Segmentation of multiple sclerosis lesions in brain MRI: A review of automated approaches

Serum neurofilament light chain is more strongly associated with T2 lesion volume than with number of T2 lesions in patients with multiple sclerosis

BACKGROUND AND PURPOSE

MR imaging provides information on the number and extend of focal lesions in multiple sclerosis (MS) patients. This study explores whether total brain T2 lesion volume or lesion number shows a better correlation with serum and cerebrospinal fluid (CSF) biomarkers of disease activity.

MATERIALS AND METHODS

In total, 52 patients suffering from clinically isolated syndrome (CIS)/relapsing-remitting multiple sclerosis (RRMS) were assessed including MRI markers (total brain T2 lesion volume semi-automatically outlined on 3D DIR/FLAIR sequences, number of lesions), serum and CSF biomarkers at the time of neuroimaging (neurofilament light chain (NfL), glial fibrillary acidic protein (GFAP)), and clinical parameters. After log-transformation and partial correlations adjusted for the covariates patients' age, BMI, EDSS-score and diagnosis, the Fisher's r-to-Z transformation was used to compare different correlation coefficients.

RESULTS

The correlation between lesion volume and serum NfL (r = 0.6, p < 0.001) was stronger compared to the association between the number of T2 lesions and serum NfL (r = 0.4, p < 0.01) (z = -2.0, p < 0.05). With regard to CSF NfL, there was a moderate, positive relationship for both number of T2 lesions and lesion volume (r = 0.5 respectively, p < 0.01). We found no significant association between MRI markers and GFAP levels.

CONCLUSION

Our findings suggest that there is a stronger association between serum NfL and T2 lesion volume, than there is between serum NfL and T2 lesion number. Improving robustness and accuracy of fully-automated lesion volume segmentation tools can expedite implementation into clinical routine and trials.

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.

Multiple sclerosis lesion segmentation: revisiting weighting mechanisms for federated learning

Background and introduction

Federated learning (FL) has been widely employed for medical image analysis to facilitate multi-client collaborative learning without sharing raw data. Despite great success, FL's applications remain suboptimal in neuroimage analysis tasks such as lesion segmentation in multiple sclerosis (MS), due to variance in lesion characteristics imparted by different scanners and acquisition parameters.

Methods

In this work, we propose the first FL MS lesion segmentation framework via two effective re-weighting mechanisms. Specifically, a learnable weight is assigned to each local node during the aggregation process, based on its segmentation performance. In addition, the segmentation loss function in each client is also re-weighted according to the lesion volume for the data during training.

Results

The proposed method has been validated on two FL MS segmentation scenarios using public and clinical datasets. Specifically, the case-wise and voxel-wise Dice score of the proposed method under the first public dataset is 65.20 and 74.30, respectively. On the second in-house dataset, the case-wise and voxel-wise Dice score is 53.66, and 62.31, respectively.

Discussions and conclusions

The Comparison experiments on two FL MS segmentation scenarios using public and clinical datasets have demonstrated the effectiveness of the proposed method by significantly outperforming other FL methods. Furthermore, the segmentation performance of FL incorporating our proposed aggregation mechanism can achieve comparable performance to that from centralized training with all the raw data.

Semisupervised white matter hyperintensities segmentation on MRI

This study proposed a semisupervised loss function named level-set loss (LSLoss) for cerebral white matter hyperintensities (WMHs) segmentation on fluid-attenuated inversion recovery images. The training procedure did not require manually labeled WMH masks. Our image preprocessing steps included biased field correction, skull stripping, and white matter segmentation. With the proposed LSLoss, we trained a V-Net using the MRI images from both local and public databases. Local databases were the small vessel disease cohort (HKU-SVD, n = 360) and the multiple sclerosis cohort (HKU-MS, n = 20) from our institutional imaging center. Public databases were the Medical Image Computing Computer-assisted Intervention (MICCAI) WMH challenge database (MICCAI-WMH, n = 60) and the normal control cohort of the Alzheimer's Disease Neuroimaging Initiative database (ADNI-CN, n = 15). We achieved an overall dice similarity coefficient (DSC) of 0.81 on the HKU-SVD testing set (n = 20), DSC = 0.77 on the HKU-MS testing set (n = 5), and DSC = 0.78 on MICCAI-WMH testing set (n = 30). The segmentation results obtained by our semisupervised V-Net were comparable with the supervised methods and outperformed the unsupervised methods in the literature.

Three Dimensional Brain Parameters of Multiple Sclerosis (MS) Patients

BACKGROUND & OBJECTIVES

MS is not only a demyelinating disease of central nervous system, but it also affects cortical and deep gray matter (GM). Furthermore, it causes axonal damage in the brain and spinal cord through inflammation and axonal degeneration. It is mostly seen between the ages of 20 and 40 and prevalence of the disease is higher among females than males. In the present study, we measured different parameters in the brains of patients with multiple sclerosis (MS) and healthy controls in both genders to determine the amount of brain atrophy quantitatively in MS patients.

METHODS

We used T2-weighted MRI scans of 40 MS patients (25 females + 15 males) with clinically definite relapsing-remitting multiple sclerosis that was determined according to Poser criteria in multiple parts of the brain, and we compared these data with those of sex-matched healthy controls in the same numbers.

RESULTS

Wideness of the lateral and third ventricles and the volumes of cerebral sulci in MS patients were significantly increased compared to both male and female controls. Brain width, corpus callosum area and the total brain/cerebellum + brain stem volumes of MS patients were decreased considerably.

INTERPRETATION & CONCLUSIONS

The present measurements indicated that MS caused parenchymal destruction in the cortex, axonal degeneration and myelin loss in the white matter of the brain. Consequently, the current observations correlate well with worsening disability in MS patients.

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.

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.

