White Matter Lesion Segmentation Research Articles

LST-AI: A deep learning ensemble for accurate MS lesion segmentation

Automated segmentation of brain white matter lesions is crucial for both clinical assessment and scientific research in multiple sclerosis (MS). Over a decade ago, we introduced an engineered lesion segmentation tool, LST. While recent lesion segmentation approaches have leveraged artificial intelligence (AI), they often remain proprietary and difficult to adopt. As an open-source tool, we present LST-AI, an advanced deep learning-based extension of LST that consists of an ensemble of three 3D U-Nets.LST-AI explicitly addresses the imbalance between white matter (WM) lesions and non-lesioned WM. It employs a composite loss function incorporating binary cross-entropy and Tversky loss to improve segmentation of the highly heterogeneous MS lesions. We train the network ensemble on 491 MS pairs of T1-weighted and FLAIR images, collected in-house from a 3T MRI scanner, and expert neuroradiologists manually segmented the utilized lesion maps for training. LST-AI also includes a lesion location annotation tool, labeling lesions as periventricular, infratentorial, and juxtacortical according to the 2017 McDonald criteria, and, additionally, as subcortical. We conduct evaluations on 103 test cases consisting of publicly available data using the Anima segmentation validation tools and compare LST-AI with several publicly available lesion segmentation models.Our empirical analysis shows that LST-AI achieves superior performance compared to existing methods. Its Dice and F1 scores exceeded 0.62, outperforming LST, SAMSEG (Sequence Adaptive Multimodal SEGmentation), and the popular nnUNet framework, which all scored below 0.56. Notably, LST-AI demonstrated exceptional performance on the MSSEG-1 challenge dataset, an international WM lesion segmentation challenge, with a Dice score of 0.65 and an F1 score of 0.63—surpassing all other competing models at the time of the challenge. With increasing lesion volume, the lesion detection rate rapidly increased with a detection rate of >75% for lesions with a volume between 10 mm3 and 100 mm3. Given its higher segmentation performance, we recommend that research groups currently using LST transition to LST-AI. To facilitate broad adoption, we are releasing LST-AI as an open-source model, available as a command-line tool, dockerized container, or Python script, enabling diverse applications across multiple platforms.

HACA3: A unified approach for multi-site MR image harmonization.

The lack of standardization and consistency of acquisition is a prominent issue in magnetic resonance (MR) imaging. This often causes undesired contrast variations in the acquired images due to differences in hardware and acquisition parameters. In recent years, image synthesis-based MR harmonization with disentanglement has been proposed to compensate for the undesired contrast variations. The general idea is to disentangle anatomy and contrast information from MR images to achieve cross-site harmonization. Despite the success of existing methods, we argue that major improvements can be made from three aspects. First, most existing methods are built upon the assumption that multi-contrast MR images of the same subject share the same anatomy. This assumption is questionable, since different MR contrasts are specialized to highlight different anatomical features. Second, these methods often require a fixed set of MR contrasts for training (e.g., both T1-weighted and T2-weighted images), limiting their applicability. Lastly, existing methods are generally sensitive to imaging artifacts. In this paper, we present Harmonization with Attention-based Contrast, Anatomy, and Artifact Awareness (HACA3), a novel approach to address these three issues. HACA3 incorporates an anatomy fusion module that accounts for the inherent anatomical differences between MR contrasts. Furthermore, HACA3 can be trained and applied to any combination of MR contrasts and is robust to imaging artifacts. HACA3 is developed and evaluated on diverse MR datasets acquired from 21 sites with varying field strengths, scanner platforms, and acquisition protocols. Experiments show that HACA3 achieves state-of-the-art harmonization performance under multiple image quality metrics. We also demonstrate the versatility and potential clinical impact of HACA3 on downstream tasks including white matter lesion segmentation for people with multiple sclerosis and longitudinal volumetric analyses for normal aging subjects. Code is available at https://github.com/lianruizuo/haca3.

BIANCA-MS: An optimized tool for automated multiple sclerosis lesion segmentation.

