to better track subtle morphological changes in dozens of neuroanatomical structures and white matter lesions. We validate the proposed method on multiple datasets of control subjects and patients suffering from Alzheimer's disease and multiple sclerosis, and compare its results against those obtained with its original cross-sectional formulation and two benchmark longitudinal methods. The results indicate that the method attains a higher test-retest reliability, while being more sensitive to longitudinal disease effect differences between patient groups. An implementation is publicly available as part of the open-source neuroimaging package FreeSurfer.

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.

Gadolinium-based contrast agent exposures and physical and cognitive disability in multiple sclerosis

BACKGROUND AND PURPOSE

The clinical correlation of gadolinium-based contrast agents (GBCAs) has not been well studied in multiple sclerosis (MS). We investigated the extent to which the number of GBCA administrations relates to self-reported disability and performance measures.

METHODS

A cohort of MS patients was analyzed in this retrospective observational study. The main outcome was the association between the cumulative number of GBCA exposures (linear or macrocyclic GBCA), Patient-Determined Disease Steps (PDDS), and measures of physical and cognitive performance (walking speed test, manual dexterity test [MDT], and processing speed test [PST]). The analysis was performed first cross-sectionally and then longitudinally.

RESULTS

The cross-sectional data included 1059 MS patients with a mean age of 44.0 years (standard deviation = 11.2). While the contrast ratio in globus pallidus weakly correlated with PDDS, MDT, and PST in a univariate correlational analysis (coefficients, 95% confidence interval [CI] = 0.11 [0.04, 0.18], 0.15 [0.08, 0.21], and -0.16 [-0.10, -0.23], respectively), the associations disappeared after covariate adjustment. A significant association was found between number of linear GBCA administrations and PDDS (coefficient [CI] = -0.131 [-0.196, -0.067]), and MDT associated with macrocyclic GBCA administrations (-0.385 [-0.616, -0.154]), but their signs indicated better outcomes in patients with greater GBCA exposures. The longitudinal data showed no significant detrimental effect of macrocyclic GBCA exposures.

CONCLUSION

No detrimental effects were observed between GBCA exposure and self-reported disability and standardized objective measures of physical and cognitive performance. While several weak associations were found, they indicated benefit on these measures.

Automatic detection of active and inactive multiple sclerosis plaques using the Bayesian approach in susceptibility-weighted imaging

BACKGROUND

Susceptibility-weighted imaging (SWI) is efficient in detecting multiple sclerosis (MS) plaques and evaluating the level of disease activity.

PURPOSE

To automatically detect active and inactive MS plaques in SWI images using a Bayesian approach.

MATERIAL AND METHODS

A 1.5-T scanner was used to evaluate 147 patients with MS. The area of the plaques along with their active or inactive status were automatically identified using a Bayesian approach. Plaques were given an orange color if they were active and a blue color if they were inactive, based on the preset signal intensity.

RESULTS

Experimental findings show that the proposed method has a high accuracy rate of 91% and a sensitivity rate of 76% for identifying the type and area of plaques. Inactive plaques were properly identified in 87% of cases, and active plaques in 76% of cases. The Kappa analysis revealed an 80% agreement between expert diagnoses based on contrast-enhanced and FLAIR images and Bayesian inferences in SWI.

CONCLUSION

The results of our study demonstrated that the proposed method has good accuracy for identifying the MS plaque area as well as for identifying the types of active or inactive plaques in SWI. Therefore, it might be helpful to use the proposed method as a supplemental tool to accelerate the specialist's diagnosis.

A unified framework for focal intensity change detection and deformable image registration. Application to the monitoring of multiple sclerosis lesions in longitudinal 3D brain MRI

Registration is a crucial step in the design of automatic change detection methods dedicated to longitudinal brain MRI. Even small registration inaccuracies can significantly deteriorate the detection performance by introducing numerous spurious detections. Rigid or affine registration are usually considered to align baseline and follow-up scans, as a pre-processing step before applying a change detection method. In the context of multiple sclerosis, using deformable registration can be required to capture the complex deformations due to brain atrophy. However, non-rigid registration can alter the shape of appearing and evolving lesions while minimizing the dissimilarity between the two images. To overcome this issue, we consider registration and change detection as intertwined problems that should be solved jointly. To this end, we formulate these two separate tasks as a single optimization problem involving a unique energy that models their coupling. We focus on intensity-based change detection and registration, but the approach is versatile and could be extended to other modeling choices. We show experimentally on synthetic and real data that the proposed joint approach overcomes the limitations of the sequential scheme.

Improving the detection of new lesions in multiple sclerosis with a cascaded 3D fully convolutional neural network approach

Longitudinal magnetic resonance imaging (MRI) has an important role in multiple sclerosis (MS) diagnosis and follow-up. Specifically, the presence of new lesions on brain MRI scans is considered a robust predictive biomarker for the disease progression. New lesions are a high-impact prognostic factor to predict evolution to MS or risk of disability accumulation over time. However, the detection of this disease activity is performed visually by comparing the follow-up and baseline scans. Due to the presence of small lesions, misregistration, and high inter-/intra-observer variability, this detection of new lesions is prone to errors. In this direction, one of the last Medical Image Computing and Computer Assisted Intervention (MICCAI) challenges was dealing with this automatic new lesion quantification. The MSSEG-2: MS new lesions segmentation challenge offers an evaluation framework for this new lesion segmentation task with a large database (100 patients, each with two-time points) compiled from the OFSEP (Observatoire français de la sclérose en plaques) cohort, the French MS registry, including 3D T2-w fluid-attenuated inversion recovery (T2-FLAIR) images from different centers and scanners. Apart from a change in centers, MRI scanners, and acquisition protocols, there are more challenges that hinder the automated detection process of new lesions such as the need for large annotated datasets, which may be not easily available, or the fact that new lesions are small areas producing a class imbalance problem that could bias trained models toward the non-lesion class. In this article, we present a novel automated method for new lesion detection of MS patient images. Our approach is based on a cascade of two 3D patch-wise fully convolutional neural networks (FCNNs). The first FCNN is trained to be more sensitive revealing possible candidate new lesion voxels, while the second FCNN is trained to reduce the number of misclassified voxels coming from the first network. 3D T2-FLAIR images from the two-time points were pre-processed and linearly co-registered. Afterward, a fully CNN, where its inputs were only the baseline and follow-up images, was trained to detect new MS lesions. Our approach obtained a mean segmentation dice similarity coefficient of 0.42 with a detection F1-score of 0.5. Compared to the challenge participants, we obtained one of the highest precision scores (PPVL = 0.52), the best PPVL rate (0.53), and a lesion detection sensitivity (SensL of 0.53).