Cortical lesions, central vein sign, and paramagnetic rim lesions in multiple sclerosis: Emerging machine learning techniques and future avenues

The current diagnostic criteria for multiple sclerosis (MS) lack specificity, and this may lead to misdiagnosis, which remains an issue in present-day clinical practice. In addition, conventional biomarkers only moderately correlate with MS disease progression. Recently, some MS lesional imaging biomarkers such as cortical lesions (CL), the central vein sign (CVS), and paramagnetic rim lesions (PRL), visible in specialized magnetic resonance imaging (MRI) sequences, have shown higher specificity in differential diagnosis. Moreover, studies have shown that CL and PRL are potential prognostic biomarkers, the former correlating with cognitive impairments and the latter with early disability progression. As machine learning-based methods have achieved extraordinary performance in the assessment of conventional imaging biomarkers, such as white matter lesion segmentation, several automated or semi-automated methods have been proposed as well for CL, PRL, and CVS. In the present review, we first introduce these MS biomarkers and their imaging methods. Subsequently, we describe the corresponding machine learning-based methods that were proposed to tackle these clinical questions, putting them into context with respect to the challenges they are facing, including non-standardized MRI protocols, limited datasets, and moderate inter-rater variability. We conclude by presenting the current limitations that prevent their broader deployment and suggesting future research directions.

Multiple sclerosis diagnosis and phenotype identification by multivariate classification of in vivo frontal cortex metabolite profiles

Multiple sclerosis (MS) is a heterogeneous autoimmune disease for which diagnosis continues to rely on subjective clinical judgment over a battery of tests. Proton magnetic resonance spectroscopy (¹H MRS) enables the noninvasive in vivo detection of multiple small-molecule metabolites and is therefore in principle a promising means of gathering information sufficient for multiple sclerosis diagnosis and subtype classification. Here we show that supervised classification using ¹H-MRS-visible normal-appearing frontal cortex small-molecule metabolites alone can indeed differentiate individuals with progressive MS from control (held-out validation sensitivity 79% and specificity 68%), as well as between relapsing and progressive MS phenotypes (held-out validation sensitivity 84% and specificity 74%). Post hoc assessment demonstrated the disproportionate contributions of glutamate and glutamine to identifying MS status and phenotype, respectively. Our finding establishes ¹H MRS as a viable means of characterizing progressive multiple sclerosis disease status and paves the way for continued refinement of this method as an auxiliary or mainstay of multiple sclerosis diagnostics.

New MS lesion segmentation with deep residual attention gate U-Net utilizing 2D slices of 3D MR images

Multiple sclerosis (MS) is an autoimmune disease that causes lesions in the central nervous system of humans due to demyelinating axons. Magnetic resonance imaging (MRI) is widely used for monitoring and measuring MS lesions. Automated methods for MS lesion segmentation have usually been performed on individual MRI scans. Recently, tracking lesion activity for quantifying and monitoring MS disease progression, especially detecting new lesions, has become an important biomarker. In this study, a unique pipeline with a deep neural network that combines U-Net, attention gate, and residual learning is proposed to perform better new MS lesion segmentation using baseline and follow-up 3D FLAIR MR images. The proposed network has a similar architecture to U-Net and is formed from residual units which facilitate the training of deep networks. Networks with fewer parameters are designed with better performance through the skip connections of U-Net and residual units, which facilitate information propagation without degradation. Attention gates also learn to focus on salient features of the target structures of various sizes and shapes. The MSSEG-2 dataset was used for training and testing the proposed pipeline, and the results were compared with those of other proposed pipelines of the challenge and experts who participated in the same challenge. According to the results over the testing set, the lesion-wise F1 and dice scores were obtained as a mean of 48 and 44.30%. For the no-lesion cases, the number of tested and volume of tested lesions were obtained as a mean of 0.148 and 1.488, respectively. The proposed pipeline outperformed 22 proposed pipelines and ranked 8th in the challenge.

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.

Delve into Multiple Sclerosis (MS) lesion exploration: A modified attention U-Net for MS lesion segmentation in Brain MRI

Multiple Sclerosis (MS) is a Central Nervous System (CNS) disease that Magnetic Resonance Imaging (MRI) system can detect and segment its lesions. Artificial Neural Networks (ANNs) recently reached a noticeable performance in finding MS lesions from MRI. U-Net and Attention U-Net are two of the most successful ANNs in the field of MS lesion segmentation. In this work, we proposed a framework to segment MS lesions in Fluid-Attenuated Inversion Recovery (FLAIR) and T2 MRI images by modified U-Net and modified Attention U-Net. For this purpose, we developed some extra preprocessing on MRI scans, made modifications in the loss function of U-Net and Attention U-Net, and proposed using the union of FLAIR and T2 predictions to reach a better performance. Results show that the union of FLAIR and T2 predicted masks by the modified Attention U-Net reaches the performance of 82.30% in terms of Dice Similarity Coefficient (DSC) in the test dataset, which is a considerable improvement compared to the previous works.

Multiple Sclerosis Lesion Analysis in Brain Magnetic Resonance Images: Techniques and Clinical Applications

Multiple sclerosis (MS) is a chronic inflammatory and degenerative disease of the central nervous system, characterized by the appearance of focal lesions in the white and gray matter that topographically correlate with an individual patients neurological symptoms and signs. Magnetic resonance imaging (MRI) provides detailed in-vivo structural information, permitting the quantification and categorization of MS lesions that critically inform disease management. Traditionally, MS lesions have been manually annotated on 2D MRI slices, a process that is inefficient and prone to inter-/intra-observer errors. Recently, automated statistical imaging analysis techniques have been proposed to detect and segment MS lesions based on MRI voxel intensity. However, their effectiveness is limited by the heterogeneity of both MRI data acquisition techniques and the appearance of MS lesions. By learning complex lesion representations directly from images, deep learning techniques have achieved remarkable breakthroughs in the MS lesion segmentation task. Here, we provide a comprehensive review of state-of-the-art automatic statistical and deep-learning MS segmentation methods and discuss current and future clinical applications. Further, we review technical strategies, such as domain adaptation, to enhance MS lesion segmentation in real-world clinical settings.

FLAIR2 post-processing: improving MS lesion detection in standard MS imaging protocols

BACKGROUND

Technical improvements in magnetic resonance imaging (MRI) acquisition, such as higher field strength and optimized sequences, lead to better multiple sclerosis (MS) lesion detection and characterization. Multiplication of 3D-FLAIR with 3D-T2 sequences (FLAIR²) results in isovoxel images with increased contrast-to-noise ratio, increased white-gray-matter contrast, and improved MS lesion visualization without increasing MRI acquisition time. The current study aims to assess the potential of 3D-FLAIR² in detecting cortical/leucocortical (LC), juxtacortical (JC), and white matter (WM) lesions.

