OASIS is Automated Statistical Inference for Segmentation, with applications to multiple sclerosis lesion segmentation in MRI

Investigation of an efficient multi-modal convolutional neural network for multiple sclerosis lesion detection

In this study, an automated 2D machine learning approach for fast and precise segmentation of MS lesions from multi-modal magnetic resonance images (mmMRI) is presented. The method is based on an U-Net like convolutional neural network (CNN) for automated 2D slice-based-segmentation of brain MRI volumes. The individual modalities are encoded in separate downsampling branches without weight sharing, to leverage the specific features. Skip connections input feature maps to multi-scale feature fusion (MSFF) blocks at every decoder stage of the network. Those are followed by multi-scale feature upsampling (MSFU) blocks which use the information about lesion shape and location. The CNN is evaluated on two publicly available datasets: The ISBI 2015 longitudinal MS lesion segmentation challenge dataset containing 19 subjects and the MICCAI 2016 MSSEG challenge dataset containing 15 subjects from various scanners. The proposed multi-input 2D architecture is among the top performing approaches in the ISBI challenge, to which open-access papers are available, is able to outperform state-of-the-art 3D approaches without additional post-processing, can be adapted to other scanners quickly, is robust against scanner variability and can be deployed for inference even on a standard laptop without a dedicated GPU.

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.

A dense residual U-net for multiple sclerosis lesions segmentation from multi-sequence 3D MR images

Multiple Sclerosis (MS) is an autoimmune disease that causes brain and spinal cord lesions, which magnetic resonance imaging (MRI) can detect and characterize. Recently, deep learning methods have achieved remarkable results in the automated segmentation of MS lesions from MRI data. Hence, this study proposes a novel dense residual U-Net model that combines attention gate (AG), efficient channel attention (ECA), and Atrous Spatial Pyramid Pooling (ASPP) to enhance the performance of the automatic MS lesion segmentation using 3D MRI sequences. First, convolution layers in each block of the U-Net architecture are replaced by residual blocks and connected densely. Then, AGs are exploited to capture salient features passed through the skip connections. The ECA module is appended at the end of each residual block and each downsampling block of U-Net. Later, the bottleneck of U-Net is replaced with the ASSP module to extract multi-scale contextual information. Furthermore, 3D MR images of Fluid Attenuated Inversion Recovery (FLAIR), T1-weighted (T1-w), and T2-weighted (T2-w) are exploited jointly to perform better MS lesion segmentation. The proposed model is validated on the publicly available ISBI2015 and MSSEG2016 challenge datasets. This model produced an ISBI score of 92.75, a mean Dice score of 66.88%, a mean positive predictive value (PPV) of 86.50%, and a mean lesion-wise true positive rate (LTPR) of 60.64% on the ISBI2015 testing set. Also, it achieved a mean Dice score of 67.27%, a mean PPV of 65.19%, and a mean sensitivity of 74.40% on the MSSEG2016 testing set. The results show that the proposed model performs better than the results of some experts and some of the other state-of-the-art methods realized related to this particular subject. Specifically, the best Dice score and the best LTPR are obtained on the ISBI2015 testing set by using the proposed model to segment MS lesions.

Molecular models of multiple sclerosis severity identify heterogeneity of pathogenic mechanisms

While autopsy studies identify many abnormalities in the central nervous system (CNS) of subjects dying with neurological diseases, without their quantification in living subjects across the lifespan, pathogenic processes cannot be differentiated from epiphenomena. Using machine learning (ML), we searched for likely pathogenic mechanisms of multiple sclerosis (MS). We aggregated cerebrospinal fluid (CSF) biomarkers from 1305 proteins, measured blindly in the training dataset of untreated MS patients (N = 129), into models that predict past and future speed of disability accumulation across all MS phenotypes. Healthy volunteers (N = 24) data differentiated natural aging and sex effects from MS-related mechanisms. Resulting models, validated (Rho 0.40-0.51, p < 0.0001) in an independent longitudinal cohort (N = 98), uncovered intra-individual molecular heterogeneity. While candidate pathogenic processes must be validated in successful clinical trials, measuring them in living people will enable screening drugs for desired pharmacodynamic effects. This will facilitate drug development making, it hopefully more efficient and successful.

Multiple Sclerosis Lesions Segmentation Using Attention-Based CNNs in FLAIR Images

Objective: Multiple Sclerosis (MS) is an autoimmune and demyelinating disease that leads to lesions in the central nervous system. This disease can be tracked and diagnosed using Magnetic Resonance Imaging (MRI). A multitude of multimodality automatic biomedical approaches are used to segment lesions that are not beneficial for patients in terms of cost, time, and usability. The authors of the present paper propose a method employing just one modality (FLAIR image) to segment MS lesions accurately. Methods: A patch-based Convolutional Neural Network (CNN) is designed, inspired by 3D-ResNet and spatial-channel attention module, to segment MS lesions. The proposed method consists of three stages: (1) the Contrast-Limited Adaptive Histogram Equalization (CLAHE) is applied to the original images and concatenated to the extracted edges to create 4D images; (2) the patches of size [Formula: see text] are randomly selected from the 4D images; and (3) the extracted patches are passed into an attention-based CNN which is used to segment the lesions. Finally, the proposed method was compared to previous studies of the same dataset. Results: The current study evaluates the model with a test set of ISIB challenge data. Experimental results illustrate that the proposed approach significantly surpasses existing methods of Dice similarity and Absolute Volume Difference while the proposed method uses just one modality (FLAIR) to segment the lesions. Conclusion: The authors have introduced an automated approach to segment the lesions, which is based on, at most, two modalities as an input. The proposed architecture comprises convolution, deconvolution, and an SCA-VoxRes module as an attention module. The results show, that the proposed method outperforms well compared to other methods.

The Effect of Training Sample Size on the Prediction of White Matter Hyperintensity Volume in a Healthy Population Using BIANCA

Introduction: White matter hyperintensities of presumed vascular origin (WMH) are an important magnetic resonance imaging marker of cerebral small vessel disease and are associated with cognitive decline, stroke, and mortality. Their relevance in healthy individuals, however, is less clear. This is partly due to the methodological challenge of accurately measuring rare and small WMH with automated segmentation programs. In this study, we tested whether WMH volumetry with FMRIB software library v6.0 (FSL; https://fsl.fmrib.ox.ac.uk/fsl/fslwiki) Brain Intensity AbNormality Classification Algorithm (BIANCA), a customizable and trainable algorithm that quantifies WMH volume based on individual data training sets, can be optimized for a normal aging population.

Methods: We evaluated the effect of varying training sample sizes on the accuracy and the robustness of the predicted white matter hyperintensity volume in a population (n = 201) with a low prevalence of confluent WMH and a substantial proportion of participants without WMH. BIANCA was trained with seven different sample sizes between 10 and 40 with increments of 5. For each sample size, 100 random samples of T1w and FLAIR images were drawn and trained with manually delineated masks. For validation, we defined an internal and external validation set and compared the mean absolute error, resulting from the difference between manually delineated and predicted WMH volumes for each set. For spatial overlap, we calculated the Dice similarity index (SI) for the external validation cohort.