Assessment of T2 lesion-based disease activity volume outcomes in predicting disease progression in multiple sclerosis over 10 years

BACKGROUND

New/enlarging T2 lesion count and T2-lesion volume (LV) are used as conventional secondary endpoints in clinical trials of patients with multiple sclerosis (PwMS). However, those outcomes may have several limitations, such as inability to account for heterogeneity of lesion formation/enlargement frequency and their dynamic volumetric behavior. Measurement of volume rather than count of new/enlarging lesions may be more representative outcome of dynamic changes over time.

OBJECTIVES

To investigate whether new/enlarging T2-LV is more predictive of confirmed disability progression (CDP), compared to total T2-LV or new/enlarging T2 lesion count over long-term follow-up.

METHODS

We studied 176 early relapsing-remitting PwMS who were followed with annual MRI examinations over 10 years. T2-LV, new/enlarging T2-LV, and new/enlarging lesion count were determined. Cumulative count/volumes were obtained. 10-year CDP was confirmed after 48-weeks. ANCOVA analysis detected MRI outcome differences in stable (n = 76) and CDP (n = 100) groups at different time points, after correction for multiple comparisons.

RESULTS

PwMS with CDP had greater cumulative new/enlarging T2-LV at 4 years (p = 0.049), and enlarging T2-LV at 4- (p = 0.039) and 6-year follow-up (p = 0.032), compared to stable patients. PwMS with CDP did not differ from stable ones in new/enlarging T2 lesion count or total T2-LV at any of the study timepoints. PwMS with Expanded Disability Status Scale change >2.0 had significantly greater enlarging T2 lesion count (p = 0.01) and enlarging T2-LV (p = 0.038) over the 10-year follow-up.

CONCLUSION

Enlargement of T2 lesions is more strongly associated with long-term disability progression compared to other conventional T2 lesion-based outcomes.

Multiple Sclerosis Diagnosis Using Machine Learning and Deep Learning: Challenges and Opportunities

Multiple Sclerosis (MS) is a disease that impacts the central nervous system (CNS), which can lead to brain, spinal cord, and optic nerve problems. A total of 2.8 million are estimated to suffer from MS. Globally, a new case of MS is reported every five minutes. In this review, we discuss the proposed approaches to diagnosing MS using machine learning (ML) published between 2011 and 2022. Numerous models have been developed using different types of data, including magnetic resonance imaging (MRI) and clinical data. We identified the methods that achieved the best results in diagnosing MS. The most implemented approaches are SVM, RF, and CNN. Moreover, we discussed the challenges and opportunities in MS diagnosis to improve AI systems to enable researchers and practitioners to enhance their approaches and improve the automated diagnosis of MS. The challenges faced by automated MS diagnosis include difficulty distinguishing the disease from other diseases showing similar symptoms, protecting the confidentiality of the patients' data, achieving reliable ML models that are also easily understood by non-experts, and the difficulty of collecting a large reliable dataset. Moreover, we discussed several opportunities in the field such as the implementation of secure platforms, employing better AI solutions, developing better disease prognosis systems, combining more than one data type for better MS prediction and using OCT data for diagnosis, utilizing larger, multi-center datasets to improve the reliability of the developed models, and commercialization.

Longitudinal detection of new MS lesions using deep learning

The detection of new multiple sclerosis (MS) lesions is an important marker of the evolution of the disease. The applicability of learning-based methods could automate this task efficiently. However, the lack of annotated longitudinal data with new-appearing lesions is a limiting factor for the training of robust and generalizing models. In this study, we describe a deep-learning-based pipeline addressing the challenging task of detecting and segmenting new MS lesions. First, we propose to use transfer-learning from a model trained on a segmentation task using single time-points. Therefore, we exploit knowledge from an easier task and for which more annotated datasets are available. Second, we propose a data synthesis strategy to generate realistic longitudinal time-points with new lesions using single time-point scans. In this way, we pretrain our detection model on large synthetic annotated datasets. Finally, we use a data-augmentation technique designed to simulate data diversity in MRI. By doing that, we increase the size of the available small annotated longitudinal datasets. Our ablation study showed that each contribution lead to an enhancement of the segmentation accuracy. Using the proposed pipeline, we obtained the best score for the segmentation and the detection of new MS lesions in the MSSEG2 MICCAI challenge.

Recent advances in the longitudinal segmentation of multiple sclerosis lesions on magnetic resonance imaging: a review

Multiple sclerosis (MS) is a chronic autoimmune disease characterized by demyelinating lesions that are often visible on magnetic resonance imaging (MRI). Segmentation of these lesions can provide imaging biomarkers of disease burden that can help monitor disease progression and the imaging response to treatment. Manual delineation of MRI lesions is tedious and prone to subjective bias, while automated lesion segmentation methods offer objectivity and speed, the latter being particularly important when analysing large datasets. Lesion segmentation can be broadly categorised into two groups: cross-sectional methods, which use imaging data acquired at a single time-point to characterise MRI lesions; and longitudinal methods, which use imaging data from the same subject acquired at two or more different time-points to characterise lesions over time. The main objective of longitudinal segmentation approaches is to more accurately detect the presence of new MS lesions and the growth or remission of existing lesions, which may be effective biomarkers of disease progression and treatment response. This paper reviews articles on longitudinal MS lesion segmentation methods published over the past 10 years. These are divided into traditional machine learning methods and deep learning techniques. PubMed articles using longitudinal information and comparing fully automatic two time point segmentations in any step of the process were selected. Nineteen articles were reviewed. There is an increasing number of deep learning techniques for longitudinal MS lesion segmentation that are promising to help better understand disease progression.