OBJECTIVE

To compare lesion detection of 3D-FLAIR² with state-of-the-art 3D-T2-FLAIR and 3D-T2-weighted images.

METHODS

We retrospectively analyzed MRI scans of thirteen MS patients, showing previously noted high cortical lesion load. Scans were acquired using a 3 T MRI scanner. WM, JC, and LC lesions were manually labeled and manually counted after randomization of 3D-T2, 3D-FLAIR, and 3D-FLAIR² scans using the ITK-SNAP tool.

RESULTS

LC lesion visibility was significantly improved by 3D-FLAIR² in comparison to 3D-FLAIR (4 vs 1; p = 0.018) and 3D-T2 (4 vs 1; p = 0.007). Comparing LC lesion detection in 3D-FLAIR² vs. 3D-FLAIR, 3D-FLAIR² detected on average 3.2 more cortical lesions (95% CI - 9.1 to 2.8). Comparing against 3D-T2, 3D-FLAIR² detected on average 3.7 more LC lesions (95% CI 3.3-10.7).

CONCLUSIONS

3D-FLAIR² is an easily applicable time-sparing MR post-processing method to improve cortical lesion detection. Larger sampled studies are warranted to validate the sensitivity and specificity of 3D-FLAIR².

Multiple sclerosis lesions segmentation from multiple experts: The MICCAI 2016 challenge dataset

MRI plays a crucial role in multiple sclerosis diagnostic and patient follow-up. In particular, the delineation of T2-FLAIR hyperintense lesions is crucial although mostly performed manually - a tedious task. Many methods have thus been proposed to automate this task. However, sufficiently large datasets with a thorough expert manual segmentation are still lacking to evaluate these methods. We present a unique dataset for MS lesions segmentation evaluation. It consists of 53 patients acquired on 4 different scanners with a harmonized protocol. Hyperintense lesions on FLAIR were manually delineated on each patient by 7 experts with control on T2 sequence, and gathered in a consensus segmentation for evaluation. We provide raw and preprocessed data and a split of the dataset into training and testing data, the latter including data from a scanner not present in the training dataset. We strongly believe that this dataset will become a reference in MS lesions segmentation evaluation, allowing to evaluate many aspects: evaluation of performance on unseen scanner, comparison to individual experts performance, comparison to other challengers who already used this dataset, etc.

Performance improvement of weakly supervised fully convolutional networks by skip connections for brain structure segmentation

PURPOSE

For the planning and navigation of neurosurgery, we have developed a fully convolutional network (FCN)-based method for brain structure segmentation on magnetic resonance (MR) images. The capability of an FCN depends on the quality of the training data (i.e., raw data and annotation data) and network architectures. The improvement of annotation quality is a significant concern because it requires much labor for labeling organ regions. To address this problem, we focus on skip connection architectures and reveal which skip connections are effective for training FCNs using sparsely annotated brain images.

METHODS

We tested 2D FCN architectures with four different types of skip connections. The first was a U-Net architecture with horizontal skip connections that transfer feature maps at the same scale from the encoder to the decoder. The second was a U-Net++ architecture with dense convolution layers and dense horizontal skip connections. The third was a full-resolution residual network (FRRN) architecture with vertical skip connections that pass feature maps between each downsampled scale path and the full-resolution scale path. The last one was a hybrid architecture with a combination of horizontal and vertical skip connections. We validated the effect of skip connections on medical image segmentation from sparse annotation based on these four FCN architectures, which were trained under the same conditions.

RESULTS

For multiclass segmentation of the cerebrum, cerebellum, brainstem, and blood vessels from sparsely annotated MR images, we performed a comparative evaluation of segmentation performance among the above four FCN approaches: U-Net, U-Net++, FRRN, and hybrid architectures. The experimental results show that the horizontal skip connections in the U-Net architectures were effective for the segmentation of larger sized objects, whereas the vertical skip connections in the FRRN architecture improved the segmentation of smaller sized objects. The hybrid architecture with both horizontal and vertical skip connections achieved the best results of the four FCN architectures. We then performed an ablation study to explore which skip connections in the FRRN architecture contributed to the improved segmentation of blood vessels. In the ablation study, we compared the segmentation performance between architectures with a horizontal path (HP), an HP and vertical up paths (HP+VUPs), an HP and vertical down paths (HP+VDPs), and an HP and vertical up and down paths (FRRN). We found that the vertical up paths were effective in improving the segmentation of smaller sized objects.

CONCLUSIONS

This paper investigated which skip connection architectures were effective for multiclass brain segmentation from sparse annotation. Consequently, using vertical skip connections with horizontal skip connections allowed FCNs to improve segmentation performance.

Lesion probability mapping in MS patients using a regression network on MR fingerprinting

BACKGROUND

To develop a regression neural network for the reconstruction of lesion probability maps on Magnetic Resonance Fingerprinting using echo-planar imaging (MRF-EPI) in addition to [Formula: see text], [Formula: see text], NAWM, and GM- probability maps.

METHODS

We performed MRF-EPI measurements in 42 patients with multiple sclerosis and 6 healthy volunteers along two sites. A U-net was trained to reconstruct the denoised and distortion corrected [Formula: see text] and [Formula: see text] maps, and to additionally generate NAWM-, GM-, and WM lesion probability maps.

RESULTS

WM lesions were predicted with a dice coefficient of [Formula: see text] and a lesion detection rate of [Formula: see text] for a threshold of 33%. The network jointly enabled accurate [Formula: see text] and [Formula: see text] times with relative deviations of 5.2% and 5.1% and average dice coefficients of [Formula: see text] and [Formula: see text] for NAWM and GM after binarizing with a threshold of 80%.

CONCLUSION

DL is a promising tool for the prediction of lesion probability maps in a fraction of time. These might be of clinical interest for the WM lesion analysis in MS patients.