In this work we present BIANCA-MS, a novel tool for brain white matter lesion segmentation in multiple sclerosis (MS), able to generalize across both the wide spectrum of MRI acquisition protocols and the heterogeneity of manually labeled data. BIANCA-MS is based on the original version of BIANCA and implements two innovative elements: a harmonized setting, tested under different MRI protocols, which avoids the need to further tune algorithm parameters to each dataset; and a cleaning step developed to improve consistency in automated and manual segmentations, thus reducing unwanted variability in output segmentations and validation data. BIANCA-MS was tested on three datasets, acquired with different MRI protocols. First, we compared BIANCA-MS to other widely used tools. Second, we tested how BIANCA-MS performs in separate datasets. Finally, we evaluated BIANCA-MS performance on a pooled dataset where all MRI data were merged. We calculated the overlap using the DICE spatial similarity index (SI) as well as the number of false positive/negative clusters (nFPC/nFNC) in comparison to the manual masks processed with the cleaning step. BIANCA-MS clearly outperformed other available tools in both high- and low-resolution images and provided comparable performance across different scanning protocols, sets of modalities and image resolutions. BIANCA-MS performance on the pooled dataset (SI: 0.72 ± 0.25, nFPC: 13 ± 11, nFNC: 4 ± 8) were comparable to those achieved on each individual dataset (median across datasets SI: 0.72 ± 0.28, nFPC: 14 ± 11, nFNC: 4 ± 8). Our findings suggest that BIANCA-MS is a robust and accurate approach for automated MS lesion segmentation.

Abstract WMP52: Markers Of Endothelial Glycocalyx Damage In Patients Withvascular Cognitive Impairment Associated With Cerebral Small Vessel Disease

Introduction: Cerebral small vessel disease (cSVD) involves a myriad of pathogenic mechanisms affecting small vessels of the brain, leading to a significant impact on motor and cognitive functions, and it is the main cause of Vascular cognitive impairment (VCI). The endothelial glycocalyx (EG), the layer lining the vascular endothelium, has a pivotal player in maintaining the proper function of neurovascular unit, and its degradation may be involved in VCI due to cSVD. Objectives: to investigate the relationship between markers of EG damage and VCI related to cSVD. Methods: Cross-sectional study based on clinical data and serum samples for the quantification of EG damage markers (syndecan-1, hyaluran) of VCI related to cSVD patients and of a control group derived from a dataset of healthy workers from the same institution. We used an automatic logarithm for segmentation and volumetric evaluation of white matter lesions on brain MRI of the patients. Logistic regression models and c-statistics were used to identify the independent variables related to VCI and investigate the accuracy of syndecan-1 to detect VCI. We studied the association of thebiomarkers and MoCA scores, index of independence in activities of daily living and whitematter lesion burden respectively. Results: Between July 2019 and March 2020, we studied 22 patients with VCI associated with cSVD and compared them with a dataset of 22 healthy workers from the same institution. Patients with VCI were older, had a higher prevalence of diabetesmellitus and hypertension, had a worse index of independence for daily activities, and higherlevels of syndecan-1 (78,4 vs 24; p < 0,01). There was no difference in hyaluran levels between both groups. In multivariate analysis, only age (OR 1,35;CI 1,04 - 1,76; p = 0,02) and syndecan-1 levels (OR 1,08;CI 1,01 - 1,15;p = 0,01) related to VCI. The ROC curve ofsyndecan-1 levels to predict VCI had a area under de curve of 0,78 (CI 0,64 - 0,92) and there was a correlation between syndecan-1 levels and MoCA scores (rho = - 0,34;p = 0,02). There were no correlations between syndecan-1 and hyaluran levels and index of independence and white matter lesion burden respectively. Conclusions: Syndecan-1, but not hyaluran, is a potential biomarker for VCI associated with cSVD.

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

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

White Matter Lesion Segmentation for Multiple Sclerosis Patients implementing deep learning.