Clinically Deployed Computational Assessment of Multiple Sclerosis Lesions

Multiple Sclerosis (MS) is a demyelinating disease of the central nervous system that affects nearly 1 million adults in the United States. Magnetic Resonance Imaging (MRI) plays a vital role in diagnosis and treatment monitoring in MS patients. In particular, follow-up MRI with T2-FLAIR images of the brain, depicting white matter lesions, is the mainstay for monitoring disease activity and making treatment decisions. In this article, we present a computational approach that has been deployed and integrated into a real-world routine clinical workflow, focusing on two tasks: (a) detecting new disease activity in MS patients, and (b) determining the necessity for injecting Gadolinium Based Contract Agents (GBCAs). This computer-aided detection (CAD) software has been utilized for the former task on more than 19, 000 patients over the course of 10 years, while its added function of identifying patients who need GBCA injection, has been operative for the past 3 years, with > 85% sensitivity. The benefits of this approach are summarized in: (1) offering a reproducible and accurate clinical assessment of MS lesion patients, (2) reducing the adverse effects of GBCAs (and the deposition of GBCAs to the patient's brain) by identifying the patients who may benefit from injection, and (3) reducing healthcare costs, patients' discomfort, and caregivers' workload.

Assessment of automatic decision-support systems for detecting active T2 lesions in multiple sclerosis patients

BACKGROUND

Active (new/enlarging) T2 lesion counts are routinely used in the clinical management of multiple sclerosis. Thus, automated tools able to accurately identify active T2 lesions would be of high interest to neuroradiologists for assisting in their clinical activity.

OBJECTIVE

To compare the accuracy in detecting active T2 lesions and of radiologically active patients based on different visual and automated methods.

METHODS

One hundred multiple sclerosis patients underwent two magnetic resonance imaging examinations within 12 months. Four approaches were assessed for detecting active T2 lesions: (1) conventional neuroradiological reports; (2) prospective visual analyses performed by an expert; (3) automated unsupervised tool; and (4) supervised convolutional neural network. As a gold standard, a reference outcome was created by the consensus of two observers.

RESULTS

The automated methods detected a higher number of active T2 lesions, and a higher number of active patients, but a higher number of false-positive active patients than visual methods. The convolutional neural network model was more sensitive in detecting active T2 lesions and active patients than the other automated method.

CONCLUSION

Automated convolutional neural network models show potential as an aid to neuroradiological assessment in clinical practice, although visual supervision of the outcomes is still required.

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.

Safety and efficacy of tolebrutinib, an oral brain-penetrant BTK inhibitor, in relapsing multiple sclerosis: a phase 2b, randomised, double-blind, placebo-controlled trial

BACKGROUND

Tolebrutinib is an oral, CNS-penetrant, irreversible inhibitor of Bruton's tyrosine kinase, an enzyme expressed in B lymphocytes and myeloid cells including microglia, which are major drivers of inflammation in multiple sclerosis. We aimed to determine the dose-response relationship between tolebrutinib and the reduction in new active brain MRI lesions in patients with relapsing multiple sclerosis.

METHODS

We did a 16-week, phase 2b, randomised, double-blind, placebo-controlled, crossover, dose-finding trial at 40 centres (academic sites, specialty clinics, and general neurology centres) in ten countries in Europe and North America. Eligible participants were adults aged 18-55 years with diagnosed relapsing multiple sclerosis (either relapsing-remitting or relapsing secondary progressive multiple sclerosis), and one or more of the following criteria: at least one relapse within the previous year, at least two relapses within the previous 2 years, or at least one active gadolinium-enhancing brain lesion in the 6 months before screening. Exclusion criteria included a diagnosis of primary progressive multiple sclerosis or a diagnosis of secondary progressive multiple sclerosis without relapse. We used a two-step randomisation process to randomly assign eligible participants (1:1) to two cohorts, then further randomly assign participants in each cohort (1:1:1:1) to four tolebrutinib dose groups (5, 15, 30, and 60 mg administered once daily as an oral tablet). Cohort 1 received tolebrutinib for 12 weeks, then matched placebo (ie, identical looking tablets) for 4 weeks; cohort 2 received 4 weeks of placebo followed by 12 weeks of tolebrutinib. Participants and investigators were masked for dose and tolebrutinib-placebo administration sequence; investigators, study team members, and study participants did not have access to unmasked data. MRI scans were done at screening and every 4 weeks over 16 weeks. The primary efficacy endpoint was the number of new gadolinium-enhancing lesions detected on the scan done after 12 weeks of tolebrutinib treatment (assessed at week 12 for cohort 1 and week 16 for cohort 2), relative to the scan done 4 weeks previously, and compared with the lesions accumulated during 4 weeks of placebo run-in period in cohort 2. Efficacy data were analysed in a modified intention-to-treat population, using a two-step multiple comparison procedure with modelling analysis. Safety was assessed for all participants who received at least one dose of study drug. This trial is registered with ClinicalTrials.gov (NCT03889639), EudraCT (2018-003927-12), and WHO (U1111-1220-0572), and has been completed.

FINDINGS

Between May 14, 2019, and Jan 2, 2020, we enrolled and randomly assigned 130 participants to tolebrutinib: 33 to 5 mg, 32 to 15 mg, 33 to 30 mg, and 32 to 60 mg. 129 (99%) completed the treatment regimen and 126 were included in the primary analysis. At treatment week 12, there was a dose-dependent reduction in the number of new gadolinium-enhancing lesions (mean [SD] lesions per patient: placebo, 1·03 [2·50]; 5 mg, 1·39 [3·20]; 15 mg, 0·77 [1·48]; 30 mg, 0·76 [3·31]; 60 mg, 0·13 [0·43]; p=0·03). One serious adverse event was reported (one patient in the 60 mg group was admitted to hospital because of a multiple sclerosis relapse). The most common non-serious adverse event during tolebrutinib treatment was headache (in one [3%] of 33 in the 5 mg group; three [9%] of 32 in the 15 mg group; one [3%] of 33 in the 30 mg group; and four [13%] of 32 in the 60 mg group). No safety-related discontinuations or treatment-related deaths occurred.