APRNet: A 3D Anisotropic Pyramidal Reversible Network with Multi-modal Cross-Dimension Attention for Brain Tissue Segmentation in MR Images

Brain tissue segmentation in multi-modal magnetic resonance (MR) images is significant for the clinical diagnosis of brain diseases. Due to blurred boundaries, low contrast, and intricate anatomical relationships between brain tissue regions, automatic brain tissue segmentation without prior knowledge is still challenging. This paper presents a novel 3D fully convolutional network (FCN) for brain tissue segmentation, called APRNet. In this network, we first propose a 3D anisotropic pyramidal convolutional reversible residual sequence (3DAPC-RRS) module to integrate the intra-slice information with the inter-slice information without significant memory consumption; secondly, we design a multi-modal cross-dimension attention (MCDA) module to automatically capture the effective information in each dimension of multi-modal images; then, we apply 3DAPC-RRS modules and MCDA modules to a 3D FCN with multiple encoded streams and one decoded stream for constituting the overall architecture of APRNet. We evaluated APRNet on two benchmark challenges, namely MRBrainS13 and iSeg-2017. The experimental results show that APRNet yields state-of-the-art segmentation results on both benchmark challenge datasets and achieves the best segmentation performance on the cerebrospinal fluid region. Compared with other methods, our proposed approach exploits the complementary information of different modalities to segment brain tissue regions in both adult and infant MR images, and it achieves the average Dice coefficient of 87.22% and 93.03% on the MRBrainS13 and iSeg-2017 testing data, respectively. The proposed method is beneficial for quantitative brain analysis in the clinical study, and our code is made publicly available.

A multi-inversion-recovery magnetic resonance fingerprinting for multi-compartment water mapping

PURPOSE

This study aimed at introducing short-T1/T2 compartment to MR fingerprinting (MRF) at 3 T. Water that is bound to myelin macromolecules have significantly shorter T1 and T2 than free water and can be distinguished from free water by multi-compartment analysis.

METHODS

We developed a new multi-inversion-recovery (mIR) water mapping-MRF based on an unbalanced steady-state coherent sequence (FISP). mIR pulses with an interval of 400 or 500 repetition times (TRs) were inserted into the conventional FISP MRF sequence. Data from our proposed mIR MRF was used to quantify different compartments, including myelin water, gray matter free water, and white matter free water, of brain water by virtue of the iterative non-negative least square (NNLS) with reweighting. Three healthy volunteers were scanned with mIR MRF on a clinical 3 T MRI.

RESULTS

Using an extended phase graph simulation, we found that our proposed mIR scheme with four IR pulses allowed differentiation between short and long T1/T2 components. For in vivo experiments, we achieved the quantification of myelin water, gray matter water, and white matter water at an image resolution of 1.17 × 1.17 × 5 mm³/pixel. As compared to the conventional MRF technique with single IR, our proposed mIR improved the detection of myelin water content. In addition, mIR MRF using spiral-in/out trajectory provided a higher signal level compared with that with spiral-out trajectory. Myelin water quantification using mIR MRF with 4 IR and 5 IR pulses were qualitatively similar. Meanwhile, 5 IR MRF showed fewer artifacts in myelin water detection.

CONCLUSION

We developed a new mIR MRF sequence for the rapid quantification of brain water compartments.

A metric learning method for estimating myelin content based on T2-weighted MRI from a de- and re-myelination model of multiple sclerosis

Myelin plays a critical role in the pathogenesis of neurological disorders but is difficult to characterize in vivo using standard analysis methods. Our goal was to develop a novel analytical framework for estimating myelin content using T2-weighted magnetic resonance imaging (MRI) based on a de- and re-myelination model of multiple sclerosis. We examined 18 mice with lysolecithin induced demyelination and spontaneous remyelination in the ventral white matter of thoracic spinal cord. Cohorts of 6 mice underwent 9.4T MRI at days 7 (peak demyelination), 14 (ongoing recovery), and 28 (near complete recovery), as well as histological analysis of myelin and the associated cellularity at corresponding timepoints. Our MRI framework took an unsupervised learning approach, including tissue segmentation using a Gaussian Markov random field (GMRF), and myelin and cellularity feature estimation based on the Mahalanobis distance. For comparison, we also investigated 2 regression-based supervised learning approaches, one using our GMRF results, and another using a freely available generalized additive model (GAM). Results showed that GMRF segmentation was 73.2% accurate, and our unsupervised learning method achieved a correlation coefficient of 0.67 (top quartile: 0.78) with histological myelin, similar to 0.70 (top quartile: 0.78) obtained using supervised analyses. Further, the area under the receiver operator characteristic curve of our unsupervised myelin feature (0.883, 95% CI: 0.874-0.891) was significantly better than any of the supervised models in detecting white matter myelin as compared to histology. Collectively, metric learning using standard MRI may prove to be a new alternative method for estimating myelin content, which ultimately can improve our disease monitoring ability in a clinical setting.

MhURI:A Supervised Segmentation Approach to Leverage Salient Brain Tissues in Magnetic Resonance Images

BACKGROUND AND OBJECTIVES

Accurate segmentation of critical tissues from a brain MRI is pivotal for characterization and quantitative pattern analysis of the human brain and thereby, identifies the earliest signs of various neurodegenerative diseases. To date, in most cases, it is done manually by the radiologists. The overwhelming workload in some of the thickly populated nations may cause exhaustion leading to interruption for the doctors, which may pose a continuing threat to patient safety. A novel fusion method called U-Net inception based on 3D convolutions and transition layers is proposed to address this issue.

METHODS

A 3D deep learning method called Multi headed U-Net with Residual Inception (MhURI) accompanied by Morphological Gradient channel for brain tissue segmentation is proposed, which incorporates Residual Inception 2-Residual (RI2R) module as the basic building block. The model exploits the benefits of morphological pre-processing for structural enhancement of MR images. A multi-path data encoding pipeline is introduced on top of the U-Net backbone, which encapsulates initial global features and captures the information from each MRI modality.

RESULTS

The proposed model has accomplished encouraging outcomes, which appreciates the adequacy in terms of some of the established quality metrices when compared with some of the state-of-the-art methods while evaluating with respect to two popular publicly available data sets.

CONCLUSION

The model is entirely automatic and able to segment gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF) from brain MRI effectively with sufficient accuracy. Hence, it may be considered to be a potential computer-aided diagnostic (CAD) tool for radiologists and other medical practitioners in their clinical diagnosis workflow.

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.