Results: The study population had a median WMH volume of 0.34 ml (IQR of 1.6 ml) and included n = 28 (18%) participants without any WMH. The mean absolute error of the difference between BIANCA prediction and manually delineated masks was minimized and became more robust with an increasing number of training participants. The lowest mean absolute error of 0.05 ml (SD of 0.24 ml) was identified in the external validation set with a training sample size of 35. Compared to the volumetric overlap, the spatial overlap was poor with an average Dice similarity index of 0.14 (SD 0.16) in the external cohort, driven by subjects with very low lesion volumes.

Discussion: We found that the performance of BIANCA, particularly the robustness of predictions, could be optimized for use in populations with a low WMH load by enlargement of the training sample size. Further work is needed to evaluate and potentially improve the prediction accuracy for low lesion volumes. These findings are important for current and future population-based studies with the majority of participants being normal aging people.

Evaluation of Ultrafast Wave-Controlled Aliasing in Parallel Imaging 3D-FLAIR in the Visualization and Volumetric Estimation of Cerebral White Matter Lesions

BACKGROUND AND PURPOSE

Our aim was to evaluate an ultrafast 3D-FLAIR sequence using Wave-controlled aliasing in parallel imaging encoding (Wave-FLAIR) compared with standard 3D-FLAIR in the visualization and volumetric estimation of cerebral white matter lesions in a clinical setting.

MATERIALS AND METHODS

Forty-two consecutive patients underwent 3T brain MR imaging, including standard 3D-FLAIR (acceleration factor = 2, scan time = 7 minutes 50 seconds) and resolution-matched ultrafast Wave-FLAIR sequences (acceleration factor  = 6, scan time = 2 minutes 45 seconds for the 20-channel coil; acceleration factor = 9, scan time  = 1 minute 50 seconds for the 32-channel coil) as part of clinical evaluation for demyelinating disease. Automated segmentation of cerebral white matter lesions was performed using the Lesion Segmentation Tool in SPM. Student t tests, intraclass correlation coefficients, relative lesion volume difference, and Dice similarity coefficients were used to compare volumetric measurements among sequences. Two blinded neuroradiologists evaluated the visualization of white matter lesions, artifacts, and overall diagnostic quality using a predefined 5-point scale.

RESULTS

Standard and Wave-FLAIR sequences showed excellent agreement of lesion volumes with an intraclass correlation coefficient of 0.99 and mean Dice similarity coefficient of 0.97 (SD, 0.05) (range, 0.84-0.99). Wave-FLAIR was noninferior to standard FLAIR for visualization of lesions and motion. The diagnostic quality for Wave-FLAIR was slightly greater than for standard FLAIR for infratentorial lesions (P < .001), and there were fewer pulsation artifacts on Wave-FLAIR compared with standard FLAIR (P < .001).

CONCLUSIONS

Ultrafast Wave-FLAIR provides superior visualization of infratentorial lesions while preserving overall diagnostic quality and yields white matter lesion volumes comparable with those estimated using standard FLAIR. The availability of ultrafast Wave-FLAIR may facilitate the greater use of 3D-FLAIR sequences in the evaluation of patients with suspected demyelinating disease.

Smartphone-based symbol-digit modalities test reliably captures brain damage in multiple sclerosis

As the burden of neurodegenerative diseases increases, time-limited clinic encounters do not allow quantification of complex neurological functions. Patient-collected digital biomarkers may remedy this, if they provide reliable information. However, psychometric properties of digital tools remain largely un-assessed. We developed a smartphone adaptation of the cognitive test, the Symbol-Digit Modalities Test (SDMT) by randomizing the test’s symbol-number codes and testing sequences. The smartphone SDMT showed comparable psychometric properties in 154 multiple sclerosis (MS) patients and 39 healthy volunteers (HV). E.g., smartphone SDMT achieved slightly higher correlations with cognitive subscores of neurological examinations and with brain injury measured by MRI (R² = 0.75, Rho = 0.83, p < 0.0001) than traditional SDMT. Mathematical adjustment for motoric disability of the dominant hand, measured by another smartphone test, compensates for the disadvantage of touch-based test. Averaging granular home measurements of the digital biomarker also increases accuracy of identifying true neurological decline.

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.

Automatic segmentation of white matter hyperintensities from brain magnetic resonance images in the era of deep learning and big data - A systematic review

BACKGROUND

White matter hyperintensities (WMH), of presumed vascular origin, are visible and quantifiable neuroradiological markers of brain parenchymal change. These changes may range from damage secondary to inflammation and other neurological conditions, through to healthy ageing. Fully automatic WMH quantification methods are promising, but still, traditional semi-automatic methods seem to be preferred in clinical research. We systematically reviewed the literature for fully automatic methods developed in the last five years, to assess what are considered state-of-the-art techniques, as well as trends in the analysis of WMH of presumed vascular origin.

METHOD

We registered the systematic review protocol with the International Prospective Register of Systematic Reviews (PROSPERO), registration number - CRD42019132200. We conducted the search for fully automatic methods developed from 2015 to July 2020 on Medline, Science direct, IEE Explore, and Web of Science. We assessed risk of bias and applicability of the studies using QUADAS 2.

RESULTS

The search yielded 2327 papers after removing 104 duplicates. After screening titles, abstracts and full text, 37 were selected for detailed analysis. Of these, 16 proposed a supervised segmentation method, 10 proposed an unsupervised segmentation method, and 11 proposed a deep learning segmentation method. Average DSC values ranged from 0.538 to 0.91, being the highest value obtained from an unsupervised segmentation method. Only four studies validated their method in longitudinal samples, and eight performed an additional validation using clinical parameters. Only 8/37 studies made available their methods in public repositories.

CONCLUSIONS

We found no evidence that favours deep learning methods over the more established k-NN, linear regression and unsupervised methods in this task. Data and code availability, bias in study design and ground truth generation influence the wider validation and applicability of these methods in clinical research.

Experimental design and sample size considerations in longitudinal magnetic resonance imaging-based biomarker detection for multiple sclerosis

Several modeling approaches have been developed to quantify differences in multiple sclerosis lesion evolution on magnetic resonance imaging to identify the effect of treatment on disease progression. These studies have limited clinical applicability due to onerous scan frequency and lengthy study duration. Efficient methods are needed to reduce the required sample size, study duration, and sampling frequency in longitudinal magnetic resonance imaging studies. We develop a data-driven approach to identify parameters of study design for evaluation of longitudinal magnetic resonance imaging biomarkers of multiple sclerosis lesion evolution. Our design strategies are considerably shorter than those described in previous studies, thus having the potential to lower costs of clinical trials. From a dataset of 36 multiple sclerosis patients with at least six monthly magnetic resonance imagings, we extracted new lesions and performed principal component analysis to estimate a biomarker that recapitulated lesion recovery. We tested the effect of multiple sclerosis disease modifying therapy on the lesion evolution index in three experimental designs and calculated sample sizes needed to appropriately power studies. Our proposed methods can be used to calculate required sample size and scan frequency in observational studies of multiple sclerosis disease progression as well as in designing clinical trials to find effects of treatment on multiple sclerosis lesion evolution.