INTERPRETATION

12 weeks of tolebrutinib treatment led to a dose-dependent reduction in new gadolinium-enhancing lesions, the 60 mg dose being the most efficacious, and the drug was well tolerated. Reduction of acute inflammation, combined with the potential to modulate the immune response within the CNS, provides a scientific rationale to pursue phase 3 clinical trials of tolebrutinib in patients with relapsing and progressive forms of multiple sclerosis.

FUNDING

Sanofi.

Automatic segmentation of gadolinium-enhancing lesions in multiple sclerosis using deep learning from clinical MRI

Gadolinium-enhancing lesions reflect active disease and are critical for in-patient monitoring in multiple sclerosis (MS). In this work, we have developed the first fully automated method to segment and count the gadolinium-enhancing lesions from routine clinical MRI of MS patients. The proposed method first segments the potential lesions using 2D-UNet from multi-channel scans (T1 post-contrast, T1 pre-contrast, FLAIR, T2, and proton-density) and classifies the lesions using a random forest classifier. The algorithm was trained and validated on 600 MRIs with manual segmentation. We compared the effect of loss functions (Dice, cross entropy, and bootstrapping cross entropy) and number of input contrasts. We compared the lesion counts with those by radiologists using 2,846 images. Dice, lesion-wise sensitivity, and false discovery rate with full 5 contrasts were 0.698, 0.844, and 0.307, which improved to 0.767, 0.969, and 0.00 in large lesions (>100 voxels). The model using bootstrapping loss function provided a statistically significant increase of 7.1% in sensitivity and of 2.3% in Dice compared with the model using cross entropy loss. T1 post/pre-contrast and FLAIR were the most important contrasts. For large lesions, the 2D-UNet model trained using T1 pre-contrast, FLAIR, T2, PD had a lesion-wise sensitivity of 0.688 and false discovery rate 0.083, even without T1 post-contrast. For counting lesions in 2846 routine MRI images, the model with 2D-UNet and random forest, which was trained with bootstrapping cross entropy, achieved accuracy of 87.7% using T1 pre-contrast, T1 post-contrast, and FLAIR when lesion counts were categorized as 0, 1, and 2 or more. The model performs well in routine non-standardized MRI datasets, allows large-scale analysis of clinical datasets, and may have clinical applications.

Current review and next steps for artificial intelligence in multiple sclerosis risk research

In the last few decades, the prevalence of multiple sclerosis (MS), a chronic inflammatory disease of the nervous system, has increased, particularly in Northern European countries, the United States, and United Kingdom. The promise of artificial intelligence (AI) and machine learning (ML) as tools to address problems in MS research has attracted increasing interest in these methods. Bayesian networks offer a clear advantage since they can integrate data and causal knowledge allowing for visualizing interactions between dependent variables and potential confounding factors. A review of AI/ML research methods applied to MS found 216 papers using terms "Multiple Sclerosis", "machine learning", "artificial intelligence", "Bayes", and "Bayesian", of which 90 were relevant and recently published. More than half of these involve the detection and segmentation of MS lesions for quantitative analysis; however clinical and lifestyle risk factor assessment and prediction have largely been ignored. Of those that address risk factors, most provide only association studies for some factors and often fail to include the potential impact of confounding factors and bias (especially where these have causal explanations) that could affect data interpretation, such as reporting quality and medical care access in various countries. To address these gaps in the literature, we propose a causal Bayesian network approach to assessing risk factors for MS, which can address deficiencies in current epidemiological methods of producing risk measurements and makes better use of observational data.

Automatic brain lesion segmentation on standard magnetic resonance images: a scoping review

OBJECTIVES

Medical image analysis practices face challenges that can potentially be addressed with algorithm-based segmentation tools. In this study, we map the field of automatic MR brain lesion segmentation to understand the clinical applicability of prevalent methods and study designs, as well as challenges and limitations in the field.

DESIGN

Scoping review.

SETTING

Three databases (PubMed, IEEE Xplore and Scopus) were searched with tailored queries. Studies were included based on predefined criteria. Emerging themes during consecutive title, abstract, methods and whole-text screening were identified. The full-text analysis focused on materials, preprocessing, performance evaluation and comparison.

RESULTS

Out of 2990 unique articles identified through the search, 441 articles met the eligibility criteria, with an estimated growth rate of 10% per year. We present a general overview and trends in the field with regard to publication sources, segmentation principles used and types of lesions. Algorithms are predominantly evaluated by measuring the agreement of segmentation results with a trusted reference. Few articles describe measures of clinical validity.

CONCLUSIONS

The observed reporting practices leave room for improvement with a view to studying replication, method comparison and clinical applicability. To promote this improvement, we propose a list of recommendations for future studies in the field.

Effects of Ibudilast on MRI Measures in the Phase 2 SPRINT-MS Study

OBJECTIVE

To determine whether ibudilast has an effect on brain volume and new lesions in progressive forms of multiple sclerosis (MS).

METHODS

A randomized, placebo-controlled, blinded study evaluated ibudilast at a dose of up to 100 mg over 96 weeks in primary and secondary progressive MS. In this secondary analysis of a previously reported trial, secondary and tertiary endpoints included gray matter atrophy, new or enlarging T2 lesions as measured every 24 weeks, and new T1 hypointensities at 96 weeks. Whole brain atrophy measured by structural image evaluation, using normalization, of atrophy (SIENA) was a sensitivity analysis.

RESULTS

A total of 129 participants were assigned to ibudilast and 126 to placebo. New or enlarging T2 lesions were observed in 37.2% on ibudilast and 29.0% on placebo (p = 0.82). New T1 hypointense lesions at 96 weeks were observed in 33.3% on ibudilast and 23.5% on placebo (p = 0.11). Gray matter atrophy was reduced by 35% for those on ibudilast vs placebo (p = 0.038). Progression of whole brain atrophy by SIENA was slowed by 20% in the ibudilast group compared with placebo (p = 0.08).

CONCLUSION

Ibudilast treatment was associated with a reduction in gray matter atrophy. Ibudilast treatment was not associated with a reduction in new or enlarging T2 lesions or new T1 lesions. An effect on brain volume contributes to prior data that ibudilast appears to affect markers associated with neurodegenerative processes, but not inflammatory processes.

CLASSIFICATION OF EVIDENCE

This study provides Class II evidence that for people with MS, ibudilast does not significantly reduce new or enlarging T2 lesions or new T1 lesions.