Diffusion Basis Spectrum Imaging Detects Axonal Loss After Transient Dexamethasone Treatment in Optic Neuritis Mice

Optic neuritis is a frequent first symptom of multiple sclerosis (MS) for which corticosteroids are a widely employed treatment option. The Optic Neuritis Treatment Trial (ONTT) reported that corticosteroid treatment does not improve long-term visual acuity, although the evolution of underlying pathologies is unclear. In this study, we employed non-invasive diffusion basis spectrum imaging (DBSI)-derived fiber volume to quantify 11% axonal loss 2 months after corticosteroid treatment (vs. baseline) in experimental autoimmune encephalomyelitis mouse optic nerves affected by optic neuritis. Longitudinal DBSI was performed at baseline (before immunization), after a 2-week corticosteroid treatment period, and 1 and 2 months after treatment, followed by histological validation of neuropathology. Pathological metrics employed to assess the optic nerve revealed axonal protection and anti-inflammatory effects of dexamethasone treatment that were transient. Two months after treatment, axonal injury and loss were indistinguishable between PBS- and dexamethasone-treated optic nerves, similar to results of the human ONTT. Our findings in mice further support that corticosteroid treatment alone is not sufficient to prevent eventual axonal loss in ON, and strongly support the potential of DBSI as an in vivo imaging outcome measure to assess optic nerve pathology.

Review of Deep Learning Approaches for the Segmentation of Multiple Sclerosis Lesions on Brain MRI

In recent years, there have been multiple works of literature reviewing methods for automatically segmenting multiple sclerosis (MS) lesions. However, there is no literature systematically and individually review deep learning-based MS lesion segmentation methods. Although the previous review also included methods based on deep learning, there are some methods based on deep learning that they did not review. In addition, their review of deep learning methods did not go deep into the specific categories of Convolutional Neural Network (CNN). They only reviewed these methods in a generalized form, such as supervision strategy, input data handling strategy, etc. This paper presents a systematic review of the literature in automated multiple sclerosis lesion segmentation based on deep learning. Algorithms based on deep learning reviewed are classified into two categories through their CNN style, and their strengths and weaknesses will also be given through our investigation and analysis. We give a quantitative comparison of the methods reviewed through two metrics: Dice Similarity Coefficient (DSC) and Positive Predictive Value (PPV). Finally, the future direction of the application of deep learning in MS lesion segmentation will be discussed.

Faster RCNN-based detection of cervical spinal cord injury and disc degeneration

Magnetic resonance imaging (MRI) can indirectly reflect microscopic changes in lesions on the spinal cord; however, the application of deep learning to MRI to classify and detect lesions for cervical spinal cord diseases has not been sufficiently explored. In this study, we implemented a deep neural network for MRI to detect lesions caused by cervical diseases. We retrospectively reviewed the MRI of 1,500 patients irrespective of whether they had cervical diseases. The patients were treated in our hospital from January 2013 to December 2018. We randomly divided the MRI data into three groups of datasets: disc group (800 datasets), injured group (200 datasets), and normal group (500 datasets). We designed the relevant parameters and used a faster-region convolutional neural network (Faster R-CNN) combined with a backbone convolutional feature extractor using the ResNet-50 and VGG-16 networks, to detect lesions during MRI. Experimental results showed that the prediction accuracy and speed of Faster R-CNN with ResNet-50 and VGG-16 in detecting and recognizing lesions from a cervical spinal cord MRI were satisfactory. The mean average precisions (mAPs) for Faster R-CNN with ResNet-50 and VGG-16 were 88.6 and 72.3%, respectively, and the testing times was 0.22 and 0.24 s/image, respectively. Faster R-CNN can identify and detect lesions from cervical MRIs. To some extent, it may aid radiologists and spine surgeons in their diagnoses. The results of our study can provide motivation for future research to combine medical imaging and deep learning.

Evaluation of discrete orthogonal versus polar Stockwell Transform for local multi-resolution texture analysis using brain MRI of multiple sclerosis patients

The Stockwell Transform has the potential to perform multi-resolution texture analysis in magnetic resonance imaging (MRI). However, it is computationally intensive and memory demanding. The polar Stockwell Transform (PST) is rotation-invariant and relatively memory efficient, but still computationally demanding. The new Discrete Orthogonal Stockwell Transform (DOST) appears to have addressed both the computation and storage challenges; however, its utility in localized texture analysis remains unclear. Our goal was to investigate the theory and texture analysis ability of the DOST versus PST using both synthetic and MR images, and explore the relative importance of the associated texture features using a simple classification example based on clinical brain MRI of six multiple sclerosis patients. MRI texture analysis focused on FLAIR images, and the classification used a machine learning algorithm, random forest, that differentiated regions of interest (ROIs) into 2 classes: white matter lesions, and the contralateral normal-appearing white matter (control). Our results showed that the PST features had a greater ability in detecting subtle changes in image structure than the DOST and polar-index DOST (PDOST). Quantitatively, based on 187 lesion and 187 control ROIs, both the PST and the rotation-invariant radial PST performed better in the classification than the DOST and PDOST, where the latter were no better than guessing (p = 0.65 and 0.98). Further analysis using a hierarchical random forest showed that combining MRI signal intensity with the PST or DOST predictions increased the classification performance, with the accuracy, sensitivity, and specificity all improved to >85% in the tests. Collectively, the DOST is less competitive than the PST in localized image texture analysis. The PST features may help with texture-based lesion classification in MS based on clinical brain MRI scans following further verification.

Multiple sclerosis cortical and WM lesion segmentation at 3T MRI: a deep learning method based on FLAIR and MP2RAGE

The presence of cortical lesions in multiple sclerosis patients has emerged as an important biomarker of the disease. They appear in the earliest stages of the illness and have been shown to correlate with the severity of clinical symptoms. However, cortical lesions are hardly visible in conventional magnetic resonance imaging (MRI) at 3T, and thus their automated detection has been so far little explored. In this study, we propose a fully-convolutional deep learning approach, based on the 3D U-Net, for the automated segmentation of cortical and white matter lesions at 3T. For this purpose, we consider a clinically plausible MRI setting consisting of two MRI contrasts only: one conventional T2-weighted sequence (FLAIR), and one specialized T1-weighted sequence (MP2RAGE). We include 90 patients from two different centers with a total of 728 and 3856 gray and white matter lesions, respectively. We show that two reference methods developed for white matter lesion segmentation are inadequate to detect small cortical lesions, whereas our proposed framework is able to achieve a detection rate of 76% for both cortical and white matter lesions with a false positive rate of 29% in comparison to manual segmentation. Further results suggest that our framework generalizes well for both types of lesion in subjects acquired in two hospitals with different scanners.