Intensity warping for multisite MRI harmonization

In multisite neuroimaging studies there is often unwanted technical variation across scanners and sites. These "scanner effects" can hinder detection of biological features of interest, produce inconsistent results, and lead to spurious associations. We propose mica (multisite image harmonization by cumulative distribution function alignment), a tool to harmonize images taken on different scanners by identifying and removing within-subject scanner effects. Our goals in the present study were to (1) establish a method that removes scanner effects by leveraging multiple scans collected on the same subject, and, building on this, (2) develop a technique to quantify scanner effects in large multisite studies so these can be reduced as a preprocessing step. We illustrate scanner effects in a brain MRI study in which the same subject was measured twice on seven scanners, and assess our method's performance in a second study in which ten subjects were scanned on two machines. We found that unharmonized images were highly variable across site and scanner type, and our method effectively removed this variability by aligning intensity distributions. We further studied the ability to predict image harmonization results for a scan taken on an existing subject at a new site using cross-validation.

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.

TAPAS: A Thresholding Approach for Probability Map Automatic Segmentation in Multiple Sclerosis

Total brain white matter lesion (WML) volume is the most widely established magnetic resonance imaging (MRI) outcome measure in studies of multiple sclerosis (MS). To estimate WML volume, there are a number of automatic segmentation methods available, yet manual delineation remains the gold standard approach. Automatic approaches often yield a probability map to which a threshold is applied to create lesion segmentation masks. Unfortunately, few approaches systematically determine the threshold employed; many methods use a manually selected threshold, thus introducing human error and bias into the automated procedure. In this study, we propose and validate an automatic thresholding algorithm, Thresholding Approach for Probability Map Automatic Segmentation in Multiple Sclerosis (TAPAS), to obtain subject-specific threshold estimates for probability map automatic segmentation of T2-weighted (T2) hyperintense WMLs. Using multimodal MRI, the proposed method applies an automatic segmentation algorithm to obtain probability maps. We obtain the true subject-specific threshold that maximizes the Sørensen-Dice similarity coefficient (DSC). Then the subject-specific thresholds are modeled on a naive estimate of volume using a generalized additive model. Applying this model, we predict a subject-specific threshold in data not used for training. We ran a Monte Carlo-resampled split-sample cross-validation (100 validation sets) using two data sets: the first obtained from the Johns Hopkins Hospital (JHH) on a Philips 3 Tesla (3T) scanner (n = 94) and a second collected at the Brigham and Women's Hospital (BWH) using a Siemens 3T scanner (n = 40). By means of the proposed automated technique, in the JHH data we found an average reduction in subject-level absolute error of 0.1 mL per one mL increase in manual volume. Using Bland-Altman analysis, we found that volumetric bias associated with group-level thresholding was mitigated when applying TAPAS. The BWH data showed similar absolute error estimates using group-level thresholding or TAPAS likely since Bland-Altman analyses indicated no systematic biases associated with group or TAPAS volume estimates. The current study presents the first validated fully automated method for subject-specific threshold prediction to segment brain lesions.

Matrix decomposition for modeling lesion development processes in multiple sclerosis

Our main goal is to study and quantify the evolution of multiple sclerosis lesions observed longitudinally over many years in multi-sequence structural magnetic resonance imaging (sMRI). To achieve that, we propose a class of functional models for capturing the temporal dynamics and spatial distribution of the voxel-specific intensity trajectories in all sMRI sequences. To accommodate the hierarchical data structure (observations nested within voxels, which are nested within lesions, which, in turn, are nested within study participants), we use structured functional principal component analysis. We propose and evaluate the finite sample properties of hypothesis tests of therapeutic intervention effects on lesion evolution while accounting for the multilevel structure of the data. Using this novel testing strategy, we found statistically significant differences in lesion evolution between treatment groups.

Automated volumetric assessment with artificial neural networks might enable a more accurate assessment of disease burden in patients with multiple sclerosis

OBJECTIVES

Patients with multiple sclerosis (MS) regularly undergo MRI for assessment of disease burden. However, interpretation may be time consuming and prone to intra- and interobserver variability. Here, we evaluate the potential of artificial neural networks (ANN) for automated volumetric assessment of MS disease burden and activity on MRI.

METHODS

A single-institutional dataset with 334 MS patients (334 MRI exams) was used to develop and train an ANN for automated identification and volumetric segmentation of T2/FLAIR-hyperintense and contrast-enhancing (CE) lesions. Independent testing was performed in a single-institutional longitudinal dataset with 82 patients (266 MRI exams). We evaluated lesion detection performance (F1 scores), lesion segmentation agreement (DICE coefficients), and lesion volume agreement (concordance correlation coefficients [CCC]). Independent evaluation was performed on the public ISBI-2015 challenge dataset.

RESULTS

The F1 score was maximized in the training set at a detection threshold of 7 mm³ for T2/FLAIR lesions and 14 mm³ for CE lesions. In the training set, mean F1 scores were 0.867 for T2/FLAIR lesions and 0.636 for CE lesions, as compared to 0.878 for T2/FLAIR lesions and 0.715 for CE lesions in the test set. Using these thresholds, the ANN yielded mean DICE coefficients of 0.834 and 0.878 for segmentation of T2/FLAIR and CE lesions in the training set (fivefold cross-validation). Corresponding DICE coefficients in the test set were 0.846 for T2/FLAIR lesions and 0.908 for CE lesions, and the CCC was ≥ 0.960 in each dataset.

CONCLUSIONS

Our results highlight the capability of ANN for quantitative state-of-the-art assessment of volumetric lesion load on MRI and potentially enable a more accurate assessment of disease burden in patients with MS.

KEY POINTS

• Artificial neural networks (ANN) can accurately detect and segment both T2/FLAIR and contrast-enhancing MS lesions in MRI data. • Performance of the ANN was consistent in a clinically derived dataset, with patients presenting all possible disease stages in MRI scans acquired from standard clinical routine rather than with high-quality research sequences. • Computer-aided evaluation of MS with ANN could streamline both clinical and research procedures in the volumetric assessment of MS disease burden as well as in lesion detection.

An improved algorithm of white matter hyperintensity detection in elderly adults

•

OASIS-AD is a method for automatic segmentation of white matter hyperintensities in older adults using structural brain MRIs.

•

OASIS-AD is an approach evolved from OASIS, which was developed for automatic lesion segmentation in multiple sclerosis.

•

OASIS-AD is a major refinement of OASIS that takes into account the specific challenges raised by white matter hyperintensities in Alzheimer’s disease.

•

OASIS-AD combines three processing steps: 1) using an eroding procedure on the skull stripped mask; 2) adding a nearest neighbor feature construction approach; and 3) applying a Gaussian filter to refine segmentation results creating a novel process for WMH detection in aging population .

•

OASIS-AD performs better than existing automatic white matter hyperintensity segmentation approaches.

Automated segmentation of the aging brain raises significant challenges because of the prevalence, extent, and heterogeneity of white matter hyperintensities. White matter hyperintensities can be frequently identified in magnetic resonance imaging (MRI) scans of older individuals and among those who have Alzheimer’s disease. We propose OASIS-AD, a method for automatic segmentation of white matter hyperintensities in older adults using structural brain MRIs. OASIS-AD is an approach evolved from OASIS, which was developed for automatic lesion segmentation in multiple sclerosis. OASIS-AD is a major refinement of OASIS that takes into account the specific challenges raised by white matter hyperintensities in Alzheimer’s disease. In particular, OASIS-AD combines three processing steps: 1) using an eroding procedure on the skull stripped mask; 2) adding a nearest neighbor feature construction approach; and 3) applying a Gaussian filter to refine segmentation results, creating a novel process for WMH detection in aging population. We show that OASIS-AD performs better than existing automatic white matter hyperintensity segmentation approaches.