Fully automated longitudinal segmentation of new or enlarged multiple sclerosis lesions using 3D convolutional neural networks

•

A fully automated segmentation of new or enlarged multiple sclerosis (MS) lesions.

•

3D convolutional neural network (CNN) with U-net-like encoder-decoder architecture.

•

Simultaneous processing of baseline and follow-up scan of the same patient.

•

Trained on 3253 patient data from over 103 different MR scanners.

•

Fast (<1min), robust algorithm with segmentation results in inter-rater variability.

The quantification of new or enlarged lesions from follow-up MRI scans is an important surrogate of clinical disease activity in patients with multiple sclerosis (MS). Not only is manual segmentation time consuming, but inter-rater variability is high. Currently, only a few fully automated methods are available. We address this gap in the field by employing a 3D convolutional neural network (CNN) with encoder-decoder architecture for fully automatic longitudinal lesion segmentation.

Input data consist of two fluid attenuated inversion recovery (FLAIR) images (baseline and follow-up) per patient. Each image is entered into the encoder and the feature maps are concatenated and then fed into the decoder. The output is a 3D mask indicating new or enlarged lesions (compared to the baseline scan). The proposed method was trained on 1809 single point and 1444 longitudinal patient data sets and then validated on 185 independent longitudinal data sets from two different scanners. From the two validation data sets, manual segmentations were available from three experienced raters, respectively. The performance of the proposed method was compared to the open source Lesion Segmentation Toolbox (LST), which is a current state-of-art longitudinal lesion segmentation method.

The mean lesion-wise inter-rater sensitivity was 62%, while the mean inter-rater number of false positive (FP) findings was 0.41 lesions per case. The two validated algorithms showed a mean sensitivity of 60% (CNN), 46% (LST) and a mean FP of 0.48 (CNN), 1.86 (LST) per case. Sensitivity and number of FP were not significantly different (p < 0.05) between the CNN and manual raters.

New or enlarged lesions counted by the CNN algorithm appeared to be comparable with manual expert ratings. The proposed algorithm seems to outperform currently available approaches, particularly LST. The high inter-rater variability in case of manual segmentation indicates the complexity of identifying new or enlarged lesions. An automated CNN-based approach can quickly provide an independent and deterministic assessment of new or enlarged lesions from baseline to follow-up scans with acceptable reliability.

Evaluating White Matter Lesion Segmentations with Refined Sørensen-Dice Analysis

The Sørensen-Dice index (SDI) is a widely used measure for evaluating medical image segmentation algorithms. It offers a standardized measure of segmentation accuracy which has proven useful. However, it offers diminishing insight when the number of objects is unknown, such as in white matter lesion segmentation of multiple sclerosis (MS) patients. We present a refinement for finer grained parsing of SDI results in situations where the number of objects is unknown. We explore these ideas with two case studies showing what can be learned from our two presented studies. Our first study explores an inter-rater comparison, showing that smaller lesions cannot be reliably identified. In our second case study, we demonstrate fusing multiple MS lesion segmentation algorithms based on the insights into the algorithms provided by our analysis to generate a segmentation that exhibits improved performance. This work demonstrates the wealth of information that can be learned from refined analysis of medical image segmentations.

Pre-treatment T-cell subsets associate with fingolimod treatment responsiveness in multiple sclerosis

Biomarkers predicting fingolimod (FTY) treatment response in relapsing-remitting multiple sclerosis (RRMS) are lacking. Here, we performed extensive functional immunophenotyping using multiparametric flow cytometry to examine peripheral immune changes under FTY treatment and explore biomarkers of FTY treatment response. From among 135 RRMS patients who initiated FTY in a 2-year multicentre observational study, 36 were classified as ‘Active’ or ‘Stable’ based on clinical and/or radiological activity on-treatment. Flow cytometric analysis of immune cell subsets was performed on pre- and on-treatment peripheral blood mononuclear cells (PBMC) samples. Decreased absolute counts of B cells and most T-cell subsets were seen on-treatment. Senescent CD8 + T cells, CD56 + T cells, CD56^dim natural killer cells, monocytes and dendritic cells were not reduced in number and hence relatively increased in frequency on-treatment. An unbiased multiparametric and traditional manual analysis of T-cell subsets suggested a higher pre-treatment frequency of CD4 + central memory T cells (TCM) in patients who were subsequently Active versus Stable on-treatment. Lower pre-treatment terminally differentiated effector memory (TEMRA) cell frequencies were also seen in the subsequently Active cohort. Together, our data highlight differential effects of FTY on peripheral immune cell subsets and suggest that pre-treatment T-cell subset frequencies may have value in predicting FTY treatment response.

Improved Methods for Brain Tumor Detection and Analysis Using MR Brain Images

Medical image processing techniques play an important role in helping doctors and facilities for patient diagnosis, the aim of this paper is comparison between three improved methods to identify the brain tumor using magnetic resonance brain images and analysis of the performance of each method according to different values, accuracy, nJaccard coeff, ndice, sensitivity, specificity, recall and precision values,We used three improved methods the first method improved fuzzy c-means algorithm (IFCM), the second method is improved feed-forward neural network (IFFNN), and the third method is a hybrid self-organizing map with a fuzzy k-means algorithm,the significance of these methods is complementary among them where each one has an advantage in a certain value as shown in the paper results, the three methods gave a very good performance, generally they can identify the tumor area clearly in MR brain image with different performance of the values, each method gave better values than others according to a comparison between the performance value of three methods,Finally, the improved methods allow the development of algorithms to diagnose a tumor more accurately and for a short period of time and each method is distinguished from each other in the performance and value, this gives integrity and strength to this work, these methods can be used in pre and post radio surgical applications

A fully convolutional neural network for new T2-w lesion detection in multiple sclerosis

•

A deep learning model for new T2-w lesions detection in multiple sclerosis is presented.

•

Combining a learning-based registration network with a segmentation one increases the performance.

•

The proposed model decreases false-positives while increasing true-positives.

•

Better performance compared to other supervised and unsupervised state-of-the-art approaches.