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.

Automated Detection and Segmentation of Multiple Sclerosis Lesions Using Ultra-High-Field MP2RAGE

OBJECTIVES

The aim of this study was to develop a new automated segmentation method of white matter (WM) and cortical multiple sclerosis (MS) lesions visible on magnetization-prepared 2 inversion-contrast rapid gradient echo (MP2RAGE) images acquired at 7 T MRI.

MATERIALS AND METHODS

The proposed prototype (MSLAST [Multiple Sclerosis Lesion Analysis at Seven Tesla]) takes as input a single image contrast derived from the 7T MP2RAGE prototype sequence and is based on partial volume estimation and topological constraints. First, MSLAST performs a skull-strip of MP2RAGE images and computes tissue concentration maps for WM, gray matter (GM), and cerebrospinal fluid (CSF) using a partial volume model of tissues within each voxel. Second, MSLAST performs (1) connected-component analysis to GM and CSF concentration maps to classify small isolated components as MS lesions; (2) hole-filling in the WM concentration map to classify areas with low WM concentration surrounded by WM (ie, MS lesions); and (3) outlier rejection to the WM mask to improve the classification of small WM lesions. Third, MSLAST unifies the 3 maps obtained from 1, 2, and 3 processing steps to generate a global lesion mask.

RESULTS

Quantitative and qualitative assessments were performed using MSLAST in 25 MS patients from 2 research centers. Overall, MSLAST detected a median of 71% of MS lesions, specifically 74% of WM and 58% of cortical lesions, when a minimum lesion size of 6 μL was considered. The median false-positive rate was 40%. When a 15 μL minimal lesions size was applied, which is the approximation of the minimal size recommended for 1.5/3 T images, the median detection rate was 80% for WM and 63% for cortical lesions, respectively, and the median false-positive rate was 33%. We observed high correlation between MSLAST and manual segmentations (Spearman rank correlation coefficient, ρ = 0.91), although MSLAST underestimated the total lesion volume (average difference of 1.1 mL), especially in patients with high lesion loads. MSLAST also showed good scan-rescan repeatability within the same session with an average absolute volume difference and F1 score of 0.38 ± 0.32 mL and 84%, respectively.

CONCLUSIONS

We propose a new methodology to facilitate the segmentation of WM and cortical MS lesions at 7 T MRI, our approach uses a single MP2RAGE scan and may be of special interest to clinicians and researchers.

SegAE: Unsupervised white matter lesion segmentation from brain MRIs using a CNN autoencoder

White matter hyperintensities (WMHs) of presumed vascular origin are frequently observed in magnetic resonance images (MRIs) of the elderly. Detection and quantification of WMHs is important to help doctors make diagnoses and evaluate prognosis of their elderly patients, and once quantified, these can act as biomarkers in clinical research studies. Manual delineation of WMHs can be both time-consuming and inconsistent, hence, automatic segmentation methods are often preferred. However, fully automatic methods can be challenging to construct due to the variability in lesion load, placement of lesions, and voxel intensities. Several state-of-the-art lesion segmentation methods based on supervised Convolutional Neural Networks (CNNs) have been proposed. These approaches require manually delineated lesions for training the parameters of the network. Here we present a novel approach for WMH segmentation using a CNN trained in an unsupervised manner, by reconstructing multiple MRI sequences as weighted sums of segmentations of WMHs and tissues present in the images. After training, our method can be used to segment new images that are not part of the training set to provide fast and robust segmentation of WMHs in a matter of seconds per subject. Comparisons with state-of-the-art WMH segmentation methods evaluated on ground truth manual labels from two distinct data sets and six different scanners indicate that the proposed method works well at generating accurate WMH segmentations without the need for manual delineations.

Segmentation and clustering in brain MRI imaging

Clustering is a vital task in magnetic resonance imaging (MRI) brain imaging and plays an important role in the reliability of brain disease detection, diagnosis, and effectiveness of the treatment. Clustering is used in processing and analysis of brain images for different tasks, including segmentation of brain regions and tissues (grey matter, white matter, and cerebrospinal fluid) and clustering of the atrophy in different parts of the brain. This paper presents a state-of-the-art review of brain MRI studies that use clustering techniques for different tasks.

MRI quality control for the Italian Neuroimaging Network Initiative: moving towards big data in multiple sclerosis

The Italian Neuroimaging Network Initiative (INNI) supports the creation of a repository, where MRI, clinical, and neuropsychological data from multiple sclerosis (MS) patients and healthy controls are collected from Italian Research Centers with internationally recognized expertise in MRI applied to MS. However, multicenter MRI data integration needs standardization and quality control (QC). This study aimed to implement quantitative measures for characterizing the standardization and quality of MRI collected within INNI. MRI scans of 423 MS patients, including 3D T₁- and T₂-weighted, were obtained from INNI repository (from Centers A, B, C, and D). QC measures were implemented to characterize: (1) head positioning relative to the magnet isocenter; (2) intensity inhomogeneity; (3) relative image contrast between brain tissues; and (4) image artefacts. Centers A and D showed the most accurate subject positioning within the MR scanner (median z-offsets = - 2.6 ± 1.7 cm and - 1.1 ± 2 cm). A low, but significantly different, intensity inhomogeneity on 3D T₁-weighted MRI was found between all centers (p < 0.05), except for Centers A and C that showed comparable image bias fields. Center D showed the highest relative contrast between gray and normal appearing white matter (NAWM) on 3D T₁-weighed MRI (0.63 ± 0.04), while Center B showed the highest relative contrast between NAWM and MS lesions on FLAIR (0.21 ± 0.06). Image artefacts were mainly due to brain movement (60%) and ghosting (35%). The implemented QC procedure ensured systematic data quality assessment within INNI, thus making available a huge amount of high-quality MRI to better investigate pathophysiological substrates and validate novel MRI biomarkers in MS.