Neuroconductor: an R platform for medical imaging analysis

Neuroconductor (https://neuroconductor.org) is an open-source platform for rapid testing and dissemination of reproducible computational imaging software. The goals of the project are to: (i) provide a centralized repository of R software dedicated to image analysis, (ii) disseminate software updates quickly, (iii) train a large, diverse community of scientists using detailed tutorials and short courses, (iv) increase software quality via automatic and manual quality controls, and (v) promote reproducibility of image data analysis. Based on the programming language R (https://www.r-project.org/), Neuroconductor starts with 51 inter-operable packages that cover multiple areas of imaging including visualization, data processing and storage, and statistical inference. Neuroconductor accepts new R package submissions, which are subject to a formal review and continuous automated testing. We provide a description of the purpose of Neuroconductor and the user and developer experience.

FLAIR2 improves LesionTOADS automatic segmentation of multiple sclerosis lesions in non-homogenized, multi-center, 2D clinical magnetic resonance images

Background

Accurate segmentation of MS lesions on MRI is difficult and, if performed manually, time consuming. Automatic segmentations rely strongly on the image contrast and signal-to-noise ratio. Literature examining segmentation tool performances in real-world multi-site data acquisition settings is scarce.

Objective

FLAIR², a combination of T₂-weighted and fluid attenuated inversion recovery (FLAIR) images, improves tissue contrast while suppressing CSF. We compared the use of FLAIR and FLAIR² in LesionTOADS, OASIS and the lesion segmentation toolbox (LST) when applied to non-homogenized, multi-center 2D-imaging data.

Methods

Lesions were segmented on 47 MS patient data sets obtained from 34 sites using LesionTOADS, OASIS and LST, and compared to a semi-automatically generated reference. The performance of FLAIR and FLAIR² was assessed using the relative lesion volume difference (LVD), Dice coefficient (DSC), sensitivity (SEN) and symmetric surface distance (SSD). Performance improvements related to lesion volumes (LVs) were evaluated for all tools. For comparison, LesionTOADS was also used to segment lesions from 3 T single-center MR data of 40 clinically isolated syndrome (CIS) patients.

Results

Compared to FLAIR, the use of FLAIR² in LesionTOADS led to improvements of 31.6% (LVD), 14.0% (DSC), 25.1% (SEN), and 47.0% (SSD) in the multi-center study. DSC and SSD significantly improved for larger LVs, while LVD and SEN were enhanced independent of LV. OASIS showed little difference between FLAIR and FLAIR², likely due to its inherent use of T₂w and FLAIR. LST replicated the benefits of FLAIR² only in part, indicating that further optimization, particularly at low LVs is needed. In the CIS study, LesionTOADS did not benefit from the use of FLAIR² as the segmentation performance for both FLAIR and FLAIR² was heterogeneous.

Conclusions

In this real-world, multi-center experiment, FLAIR² outperformed FLAIR in its ability to segment MS lesions with LesionTOADS. The computation of FLAIR² enhanced lesion detection, at minimally increased computational time or cost, even retrospectively. Further work is needed to determine how LesionTOADS and other tools, such as LST, can optimally benefit from the improved FLAIR² contrast.

•

FLAIR² improves automatic MS lesion segmentation with LesionTOADS compared to FLAIR.

•

Segmentation similarity improves for higher lesion volumes, particularly for FLAIR².

•

FLAIR² provides greater sensitivity independent of lesion volume than FLAIR alone.

•

Other segmentation tools need further optimization to fully benefit from FLAIR².

•

FLAIR² provides immediate benefits at 1.5 T and visually improves segmentation at 3 T.

Robust, atlas-free, automatic segmentation of brain MRI in health and disease

Background

Brain- and lesion-volumes derived from magnetic resonance images (MRI) serve as important imaging markers of disease progression in neurodegenerative diseases and aging. While manual segmentation of these volumes is both tedious and impractical in large cohorts of subjects, automated segmentation methods often fail in accurate segmentation of brains with severe atrophy or high lesion loads. The purpose of this study was to develop an atlas-free brain Classification using DErivative-based Features (C-DEF), which utilizes all scans that may be acquired during the course of a routine MRI study at any center.

Methods

Proton-density, T₂-weighted, T₁-weighted, brain-free water, 3D FLAIR, 3D T₂-weighted, and 3D T₂*-weighted images, collected routinely on patients with neuroinflammatory diseases at the NIH, were used to optimize the C-DEF algorithm on healthy volunteers and HIV + subjects (cohort 1). First, manually marked lesions and eroded FreeSurfer brain segmentation masks (compiled into gray and white matter, globus pallidus, CSF labels) were used in training. Next, the optimized C-DEF was applied on a separate cohort of HIV + subjects (cohort two), and the results were compared with that of FreeSurfer and Lesion-TOADS. Finally, C-DEF segmentation was evaluated on subjects clinically diagnosed with various other neurological diseases (cohort three).

Results

C-DEF algorithm was optimized using leave-one-out cross validation on five healthy subjects (age 36 ± 11 years), and five subjects infected with HIV (age 57 ± 2.6 years) in cohort one. The optimized C-DEF algorithm outperformed FreeSurfer and Lesion-TOADS segmentation in 49 other subjects infected with HIV (cohort two, age 54 ± 6 years) in qualitative and quantitative comparisons. Although trained only on HIV brains, sensitivity to detect lesions using C-DEF increased by 45% in HTLV-I-associated myelopathy/tropical spastic paraparesis (n = 5; age 58 ± 7 years), 33% in multiple sclerosis (n = 5; 42 ± 9 years old), and 4% in subjects with polymorphism of the cytotoxic T-lymphocyte-associated protein 4 gene (n = 5; age 24 ± 12 years) compared to Lesion-TOADS.

Conclusion

C-DEF outperformed other segmentation algorithms in the various neurological diseases explored herein, especially in lesion segmentation. While the results reported are from routine images acquired at the NIH, the algorithm can be easily trained and optimized for any set of contrasts and protocols for wider application. We are currently exploring various technical aspects of optimal implementation of CDEF in a clinical setting and evaluating a larger cohort of patients with other neurological diseases. Improving the accuracy of brain segmentation methodology will help better understand the relationship of imaging abnormalities to clinical and neuropsychological markers in disease.

A dual modeling approach to automatic segmentation of cerebral T2 hyperintensities and T1 black holes in multiple sclerosis

BACKGROUND AND PURPOSE

Magnetic resonance imaging (MRI) is crucial for in vivo detection and characterization of white matter lesions (WML) in multiple sclerosis (MS). The most widely established MRI outcome measure is the volume of hyperintense lesions on T2-weighted images (T2L). Unfortunately, T2L are non-specific for the level of tissue destruction and show a weak relationship to clinical status. Interest in lesions that appear hypointense on T1-weighted images (T1L) ("black holes") has grown because T1L provide more specificity for axonal loss and a closer link to neurologic disability. The technical difficulty of T1L segmentation has led investigators to rely on time-consuming manual assessments prone to inter- and intra-rater variability. This study aims to develop an automatic T1L segmentation approach, adapted from a T2L segmentation algorithm.