Introduction: Longitudinal magnetic resonance imaging (MRI) has an important role in multiple sclerosis (MS) diagnosis and follow-up. Specifically, the presence of new T2-w lesions on brain MR scans is considered a predictive biomarker for the disease. In this study, we propose a fully convolutional neural network (FCNN) to detect new T2-w lesions in longitudinal brain MR images.

Methods: One year apart, multichannel brain MR scans (T1-w, T2-w, PD-w, and FLAIR) were obtained for 60 patients, 36 of them with new T2-w lesions. Modalities from both temporal points were preprocessed and linearly coregistered. Afterwards, an FCNN, whose inputs were from the baseline and follow-up images, was trained to detect new MS lesions. The first part of the network consisted of U-Net blocks that learned the deformation fields (DFs) and nonlinearly registered the baseline image to the follow-up image for each input modality. The learned DFs together with the baseline and follow-up images were then fed to the second part, another U-Net that performed the final detection and segmentation of new T2-w lesions. The model was trained end-to-end, simultaneously learning both the DFs and the new T2-w lesions, using a combined loss function. We evaluated the performance of the model following a leave-one-out cross-validation scheme.

Results: In terms of the detection of new lesions, we obtained a mean Dice similarity coefficient of 0.83 with a true positive rate of 83.09% and a false positive detection rate of 9.36%. In terms of segmentation, we obtained a mean Dice similarity coefficient of 0.55. The performance of our model was significantly better compared to the state-of-the-art methods (p < 0.05).

Conclusions: Our proposal shows the benefits of combining a learning-based registration network with a segmentation network. Compared to other methods, the proposed model decreases the number of false positives. During testing, the proposed model operates faster than the other two state-of-the-art methods based on the DF obtained by Demons.

Accuracy of Unenhanced MRI in the Detection of New Brain Lesions in Multiple Sclerosis

Background Administration of a gadolinium-based contrast material is widely considered obligatory for follow-up imaging of patients with multiple sclerosis (MS). However, advances in MRI have substantially improved the sensitivity for detecting new or enlarged lesions in MS. Purpose To investigate whether the use of contrast material has an effect on the detection of new or enlarged MS lesions and, consequently, the assessment of interval progression. Materials and Methods In this retrospective study based on a local prospective observational cohort, 507 follow-up MR images obtained in 359 patients with MS (mean age, 38.2 years ± 10.3; 246 women, 113 men) were evaluated. With use of subtraction maps, nonenhanced images (double inversion recovery [DIR], fluid-attenuated inversion recovery [FLAIR]) and contrast material-enhanced (gadoterate meglumine, 0.1 mmol/kg) T1-weighted images were separately assessed for new or enlarged lesions in independent readings by two readers blinded to each other's findings and to clinical information. Primary outcome was the percentage of new or enlarged lesions detected only on contrast-enhanced T1-weighted images and the assessment of interval progression. Interval progression was defined as at least one new or unequivocally enlarged lesion on follow-up MR images. Results Of 507 follow-up images, 264 showed interval progression, with a total of 1992 new or enlarged and 207 contrast-enhancing lesions. Four of these lesions (on three MR images) were retrospectively detected on only the nonenhanced images, corresponding to 1.9% (four of 207) of the enhancing and 0.2% (four of 1992) of all new or enlarged lesions. Nine enhancing lesions were not detected on FLAIR-based subtraction maps (nine of 1442, 0.6%). In none of the 507 images did the contrast-enhanced sequences reveal interval progression that was missed in the readouts of the nonenhanced sequences, with use of either DIR- or FLAIR-based subtraction maps. Interrater agreement was high for all three measures, with intraclass correlation coefficients of 0.91 with FLAIR, 0.94 with DIR, and 0.99 with contrast-enhanced T1-weighted imaging. Conclusion At 3.0 T, use of a gadolinium-based contrast agent at follow-up MRI did not change the diagnosis of interval disease progression in patients with multiple sclerosis. © RSNA, 2019 See also the editorial by Saindane in this issue.

Dice Overlap Measures for Objects of Unknown Number: Application to Lesion Segmentation

The Dice overlap ratio is commonly used to evaluate the performance of image segmentation algorithms. While Dice overlap is very useful as a standardized quantitative measure of segmentation accuracy in many applications, it offers a very limited picture of segmentation quality in complex segmentation tasks where the number of target objects is not known a priori, such as the segmentation of white matter lesions or lung nodules. While Dice overlap can still be used in these applications, segmentation algorithms may perform quite differently in ways not reflected by differences in their Dice score. Here we propose a new set of evaluation techniques that offer new insights into the behavior of segmentation algorithms. We illustrate these techniques with a case study comparing two popular multiple sclerosis (MS) lesion segmentation algorithms: OASIS and LesionTOADS.

A supervised framework with intensity subtraction and deformation field features for the detection of new T2-w lesions in multiple sclerosis

Introduction

Longitudinal magnetic resonance imaging (MRI) analysis has an important role in multiple sclerosis diagnosis and follow-up. The presence of new T2-w lesions on brain MRI scans is considered a prognostic and predictive biomarker for the disease. In this study, we propose a supervised approach for detecting new T2-w lesions using features from image intensities, subtraction values, and deformation fields (DF).

Methods

One year apart multi-channel brain MRI scans were obtained for 60 patients, 36 of them with new T2-w lesions. Images from both temporal points were preprocessed and co-registered. Afterwards, they were registered using multi-resolution affine registration, allowing their subtraction. In particular, the DFs between both images were computed with the Demons non-rigid registration algorithm. Afterwards, a logistic regression model was trained with features from image intensities, subtraction values, and DF operators. We evaluated the performance of the model following a leave-one-out cross-validation scheme.

Results

In terms of detection, we obtained a mean Dice similarity coefficient of 0.77 with a true-positive rate of 74.30% and a false-positive detection rate of 11.86%. In terms of segmentation, we obtained a mean Dice similarity coefficient of 0.56. The performance of our model was significantly higher than state-of-the-art methods.

Conclusions

The performance of the proposed method shows the benefits of using DF operators as features to train a supervised learning model. Compared to other methods, the proposed model decreases the number of false-positives while increasing the number of true-positives, which is relevant for clinical settings.

•

A new framework for detecting new T2-w lesions in multiple sclerosis is proposed.