Longitudinal analysis of white matter and cortical lesions in multiple sclerosis

PURPOSE

The goals of this study were to assess the performance of a novel lesion segmentation tool for longitudinal analyses, as well as to validate the generated lesion progression map between two time points using conventional and non-conventional MR sequences.

MATERIAL AND METHODS

The lesion segmentation approach was evaluated with (LeMan-PV) and without (LeMan) the partial volume framework using "conventional" and "non-conventional" MR imaging in a two-year follow-up prospective study of 32 early RRMS patients. Manual segmentations of new, enlarged, shrunken, and stable lesions were used to evaluate the performance of the method variants. The true positive rate was estimated for those lesion evolutions in both white matter and cortex. The number of false positives was compared with two strategies for longitudinal analyses. New lesion tissue volume estimation was evaluated using Bland-Altman plots. Wilcoxon signed-rank test was used to evaluate the different setups.

RESULTS

The best median of the true positive rate was obtained using LeMan-PV with non-conventional sequences (P < .05): 87%, 87%, 100%, 83%, for new, enlarged, shrunken, and stable WM lesions, and 50%, 60%, 50%, 80%, for new, enlarged, shrunken, and stable cortical lesions, respectively. Most of the missed lesions were below the mean lesion size in each category. Lesion progression maps presented a median of 0 false positives (range:0-9) and the partial volume framework improved the volume estimation of new lesion tissue.

CONCLUSION

LeMan-PV exhibited the best performance in the detection of new, enlarged, shrunken and stable WM lesions. The method showed lower performance in the detection of cortical lesions, likely due to their low occurrence, small size and low contrast with respect to surrounding tissues. The proposed lesion progression map might be useful in clinical trials or clinical routine.

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.

Automated segmentation of changes in FLAIR-hyperintense white matter lesions in multiple sclerosis on serial magnetic resonance imaging

Longitudinal analysis of white matter lesion changes on serial MRI has become an important parameter to study diseases with white-matter lesions. Here, we build on earlier work on cross-sectional lesion segmentation; we present a fully automatic pipeline for serial analysis of FLAIR-hyperintense white matter lesions. Our algorithm requires three-dimensional gradient echo T1- and FLAIR- weighted images at 3 Tesla as well as available cross-sectional lesion segmentations of both time points. Preprocessing steps include lesion filling and intrasubject registration. For segmentation of lesion changes, initial lesion maps of different time points are fused; herein changes in intensity are analyzed at the voxel level. Significance of lesion change is estimated by comparison with the difference distribution of FLAIR intensities within normal appearing white matter. The method is validated on MRI data of two time points from 40 subjects with multiple sclerosis derived from two different scanners (20 subjects per scanner). Manual segmentation of lesion increases served as gold standard. Across all lesion increases, voxel-wise Dice coefficient (0.7) as well as lesion-wise detection rate (0.8) and false-discovery rate (0.2) indicate good overall performance. Analysis of scans from a repositioning experiment in a single patient with multiple sclerosis did not yield a single false positive lesion. We also introduce the lesion change plot as a descriptive tool for the lesion change of individual patients with regard to both number and volume. An open source implementation of the algorithm is available at http://www.statistical-modeling.de/lst.html.

•

Quantification of white matter lesion changes is important in multiple sclerosis.

•

We developed and validated an algorithm for automated detection of lesion changes.

•

Our algorithm requires T1-weighted and FLAIR images derived at 3 T as well as available cross-sectional lesion segmentations.

•

With data from 2 different scanners, the tool showed good agreement with manual tracing.

•

An open-source application is available.

HyperDense-Net: A Hyper-Densely Connected CNN for Multi-Modal Image Segmentation

Recently, dense connections have attracted substantial attention in computer vision because they facilitate gradient flow and implicit deep supervision during training. Particularly, DenseNet that connects each layer to every other layer in a feed-forward fashion and has shown impressive performances in natural image classification tasks. We propose HyperDenseNet, a 3-D fully convolutional neural network that extends the definition of dense connectivity to multi-modal segmentation problems. Each imaging modality has a path, and dense connections occur not only between the pairs of layers within the same path but also between those across different paths. This contrasts with the existing multi-modal CNN approaches, in which modeling several modalities relies entirely on a single joint layer (or level of abstraction) for fusion, typically either at the input or at the output of the network. Therefore, the proposed network has total freedom to learn more complex combinations between the modalities, within and in-between all the levels of abstraction, which increases significantly the learning representation. We report extensive evaluations over two different and highly competitive multi-modal brain tissue segmentation challenges, iSEG 2017 and MRBrainS 2013, with the former focusing on six month infant data and the latter on adult images. HyperDenseNet yielded significant improvements over many state-of-the-art segmentation networks, ranking at the top on both benchmarks. We further provide a comprehensive experimental analysis of features re-use, which confirms the importance of hyper-dense connections in multi-modal representation learning. Our code is publicly available.

Gender Identification of Human Cortical 3-D Morphology Using Hierarchical Sparsity

Difference exists widely in cognition, behavior and psychopathology between males and females, while the underlying neurobiology is still unclear. As brain structure is the fundament of its function, getting insight into structural brain may help us to better understand the functional mechanism of gender difference. Previous structural studies of gender difference in Magnetic Resonance Imaging (MRI) usually focused on gray matter (GM) concentration and structural connectivity (SC), leaving cortical morphology not characterized properly. In this study a large dataset is used to explore whether cortical three-dimensional (3-D) morphology can offer enough discriminative morphological features to effectively identify gender. Data of all available healthy controls (N = 1113) from the Human Connectome Project (HCP) were utilized. We suggested a multivariate pattern analysis method called Hierarchical Sparse Representation Classifier (HSRC) and got an accuracy of 96.77% for gender identification. Permutation tests were used to testify the reliability of gender discrimination (p < 0.001). Cortical 3-D morphological features within the frontal lobe were found the most important contributors to gender difference of human brain morphology. Moreover, we investigated gender discriminative ability of cortical 3-D morphology in predefined Anatomical Automatic Labeling (AAL) and Resting-State Networks (RSN) templates, and found the superior frontal gyrus the most discriminative in AAL and the default mode network the most discriminative in RSN. Gender difference of surface-based morphology was also discussed. The frontal lobe, as well as the default mode network, was widely reported of gender difference in previous structural and functional MRI studies, which suggested that morphology indeed affect human brain function. Our study indicates that gender can be identified on individual level by using cortical 3-D morphology and offers a new approach for structural MRI research, as well as highlights the importance of gender balance in brain imaging studies.