MATERIALS AND METHODS

T1, T2, and fluid-attenuated inversion recovery (FLAIR) sequences were acquired from 40 MS subjects at 3 Tesla (3 T). T2L and T1L were manually segmented. A Method for Inter-Modal Segmentation Analysis (MIMoSA) was then employed.

RESULTS

Using cross-validation, MIMoSA proved to be robust for segmenting both T2L and T1L. For T2L, a Sørensen-Dice coefficient (DSC) of 0.66 and partial AUC (pAUC) up to 1% false positive rate of 0.70 were achieved. For T1L, 0.53 DSC and 0.64 pAUC were achieved. Manual and MIMoSA segmented volumes were correlated and resulted in 0.88 for T1L and 0.95 for T2L. The correlation between Expanded Disability Status Scale (EDSS) scores and manual versus automatic volumes were similar for T1L (0.32 manual vs. 0.34 MIMoSA), T2L (0.33 vs. 0.32), and the T1L/T2L ratio (0.33 vs 0.33).

CONCLUSIONS

Though originally designed to segment T2L, MIMoSA performs well for segmenting T1 black holes in patients with MS.

Automated Integration of Multimodal MRI for the Probabilistic Detection of the Central Vein Sign in White Matter Lesions

BACKGROUND AND PURPOSE

The central vein sign is a promising MR imaging diagnostic biomarker for multiple sclerosis. Recent studies have demonstrated that patients with MS have higher proportions of white matter lesions with the central vein sign compared with those with diseases that mimic MS on MR imaging. However, the clinical application of the central vein sign as a biomarker is limited by interrater differences in the adjudication of the central vein sign as well as the time burden required for the determination of the central vein sign for each lesion in a patient's full MR imaging scan. In this study, we present an automated technique for the detection of the central vein sign in white matter lesions.

MATERIALS AND METHODS

Using multimodal MR imaging, the proposed method derives a central vein sign probability, π_ij, for each lesion, as well as a patient-level central vein sign biomarker, ψ_i. The method is probabilistic in nature, allows site-specific lesion segmentation methods, and is potentially robust to intersite variability. The proposed algorithm was tested on imaging acquired at the University of Vermont in 16 participants who have MS and 15 participants who do not.

RESULTS

By means of the proposed automated technique, participants with MS were found to have significantly higher values of ψ than those without MS (ψ_MS = 0.55 ± 0.18; ψ_non-MS = 0.31 ± 0.12; P < .001). The algorithm was also found to show strong discriminative ability between patients with and without MS, with an area under the curve of 0.88.

CONCLUSIONS

The current study presents the first fully automated method for detecting the central vein sign in white matter lesions and demonstrates promising performance in a sample of patients with and without MS.

Voxel-Wise Logistic Regression and Leave-One-Source-Out Cross Validation for white matter hyperintensity segmentation

Many algorithms have been proposed for automated segmentation of white matter hyperintensities (WMH) in brain MRI. Yet, broad uptake of any particular algorithm has not been observed. In this work, we argue that this may be due to variable and suboptimal validation data and frameworks, precluding direct comparison of methods on heterogeneous data. As a solution, we present Leave-One-Source-Out Cross Validation (LOSO-CV), which leverages all available data for performance estimation, and show that this gives more realistic (lower) estimates of segmentation algorithm performance on data from different scanners. We also develop a FLAIR-only WMH segmentation algorithm: Voxel-Wise Logistic Regression (VLR), inspired by the open-source Lesion Prediction Algorithm (LPA). Our variant facilitates more accurate parameter estimation, and permits intuitive interpretation of model parameters. We illustrate the performance of the VLR algorithm using the LOSO-CV framework with a dataset comprising freely available data from several recent competitions (96 images from 7 scanners). The performance of the VLR algorithm (median Similarity Index of 0.69) is compared to its LPA predecessor (0.58), and the results of the VLR algorithm in the 2017 WMH Segmentation Competition are also presented.

Improved Automatic Segmentation of White Matter Hyperintensities in MRI Based on Multilevel Lesion Features

Brain white matter hyperintensities (WMHs) are linked to increased risk of cerebrovascular and neurodegenerative diseases among the elderly. Consequently, detection and characterization of WMHs are of significant clinical importance. We propose a novel approach for WMH segmentation from multi-contrast MRI where both voxel-based and lesion-based information are used to improve overall performance in both volume-oriented and object-oriented metrics. Our segmentation method (AMOS-2D) consists of four stages following a "generate-and-test" approach: pre-processing, Gaussian white matter (WM) modelling, hierarchical multi-threshold WMH segmentation and object-based WMH filtering using support vector machines. Data from 28 subjects was used in this study covering a wide range of lesion loads. Volumetric T1-weighted images and 2D fluid attenuated inversion recovery (FLAIR) images were used as basis for the WM model and lesion masks defined manually in each subject by experts were used for training and evaluating the proposed method. The method obtained an average agreement (in terms of the Dice similarity coefficient, DSC) with experts equivalent to inter-expert agreement both in terms of WMH number (DSC = 0.637 vs. 0.651) and volume (DSC = 0.743 vs. 0.781). It allowed higher accuracy in detecting WMH compared to alternative methods tested and was further found to be insensitive to WMH lesion burden. Good agreement with expert annotations combined with stable performance largely independent of lesion burden suggests that AMOS-2D will be a valuable tool for fully automated WMH segmentation in patients with cerebrovascular and neurodegenerative pathologies.

An Automated Statistical Technique for Counting Distinct Multiple Sclerosis Lesions

BACKGROUND AND PURPOSE

Lesion load is a common biomarker in multiple sclerosis, yet it has historically shown modest association with clinical outcome. Lesion count, which encapsulates the natural history of lesion formation and is thought to provide complementary information, is difficult to assess in patients with confluent (ie, spatially overlapping) lesions. We introduce a statistical technique for cross-sectionally counting pathologically distinct lesions.

MATERIALS AND METHODS

MR imaging was used to assess the probability of a lesion at each location. The texture of this map was quantified using a novel technique, and clusters resembling the center of a lesion were counted. Validity compared with a criterion standard count was demonstrated in 60 subjects observed longitudinally, and reliability was determined using 14 scans of a clinically stable subject acquired at 7 sites.

RESULTS

The proposed count and the criterion standard count were highly correlated (r = 0.97, P < .001) and not significantly different (t₅₉ = -.83, P = .41), and the variability of the proposed count across repeat scans was equivalent to that of lesion load. After accounting for lesion load and age, lesion count was negatively associated (t₅₈ = -2.73, P < .01) with the Expanded Disability Status Scale. Average lesion size had a higher association with the Expanded Disability Status Scale (r = 0.35, P < .01) than lesion load (r = 0.10, P = .44) or lesion count (r = -.12, P = .36) alone.

CONCLUSIONS

This study introduces a novel technique for counting pathologically distinct lesions using cross-sectional data and demonstrates its ability to recover obscured longitudinal information. The proposed count allows more accurate estimation of lesion size, which correlated more closely with disability scores than either lesion load or lesion count alone.

MIMoSA: An Automated Method for Intermodal Segmentation Analysis of Multiple Sclerosis Brain Lesions

BACKGROUND AND PURPOSE

Magnetic resonance imaging (MRI) is crucial for in vivo detection and characterization of white matter lesions (WMLs) in multiple sclerosis. While WMLs have been studied for over two decades using MRI, automated segmentation remains challenging. Although the majority of statistical techniques for the automated segmentation of WMLs are based on single imaging modalities, recent advances have used multimodal techniques for identifying WMLs. Complementary modalities emphasize different tissue properties, which help identify interrelated features of lesions.