•

We train logistic regression classifier with subtraction and deformation features.

•

We analyze the effect of deformation field operators on detecting new T2-w lesions.

•

We show an increase in the accuracy due to the addition of deformation fields.

•

The proposed model decreases false-positives while increasing true-positives.

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.

Longitudinal multiple sclerosis lesion segmentation: Resource and challenge

In conjunction with the ISBI 2015 conference, we organized a longitudinal lesion segmentation challenge providing training and test data to registered participants. The training data consisted of five subjects with a mean of 4.4 time-points, and test data of fourteen subjects with a mean of 4.4 time-points. All 82 data sets had the white matter lesions associated with multiple sclerosis delineated by two human expert raters. Eleven teams submitted results using state-of-the-art lesion segmentation algorithms to the challenge, with ten teams presenting their results at the conference. We present a quantitative evaluation comparing the consistency of the two raters as well as exploring the performance of the eleven submitted results in addition to three other lesion segmentation algorithms. The challenge presented three unique opportunities: (1) the sharing of a rich data set; (2) collaboration and comparison of the various avenues of research being pursued in the community; and (3) a review and refinement of the evaluation metrics currently in use. We report on the performance of the challenge participants, as well as the construction and evaluation of a consensus delineation. The image data and manual delineations will continue to be available for download, through an evaluation website2 as a resource for future researchers in the area. This data resource provides a platform to compare existing methods in a fair and consistent manner to each other and multiple manual raters.

Longitudinal segmentation of age-related white matter hyperintensities

Although white matter hyperintensities evolve in the course of ageing, few solutions exist to consider the lesion segmentation problem longitudinally. Based on an existing automatic lesion segmentation algorithm, a longitudinal extension is proposed. For evaluation purposes, a longitudinal lesion simulator is created allowing for the comparison between the longitudinal and the cross-sectional version in various situations of lesion load progression. Finally, applied to clinical data, the proposed framework demonstrates an increased robustness compared to available cross-sectional methods and findings are aligned with previously reported clinical patterns.

Two Time Point MS Lesion Segmentation in Brain MRI: An Expectation-Maximization Framework

Purpose: Lesion volume is a meaningful measure in multiple sclerosis (MS) prognosis. Manual lesion segmentation for computing volume in a single or multiple time points is time consuming and suffers from intra and inter-observer variability. Methods: In this paper, we present MSmetrix-long: a joint expectation-maximization (EM) framework for two time point white matter (WM) lesion segmentation. MSmetrix-long takes as input a 3D T1-weighted and a 3D FLAIR MR image and segments lesions in three steps: (1) cross-sectional lesion segmentation of the two time points; (2) creation of difference image, which is used to model the lesion evolution; (3) a joint EM lesion segmentation framework that uses output of step (1) and step (2) to provide the final lesion segmentation. The accuracy (Dice score) and reproducibility (absolute lesion volume difference) of MSmetrix-long is evaluated using two datasets. Results: On the first dataset, the median Dice score between MSmetrix-long and expert lesion segmentation was 0.63 and the Pearson correlation coefficient (PCC) was equal to 0.96. On the second dataset, the median absolute volume difference was 0.11 ml. Conclusions: MSmetrix-long is accurate and consistent in segmenting MS lesions. Also, MSmetrix-long compares favorably with the publicly available longitudinal MS lesion segmentation algorithm of Lesion Segmentation Toolbox.

Improved Automatic Detection of New T2 Lesions in Multiple Sclerosis Using Deformation Fields

BACKGROUND AND PURPOSE

Detection of disease activity, defined as new/enlarging T2 lesions on brain MR imaging, has been proposed as a biomarker in MS. However, detection of new/enlarging T2 lesions can be hindered by several factors that can be overcome with image subtraction. The purpose of this study was to improve automated detection of new T2 lesions and reduce user interaction to eliminate inter- and intraobserver variability.

MATERIALS AND METHODS

Multiparametric brain MR imaging was performed at 2 time points in 36 patients with new T2 lesions. Images were registered by using an affine transformation and the Demons algorithm to obtain a deformation field. After affine registration, images were subtracted and a threshold was applied to obtain a lesion mask, which was then refined by using the deformation field, intensity, and local information. This pipeline was compared with only applying a threshold, and with a state-of-the-art approach relying only on image intensities. To assess improvements, we compared the results of the different pipelines with the expert visual detection.

RESULTS

The multichannel pipeline based on the deformation field obtained a detection Dice similarity coefficient close to 0.70, with a false-positive detection of 17.8% and a true-positive detection of 70.9%. A statistically significant correlation (r = 0.81, P value = 2.2688e-09) was found between visual detection and automated detection by using our approach.

CONCLUSIONS

The deformation field-based approach proposed in this study for detecting new/enlarging T2 lesions resulted in significantly fewer false-positives while maintaining most true-positives and showed a good correlation with visual detection annotations. This approach could reduce user interaction and inter- and intraobserver variability.

Patch-Based Segmentation with Spatial Consistency: Application to MS Lesions in Brain MRI

This paper presents an automatic lesion segmentation method based on similarities between multichannel patches. A patch database is built using training images for which the label maps are known. For each patch in the testing image, k similar patches are retrieved from the database. The matching labels for these k patches are then combined to produce an initial segmentation map for the test case. Finally an iterative patch-based label refinement process based on the initial segmentation map is performed to ensure the spatial consistency of the detected lesions. The method was evaluated in experiments on multiple sclerosis (MS) lesion segmentation in magnetic resonance images (MRI) of the brain. An evaluation was done for each image in the MICCAI 2008 MS lesion segmentation challenge. Results are shown to compete with the state of the art in the challenge. We conclude that the proposed algorithm for segmentation of lesions provides a promising new approach for local segmentation and global detection in medical images.