Quantitative neuroimaging measures of myelin in the healthy brain and in multiple sclerosis

Quantitative magnetic resonance imaging (MRI) techniques have been developed as imaging biomarkers, aiming to improve the specificity of MRI to underlying pathology compared to conventional weighted MRI. For assessing the integrity of white matter (WM), myelin, in particular, several techniques have been proposed and investigated individually. However, comparisons between these methods are lacking. In this study, we compared four established myelin‐sensitive MRI techniques in 56 patients with relapsing–remitting multiple sclerosis (MS) and 38 healthy controls. We used T2‐relaxation with combined GRadient And Spin Echoes (GRASE) to measure myelin water fraction (MWF‐G), multi‐component driven equilibrium single pulse observation of T₁ and T₂ (mcDESPOT) to measure MWF‐D, magnetization‐transfer imaging to measure magnetization‐transfer ratio (MTR), and T₁ relaxation to measure quantitative T₁ (qT₁). Using voxelwise Spearman correlations, we tested the correspondence of methods throughout the brain. All four methods showed associations that varied across tissue types; the highest correlations were found between MWF‐D and qT₁ (median ρ across tissue classes 0.8) and MWF‐G and MWF‐D (median ρ = 0.59). In eight WM tracts, all measures showed differences (p < 0.05) between MS normal‐appearing WM and healthy control WM, with qT1 showing the highest number of different regions (8), followed by MWF‐D and MTR (6), and MWF‐G (n = 4). Comparing the methods in terms of their statistical sensitivity to MS lesions in WM, MWF‐D demonstrated the best accuracy (p < 0.05, after multiple comparison correction). To aid future power analysis, we provide the average and standard deviation volumes of the four techniques, estimated from the healthy control sample.

Automatic segmentation of the spinal cord and intramedullary multiple sclerosis lesions with convolutional neural networks

The spinal cord is frequently affected by atrophy and/or lesions in multiple sclerosis (MS) patients. Segmentation of the spinal cord and lesions from MRI data provides measures of damage, which are key criteria for the diagnosis, prognosis, and longitudinal monitoring in MS. Automating this operation eliminates inter-rater variability and increases the efficiency of large-throughput analysis pipelines. Robust and reliable segmentation across multi-site spinal cord data is challenging because of the large variability related to acquisition parameters and image artifacts. In particular, a precise delineation of lesions is hindered by a broad heterogeneity of lesion contrast, size, location, and shape. The goal of this study was to develop a fully-automatic framework - robust to variability in both image parameters and clinical condition - for segmentation of the spinal cord and intramedullary MS lesions from conventional MRI data of MS and non-MS cases. Scans of 1042 subjects (459 healthy controls, 471 MS patients, and 112 with other spinal pathologies) were included in this multi-site study (n = 30). Data spanned three contrasts (T1-, T2-, and T2∗-weighted) for a total of 1943 vol and featured large heterogeneity in terms of resolution, orientation, coverage, and clinical conditions. The proposed cord and lesion automatic segmentation approach is based on a sequence of two Convolutional Neural Networks (CNNs). To deal with the very small proportion of spinal cord and/or lesion voxels compared to the rest of the volume, a first CNN with 2D dilated convolutions detects the spinal cord centerline, followed by a second CNN with 3D convolutions that segments the spinal cord and/or lesions. CNNs were trained independently with the Dice loss. When compared against manual segmentation, our CNN-based approach showed a median Dice of 95% vs. 88% for PropSeg (p ≤ 0.05), a state-of-the-art spinal cord segmentation method. Regarding lesion segmentation on MS data, our framework provided a Dice of 60%, a relative volume difference of -15%, and a lesion-wise detection sensitivity and precision of 83% and 77%, respectively. In this study, we introduce a robust method to segment the spinal cord and intramedullary MS lesions on a variety of MRI contrasts. The proposed framework is open-source and readily available in the Spinal Cord Toolbox.

One-shot domain adaptation in multiple sclerosis lesion segmentation using convolutional neural networks

In recent years, several convolutional neural network (CNN) methods have been proposed for the automated white matter lesion segmentation of multiple sclerosis (MS) patient images, due to their superior performance compared with those of other state-of-the-art methods. However, the accuracies of CNN methods tend to decrease significantly when evaluated on different image domains compared with those used for training, which demonstrates the lack of adaptability of CNNs to unseen imaging data. In this study, we analyzed the effect of intensity domain adaptation on our recently proposed CNN-based MS lesion segmentation method. Given a source model trained on two public MS datasets, we investigated the transferability of the CNN model when applied to other MRI scanners and protocols, evaluating the minimum number of annotated images needed from the new domain and the minimum number of layers needed to re-train to obtain comparable accuracy. Our analysis comprised MS patient data from both a clinical center and the public ISBI2015 challenge database, which permitted us to compare the domain adaptation capability of our model to that of other state-of-the-art methods. In both datasets, our results showed the effectiveness of the proposed model in adapting previously acquired knowledge to new image domains, even when a reduced number of training samples was available in the target dataset. For the ISBI2015 challenge, our one-shot domain adaptation model trained using only a single case showed a performance similar to that of other CNN methods that were fully trained using the entire available training set, yielding a comparable human expert rater performance. We believe that our experiments will encourage the MS community to incorporate its use in different clinical settings with reduced amounts of annotated data. This approach could be meaningful not only in terms of the accuracy in delineating MS lesions but also in the related reductions in time and economic costs derived from manual lesion labeling.

•

We analyzed the effect of intensity domain adaptation on CNN MS lesion segmentation.

•

We evaluated the minimum number of images and layers needed to re-train the model.

•

The model showed good adaptation even when trained on very few or a single case.

•

The performance of models trained on one case was similar to other fully-trained CNN.

•

On ISBI0215, our model trained on one case was comparable to human rate performance.