METHODS

Method for Inter-Modal Segmentation Analysis (MIMoSA), a fully automatic lesion segmentation algorithm that utilizes novel covariance features from intermodal coupling regression in addition to mean structure to model the probability lesion is contained in each voxel, is proposed. MIMoSA was validated by comparison with both expert manual and other automated segmentation methods in two datasets. The first included 98 subjects imaged at Johns Hopkins Hospital in which bootstrap cross-validation was used to compare the performance of MIMoSA against OASIS and LesionTOADS, two popular automatic segmentation approaches. For a secondary validation, a publicly available data from a segmentation challenge were used for performance benchmarking.

RESULTS

In the Johns Hopkins study, MIMoSA yielded average Sørensen-Dice coefficient (DSC) of .57 and partial AUC of .68 calculated with false positive rates up to 1%. This was superior to performance using OASIS and LesionTOADS. The proposed method also performed competitively in the segmentation challenge dataset.

CONCLUSION

MIMoSA resulted in statistically significant improvements in lesion segmentation performance compared with LesionTOADS and OASIS, and performed competitively in an additional validation study.

Partial volume-aware assessment of multiple sclerosis lesions

White-matter lesion count and volume estimation are key to the diagnosis and monitoring of multiple sclerosis (MS). Automated MS lesion segmentation methods that have been proposed in the past 20 years reach their limits when applied to patients in early disease stages characterized by low lesion load and small lesions. We propose an algorithm to automatically assess MS lesion load (number and volume) while taking into account the mixing of healthy and lesional tissue in the image voxels due to partial volume effects. The proposed method works on 3D MPRAGE and 3D FLAIR images as obtained from current routine MS clinical protocols. The method was evaluated and compared with manual segmentation on a cohort of 39 early-stage MS patients with low disability, and showed higher Dice similarity coefficients (median DSC = 0.55) and higher detection rate (median DR = 61%) than two widely used methods (median DSC = 0.50, median DR < 45%) for automated MS lesion segmentation. We argue that this is due to the higher performance in segmentation of small lesions, which are inherently prone to partial volume effects.

•

Modeling the partial volume improves lesion volumetric measurements.

•

Higher detection of small lesions inherently prone to partial volume effects.

•

Partial volume effects should be taken into account in early stages of MS.

Joint Intensity Fusion Image Synthesis Applied to Multiple Sclerosis Lesion Segmentation

We propose a new approach to Multiple Sclerosis lesion segmentation that utilizes synthesized images. A new method of image synthesis is considered: joint intensity fusion (JIF). JIF synthesizes an image from a library of deformably registered and intensity normalized atlases. Each location in the synthesized image is a weighted average of the registered atlases; atlas weights vary spatially. The weights are determined using the joint label fusion (JLF) framework. The primary methodological contribution is the application of JLF to MRI signal directly rather than labels. Synthesized images are then used as additional features in a lesion segmentation task using the OASIS classifier, a logistic regression model on intensities from multiple modalities. The addition of JIF synthesized images improved the Dice-Sorensen coefficient (relative to manually drawn gold standards) of lesion segmentations over the standard model segmentations by 0.0462 ± 0.0050 (mean ± standard deviation) at optimal threshold over all subjects and 10 separate training/testing folds.

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.

Multiple Sclerosis Lesion Segmentation Using Joint Label Fusion

This paper adapts the joint label fusion (JLF) multi-atlas image segmentation algorithm to the problem of multiple sclerosis (MS) lesion segmentation in multi-modal MRI. Conventionally, JLF requires a set of atlas images to be co-registered to the target image using deformable registration. However, given the variable spatial distribution of lesions in the brain, whole-brain deformable registration is unlikely to line up lesions between atlases and the target image. As a solution, we propose to first pre-segment the target image using an intensity regression based technique, yielding a set of "candidate" lesions. Each "candidate" lesion is then matched to a set of similar lesions in the atlas based on location and size; and deformable registration and JLF are applied at the level of the "candidate" lesion. The approach is evaluated on a dataset of 74 subjects with MS and shown to improve Dice similarity coefficient with reference manual segmentation by 12% over intensity regression technique.

Volumetric Analysis from a Harmonized Multisite Brain MRI Study of a Single Subject with Multiple Sclerosis

BACKGROUND AND PURPOSE

MR imaging can be used to measure structural changes in the brains of individuals with multiple sclerosis and is essential for diagnosis, longitudinal monitoring, and therapy evaluation. The North American Imaging in Multiple Sclerosis Cooperative steering committee developed a uniform high-resolution 3T MR imaging protocol relevant to the quantification of cerebral lesions and atrophy and implemented it at 7 sites across the United States. To assess intersite variability in scan data, we imaged a volunteer with relapsing-remitting MS with a scan-rescan at each site.

MATERIALS AND METHODS

All imaging was acquired on Siemens scanners (4 Skyra, 2 Tim Trio, and 1 Verio). Expert segmentations were manually obtained for T1-hypointense and T2 (FLAIR) hyperintense lesions. Several automated lesion-detection and whole-brain, cortical, and deep gray matter volumetric pipelines were applied. Statistical analyses were conducted to assess variability across sites, as well as systematic biases in the volumetric measurements that were site-related.

RESULTS

Systematic biases due to site differences in expert-traced lesion measurements were significant (P < .01 for both T1 and T2 lesion volumes), with site explaining >90% of the variation (range, 13.0-16.4 mL in T1 and 15.9-20.1 mL in T2) in lesion volumes. Site also explained >80% of the variation in most automated volumetric measurements. Output measures clustered according to scanner models, with similar results from the Skyra versus the other 2 units.

CONCLUSIONS

Even in multicenter studies with consistent scanner field strength and manufacturer after protocol harmonization, systematic differences can lead to severe biases in volumetric analyses.

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.

A LAG FUNCTIONAL LINEAR MODEL FOR PREDICTION OF MAGNETIZATION TRANSFER RATIO IN MULTIPLE SCLEROSIS LESIONS

We propose a lag functional linear model to predict a response using multiple functional predictors observed at discrete grids with noise. Two procedures are proposed to estimate the regression parameter functions: (1) an approach that ensures smoothness for each value of time using generalized cross-validation; and (2) a global smoothing approach using a restricted maximum likelihood framework. Numerical studies are presented to analyze predictive accuracy in many realistic scenarios. The methods are employed to estimate a magnetic resonance imaging (MRI)-based measure of tissue damage (the magnetization transfer ratio, or MTR) in multiple sclerosis (MS) lesions, a disease that causes damage to the myelin sheaths around axons in the central nervous system. Our method of estimation of MTR within lesions is useful retrospectively in research applications where MTR was not acquired, as well as in clinical practice settings where acquiring MTR is not currently part of the standard of care. The model facilitates the use of commonly acquired imaging modalities to estimate MTR within lesions, and outperforms cross-sectional models that do not account for temporal patterns of lesion development and repair.

GRAPE: a graphical pipeline environment for image analysis in adaptive magnetic resonance imaging

PURPOSE

We present a platform, GRAphical Pipeline Environment (GRAPE), to facilitate the development of patient-adaptive magnetic resonance imaging (MRI) protocols.