Stratified mixture modeling for segmentation of white-matter lesions in brain MR images

Accurate characterization of white-matter lesions from magnetic resonance (MR) images has increasing importance for diagnosis and management of treatment of certain neurological diseases, and can be performed in an objective and effective way by automated lesion segmentation. This usually involves modeling the whole-brain MR intensity distribution, however, capturing various sources of MR intensity variability and lesion heterogeneity results in highly complex whole-brain MR intensity models, thus their robust estimation on a large set of MR images presents a huge challenge. We propose a novel approach employing stratified mixture modeling, where the main premise is that the otherwise complex whole-brain model can be reduced to a tractable parametric form in small brain subregions. We show on MR images of multiple sclerosis (MS) patients with different lesion loads that robust estimators enable accurate mixture modeling of MR intensity in small brain subregions even in the presence of lesions. Recombination of the mixture models across strata provided an accurate whole-brain MR intensity model. Increasing the number of subregions and, thereby, the model complexity, consistently improved the accuracy of whole-brain MR intensity modeling and segmentation of normal structures. The proposed approach was incorporated into three unsupervised lesion segmentation methods and, compared to original and three other state-of-the-art methods, the proposed modeling approach significantly improved lesion segmentation according to increased Dice similarity indices and lower number of false positives on real MR images of 30 patients with MS.

Adaptive multi-level conditional random fields for detection and segmentation of small enhanced pathology in medical images

Detection and segmentation of large structures in an image or within a region of interest have received great attention in the medical image processing domains. However, the problem of small pathology detection and segmentation still remains an unresolved challenge due to the small size of these pathologies, their low contrast and variable position, shape and texture. In many contexts, early detection of these pathologies is critical in diagnosis and assessing the outcome of treatment. In this paper, we propose a probabilistic Adaptive Multi-level Conditional Random Fields (AMCRF) with the incorporation of higher order cliques for detecting and segmenting such pathologies. In the first level of our graphical model, a voxel-based CRF is used to identify candidate lesions. In the second level, in order to further remove falsely detected regions, a new CRF is developed that incorporates higher order textural features, which are invariant to rotation and local intensity distortions. At this level, higher order textures are considered together with the voxel-wise cliques to refine boundaries and is therefore adaptive. The proposed algorithm is tested in the context of detecting enhancing Multiple Sclerosis (MS) lesions in brain MRI, where the problem is further complicated as many of the enhancing voxels are associated with normal structures (i.e. blood vessels) or noise in the MRI. The algorithm is trained and tested on large multi-center clinical trials from Relapsing-Remitting MS patients. The effect of several different parameter learning and inference techniques is further investigated. When tested on 120 cases, the proposed method reaches a lesion detection rate of 90%, with very few false positive lesion counts on average, ranging from 0.17 for very small (3-5 voxels) to 0 for very large (50+ voxels) regions. The proposed model is further tested on a very large clinical trial containing 2770 scans where a high sensitivity of 91% with an average false positive count of 0.5 is achieved. Incorporation of contextual information at different scales is also explored. Finally, superior performance is shown upon comparing with Support Vector Machine (SVM), Random Forest and variant of an MRF.

Temporal Hierarchical Adaptive Texture CRF for Automatic Detection of Gadolinium-Enhancing Multiple Sclerosis Lesions in Brain MRI

We propose a conditional random field (CRF) based classifier for segmentation of small enhanced pathologies. Specifically, we develop a temporal hierarchical adaptive texture CRF (THAT-CRF) and apply it to the challenging problem of gad enhancing lesion segmentation in brain MRI of patients with multiple sclerosis. In this context, the presence of many nonlesion enhancements (such as blood vessels) renders the problem more difficult. In addition to voxel-wise features, the framework exploits multiple higher order textures to discriminate the true lesional enhancements from the pool of other enhancements. Since lesional enhancements show more variation over time as compared to the nonlesional ones, we incorporate temporal texture analysis in order to study the textures of enhanced candidates over time. The parameters of the THAT-CRF model are learned based on 2380 scans from a multi-center clinical trial. The effect of different components of the model is extensively evaluated on 120 scans from a separate multi-center clinical trial. The incorporation of the temporal textures results in a general decrease of the false discovery rate. Specifically, THAT-CRF achieves overall sensitivity of 95% along with false discovery rate of 20% and average false positive count of 0.5 lesions per scan. The sensitivity of the temporal method to the trained time interval is further investigated on five different intervals of 69 patients. Moreover, superior performance is achieved by the reviewed labelings of our model compared to the fully manual labeling when applied to the context of separating different treatment arms in a real clinical trial.

Intensity based methods for brain MRI longitudinal registration. A study on multiple sclerosis patients

Registration is a key step in many automatic brain Magnetic Resonance Imaging (MRI) applications. In this work we focus on longitudinal registration of brain MRI for Multiple Sclerosis (MS) patients. First of all, we analyze the effect that MS lesions have on registration by synthetically eliminating some of the lesions. Our results show how a widely used method for longitudinal registration such as rigid registration is practically unconcerned by the presence of MS lesions while several non-rigid registration methods produce outputs that are significantly different. We then focus on assessing which is the best registration method for longitudinal MRI images of MS patients. In order to analyze the results obtained for all studied criteria, we use both descriptive statistics and statistical inference: one way ANOVA, pairwise t-tests and permutation tests.

A subtraction pipeline for automatic detection of new appearing multiple sclerosis lesions in longitudinal studies

INTRODUCTION

Time-series analysis of magnetic resonance images (MRI) is of great value for multiple sclerosis (MS) diagnosis and follow-up. In this paper, we present an unsupervised subtraction approach which incorporates multisequence information to deal with the detection of new MS lesions in longitudinal studies.

METHODS

The proposed pipeline for detecting new lesions consists of the following steps: skull stripping, bias field correction, histogram matching, registration, white matter masking, image subtraction, automated thresholding, and postprocessing. We also combine the results of PD-w and T2-w images to reduce false positive detections.

RESULTS

Experimental tests are performed in 20 MS patients with two temporal studies separated 12 (12M) or 48 (48M) months in time. The pipeline achieves very good performance obtaining an overall sensitivity of 0.83 and 0.77 with a false discovery rate (FDR) of 0.14 and 0.18 for the 12M and 48M datasets, respectively. The most difficult situation for the pipeline is the detection of very small lesions where the obtained sensitivity is lower and the FDR higher.

CONCLUSION

Our fully automated approach is robust and accurate, allowing detection of new appearing MS lesions. We believe that the pipeline can be applied to large collections of images and also be easily adapted to monitor other brain pathologies.