METHODS

GRAPE is an open-source project implemented in the Qt C++ framework to enable graphical creation, execution, and debugging of real-time image analysis algorithms integrated with the MRI scanner. The platform provides the tools and infrastructure to design new algorithms, and build and execute an array of image analysis routines, and provides a mechanism to include existing analysis libraries, all within a graphical environment. The application of GRAPE is demonstrated in multiple MRI applications, and the software is described in detail for both the user and the developer.

RESULTS

GRAPE was successfully used to implement and execute three applications in MRI of the brain, performed on a 3.0-T MRI scanner: (i) a multi-parametric pipeline for segmenting the brain tissue and detecting lesions in multiple sclerosis (MS), (ii) patient-specific optimization of the 3D fluid-attenuated inversion recovery MRI scan parameters to enhance the contrast of brain lesions in MS, and (iii) an algebraic image method for combining two MR images for improved lesion contrast.

CONCLUSIONS

GRAPE allows graphical development and execution of image analysis algorithms for inline, real-time, and adaptive MRI applications.

PREVAIL: Predicting Recovery through Estimation and Visualization of Active and Incident Lesions

Objective

The goal of this study was to develop a model that integrates imaging and clinical information observed at lesion incidence for predicting the recovery of white matter lesions in multiple sclerosis (MS) patients.

Methods

Demographic, clinical, and magnetic resonance imaging (MRI) data were obtained from 60 subjects with MS as part of a natural history study at the National Institute of Neurological Disorders and Stroke. A total of 401 lesions met the inclusion criteria and were used in the study. Imaging features were extracted from the intensity-normalized T₁-weighted (T₁w) and T₂-weighted sequences as well as magnetization transfer ratio (MTR) sequence acquired at lesion incidence. T₁w and MTR signatures were also extracted from images acquired one-year post-incidence. Imaging features were integrated with clinical and demographic data observed at lesion incidence to create statistical prediction models for long-term damage within the lesion.

Validation

The performance of the T₁w and MTR predictions was assessed in two ways: first, the predictive accuracy was measured quantitatively using leave-one-lesion-out cross-validated (CV) mean-squared predictive error. Then, to assess the prediction performance from the perspective of expert clinicians, three board-certified MS clinicians were asked to individually score how similar the CV model-predicted one-year appearance was to the true one-year appearance for a random sample of 100 lesions.

Results

The cross-validated root-mean-square predictive error was 0.95 for normalized T₁w and 0.064 for MTR, compared to the estimated measurement errors of 0.48 and 0.078 respectively. The three expert raters agreed that T₁w and MTR predictions closely resembled the true one-year follow-up appearance of the lesions in both degree and pattern of recovery within lesions.

Conclusion

This study demonstrates that by using only information from a single visit at incidence, we can predict how a new lesion will recover using relatively simple statistical techniques. The potential to visualize the likely course of recovery has implications for clinical decision-making, as well as trial enrichment.

•

A model for predicting degree and pattern of MS lesion tissue recovery is proposed.

•

The model relies solely on MR images at lesion incidence and patient information.

•

Predictions performed well when rated for accuracy by expert MS clinicians.

Removing inter-subject technical variability in magnetic resonance imaging studies

Magnetic resonance imaging (MRI) intensities are acquired in arbitrary units, making scans non-comparable across sites and between subjects. Intensity normalization is a first step for the improvement of comparability of the images across subjects. However, we show that unwanted inter-scan variability associated with imaging site, scanner effect, and other technical artifacts is still present after standard intensity normalization in large multi-site neuroimaging studies. We propose RAVEL (Removal of Artificial Voxel Effect by Linear regression), a tool to remove residual technical variability after intensity normalization. As proposed by SVA and RUV [Leek and Storey, 2007, 2008, Gagnon-Bartsch and Speed, 2012], two batch effect correction tools largely used in genomics, we decompose the voxel intensities of images registered to a template into a biological component and an unwanted variation component. The unwanted variation component is estimated from a control region obtained from the cerebrospinal fluid (CSF), where intensities are known to be unassociated with disease status and other clinical covariates. We perform a singular value decomposition (SVD) of the control voxels to estimate factors of unwanted variation. We then estimate the unwanted factors using linear regression for every voxel of the brain and take the residuals as the RAVEL-corrected intensities. We assess the performance of RAVEL using T1-weighted (T1-w) images from more than 900 subjects with Alzheimer's disease (AD) and mild cognitive impairment (MCI), as well as healthy controls from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. We compare RAVEL to two intensity-normalization-only methods: histogram matching and White Stripe. We show that RAVEL performs best at improving the replicability of the brain regions that are empirically found to be most associated with AD, and that these regions are significantly more present in structures impacted by AD (hippocampus, amygdala, parahippocampal gyrus, enthorinal area, and fornix stria terminals). In addition, we show that the RAVEL-corrected intensities have the best performance in distinguishing between MCI subjects and healthy subjects using the mean hippocampal intensity (AUC=67%), a marked improvement compared to results from intensity normalization alone (AUC=63% and 59% for histogram matching and White Stripe, respectively). RAVEL is promising for many other imaging modalities.

Statistical estimation of T1 relaxation times using conventional magnetic resonance imaging

Quantitative T1 maps estimate T1 relaxation times and can be used to assess diffuse tissue abnormalities within normal-appearing tissue. T1 maps are popular for studying the progression and treatment of multiple sclerosis (MS). However, their inclusion in standard imaging protocols remains limited due to the additional scanning time and expert calibration required and susceptibility to bias and noise. Here, we propose a new method of estimating T1 maps using four conventional MR images, which are intensity-normalized using cerebellar gray matter as a reference tissue and related to T1 using a smooth regression model. Using cross-validation, we generate statistical T1 maps for 61 subjects with MS. The statistical maps are less noisy than the acquired maps and show similar reproducibility. Tests of group differences in normal-appearing white matter across MS subtypes give similar results using both methods.

Relating multi-sequence longitudinal intensity profiles and clinical covariates in incident multiple sclerosis lesions

The formation of multiple sclerosis (MS) lesions is a complex process involving inflammation, tissue damage, and tissue repair - all of which are visible on structural magnetic resonance imaging (MRI) and potentially modifiable by pharmacological therapy. In this paper, we introduce two statistical models for relating voxel-level, longitudinal, multi-sequence structural MRI intensities within MS lesions to clinical information and therapeutic interventions: (1) a principal component analysis (PCA) and regression model and (2) function-on-scalar regression models. To do so, we first characterize the post-lesion incidence repair process on longitudinal, multi-sequence structural MRI from 34 MS patients as voxel-level intensity profiles. For the PCA regression model, we perform PCA on the intensity profiles to develop a voxel-level biomarker for identifying slow and persistent, long-term intensity changes within lesion tissue voxels. The proposed biomarker's ability to identify such effects is validated by two experienced clinicians (a neuroradiologist and a neurologist). On a scale of 1 to 4, with 4 being the highest quality, the neuroradiologist gave the score on the first PC a median quality rating of 4 (95% CI: [4,4]), and the neurologist gave the score a median rating of 3 (95% CI: [3,3]). We then relate the biomarker to the clinical information in a mixed model framework. Treatment with disease-modifying therapies (p < 0.01), steroids (p < 0.01), and being closer to the boundary of abnormal signal intensity (p < 0.01) are all associated with return of a voxel to an intensity value closer to that of normal-appearing tissue. The function-on-scalar regression model allows for assessment of the post-incidence time points at which the covariates are associated with the profiles. In the function-on-scalar regression, both age and distance to the boundary were found to have a statistically significant association with the lesion intensities at some time point. The two models presented in this article show promise for understanding the mechanisms of tissue damage in MS and for evaluating the impact of treatments for the disease in clinical trials.

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.

Scan-stratified case-control sampling for modeling blood-brain barrier integrity in multiple sclerosis

Multiple sclerosis (MS) is an immune-mediated neurological disease that causes morbidity and disability. In patients with MS, the accumulation of lesions in the white matter of the brain is associated with disease progression and worse clinical outcomes. Breakdown of the blood-brain barrier in newer lesions is indicative of more active disease-related processes and is a primary outcome considered in clinical trials of treatments for MS. Such abnormalities in active MS lesions are evaluated in vivo using contrast-enhanced structural MRI, during which patients receive an intravenous infusion of a costly magnetic contrast agent. In some instances, the contrast agents can have toxic effects. Recently, local image regression techniques have been shown to have modest performance for assessing the integrity of the blood-brain barrier based on imaging without contrast agents. These models have centered on the problem of cross-sectional classification in which patients are imaged at a single study visit and pre-contrast images are used to predict post-contrast imaging. In this paper, we extend these methods to incorporate historical imaging information, and we find the proposed model to exhibit improved performance. We further develop scan-stratified case-control sampling techniques that reduce the computational burden of local image regression models, while respecting the low proportion of the brain that exhibits abnormal vascular permeability.

Subject-Specific Sparse Dictionary Learning for Atlas-Based Brain MRI Segmentation

Quantitative measurements from segmentations of human brain magnetic resonance (MR) images provide important biomarkers for normal aging and disease progression. In this paper, we propose a patch-based tissue classification method from MR images that uses a sparse dictionary learning approach and atlas priors. Training data for the method consists of an atlas MR image, prior information maps depicting where different tissues are expected to be located, and a hard segmentation. Unlike most atlas-based classification methods that require deformable registration of the atlas priors to the subject, only affine registration is required between the subject and training atlas. A subject-specific patch dictionary is created by learning relevant patches from the atlas. Then the subject patches are modeled as sparse combinations of learned atlas patches leading to tissue memberships at each voxel. The combination of prior information in an example-based framework enables us to distinguish tissues having similar intensities but different spatial locations. We demonstrate the efficacy of the approach on the application of whole-brain tissue segmentation in subjects with healthy anatomy and normal pressure hydrocephalus, as well as lesion segmentation in multiple sclerosis patients. For each application, quantitative comparisons are made against publicly available state-of-the art approaches.

Rotation-invariant multi-contrast non-local means for MS lesion segmentation

Multiple sclerosis (MS) lesion segmentation is crucial for evaluating disease burden, determining disease progression and measuring the impact of new clinical treatments. MS lesions can vary in size, location and intensity, making automatic segmentation challenging. In this paper, we propose a new supervised method to segment MS lesions from 3D magnetic resonance (MR) images using non-local means (NLM). The method uses a multi-channel and rotation-invariant distance measure to account for the diversity of MS lesions. The proposed segmentation method, rotation-invariant multi-contrast non-local means segmentation (RMNMS), captures the MS lesion spatial distribution and can accurately and robustly identify lesions regardless of their orientation, shape or size.

An internal validation on a large clinical magnetic resonance imaging (MRI) dataset of MS patients demonstrated a good similarity measure result (Dice similarity = 60.1% and sensitivity = 75.4%), a strong correlation between expert and automatic lesion load volumes (R² = 0.91), and a strong ability to detect lesions of different sizes and in varying spatial locations (lesion detection rate = 79.8%). On the independent MS Grand Challenge (MSGC) dataset validation, our method provided competitive results with state-of-the-art supervised and unsupervised methods. Qualitative visual and quantitative voxel- and lesion-wise evaluations demonstrated the accuracy of RMNMS method.

•

We propose a new multi-channel MS lesion segmentation technique.

•

We adapt for lesion segmentation the non-local means operator to account for multi-contrast and rotation-invariant distance.

•

The proposed method presents highly competitive results compared to state-of-the-art methods.

•

The proposed method provides segmentation quality near inter-rater variability for MS lesion segmentation.

•

Our non-local approach is able to detect structures that vary in size, shape and location such as MS lesions.

Multi-Output Decision Trees for Lesion Segmentation in Multiple Sclerosis

Multiple Sclerosis (MS) is a disease of the central nervous system in which the protective myelin sheath of the neurons is damaged. MS leads to the formation of lesions, predominantly in the white matter of the brain and the spinal cord. The number and volume of lesions visible in magnetic resonance (MR) imaging (MRI) are important criteria for diagnosing and tracking the progression of MS. Locating and delineating lesions manually requires the tedious and expensive efforts of highly trained raters. In this paper, we propose an automated algorithm to segment lesions in MR images using multi-output decision trees. We evaluated our algorithm on the publicly available MICCAI 2008 MS Lesion Segmentation Challenge training dataset of 20 subjects, and showed improved results in comparison to state-of-the-art methods. We also evaluated our algorithm on an in-house dataset of 49 subjects with a true positive rate of 0.41 and a positive predictive value 0.36.

Spatially regularized mixture model for lesion segmentation with application to stroke patients

In medical imaging, lesion segmentation (differentiation between lesioned and non-lesioned tissue) is a crucial and difficult task. Automated segmentation algorithms based on intensity analysis have been already proposed and recent developments have shown that integrating spatial information enhances automatic image segmentation. However, spatial modeling is often limited to short-range spatial interactions that deal only with noise or small artifacts. Previous tissue alterations (e.g. white matter disease (WMD)) similar in intensity with the lesion of interest require a broader-scale approach to be corrected. On the other hand, imaging techniques offer now a multiparametric voxel characterization that may help differentiating lesioned from non-lesioned voxels. We developed an unsupervised multivariate segmentation algorithm based on finite mixture modeling that incorporates spatial information. We extended the usual spatial Potts model to the regional scale using a 'multi-order' neighborhood potential, with internal adjustment of the regional scale according to the lesion size. We validate the ability of this new algorithm to deal with noise and artifacts (linear and spherical) using artificial data. We then assess its performance on real magnetic resonance imaging brain scans of stroke patients with history of WMD and show that regional regularization was able to remove large-scale WMD artifacts.

Health effects of lesion localization in multiple sclerosis: spatial registration and confounding adjustment

Brain lesion localization in multiple sclerosis (MS) is thought to be associated with the type and severity of adverse health effects. However, several factors hinder statistical analyses of such associations using large MRI datasets: 1) spatial registration algorithms developed for healthy individuals may be less effective on diseased brains and lead to different spatial distributions of lesions; 2) interpretation of results requires the careful selection of confounders; and 3) most approaches have focused on voxel-wise regression approaches. In this paper, we evaluated the performance of five registration algorithms and observed that conclusions regarding lesion localization can vary substantially with the choice of registration algorithm. Methods for dealing with confounding factors due to differences in disease duration and local lesion volume are introduced. Voxel-wise regression is then extended by the introduction of a metric that measures the distance between a patient-specific lesion mask and the population prevalence map.