The aim of this work is to address the problem of White Matter Lesion (WML) segmentation employing Magnetic Resonance Imaging (MRI) images from Multiple Sclerosis (MS) patients through the application of deep learning. A U-net based architecture containing a contrastive path and an expanding path prior to the final pixel-wise classification is implemented. The data are provided by the Ippokratio Radiology Center of Ioannina and include Fluid-Attenuated Inversion Recovery (FLAIR) MRI images from 30 patients in three phases, baseline and two follow ups. The prediction results are quite significant in terms of pixel-wise classification. The implemented deep learning model demonstrates Dice coefficient 0.7292, Precision 75.92% and Recall 70.16% in 2D slices of FLAIR MRI non-skull stripped images.

Rest-activity rhythms and tract specific white matter lesions in older adults at risk for cognitive decline

White matter lesions (WMLs) are common in older adults and represent an important predictor of negative long-term outcomes. Rest-activity rhythm disturbance is also common, however, few studies have investigated associations between these factors. We employed a novel AI-based automatic WML segmentation tool and diffusion-weighted tractography to investigate associations between tract specific WML volumes and non-parametric actigraphy measures in older adults at risk for cognitive decline. The primary non-parametric measures of interest were inter-daily stability (IS), intra-daily variability and relative amplitude, with the anterior thalamic radiation (ATR), superior longitudinal fasciculus (SLF) and inferior longitudinal fasciculus (ILF) selected as tracts of interest. One hundred and eight participants at risk for cognitive decline (classified as experiencing subjective or objective cognitive decline) were included (mean age = 68.85 years, SD = 8.91). Of the primary non-parametric measures of interest, results showed that lower IS was associated with a greater likelihood of higher WML burden in the ATR (OR = 1.82, 95% CI [1.12,3.15]). Analysis of secondary non-parametric measures revealed later onset of the least active period to be associated with greater likelihood of high WML burden in the SLF (OR = 1.55, 95% CI [1.00,2.53]) and increased activity during the least active 5-h period to be associated with a greater likelihood of high whole-brain WML burden (OR = 1.83, 95% CI [1.06,3.47]). This study shows integrity of the ATR and SLF, and overall WML burden is linked to altered rest-activity rhythms in older adults at risk for cognitive decline, with those demonstrating altered rest-activity rhythms showing 50%-80% higher odds of having high WML burden.

A polynomial regression-based approach to estimate relaxation rate maps suitable for multiparametric segmentation of clinical brain MRI studies in multiple sclerosis

Background and ObjectiveRelaxation parameter maps (RPMs) calculated from spin-echo data have provided a basis for the segmentation of normal brain tissues and white matter lesions in multiple sclerosis (MS) MRI studies. However, Conventional Spin-Echo (CSE) sequences, once the core of clinical MRI studies, have been largely replaced by faster ones, which do not allow the calculation a-posteriori of RPMs from clinical studies. Aim of the study was to develop and validate a method to estimate RPMs (pseudo-RPMs) from routine clinical MRI protocols (including 3D-Gradient Echo T1w, FLAIR and fast-T2w sequences), suitable for fully automatic multiparametric segmentation of normal-appearing and pathological brain tissues in MS. MethodsThe proposed method processes spatially normalized clinical MRI studies through a multistep pipeline, to collect a set of data points of matched signal intensities (from MRI studies) and relaxation parameters (from a CSE-derived digital template and an MS lesion database), which are then fitted by a multiple and multivariate 4-th degree polynomial regression, providing pseudo-RPMs. The method was applied to a dataset of 59 clinical MRI studies providing pseudo-RPMs that were segmented through a method originally developed for the CSE-derived RPMs. Results of the segmentation in 12 studies were used to iteratively optimize method parameters. Accuracy of segmentation of normal-appearing brain tissues from the pseudo-RPMs was assessed by comparing their age-related changes, as measured in 47 clinical studies, against those measured acquired using CSE sequences in a comparable dataset of 47 patients. Lesion segmentation was validated against manual segmentation carried out by three neuroradiologists. ResultsAge-related changes of normal-appearing brain tissue volumes measured using the pseudo-RPMs substantially overlapped those measured using the RPMs obtained from CSE sequences, and segmentation of MS lesions showed a moderate-high spatial overlap with manual segmentation, comparable to that achieved by the widely used Lesion Segmentation Tool on FLAIR images, with a greater volumetric agreement. ConclusionsThe proposed approach allows calculation from clinical studies of pseudo-RPMs, which are equivalent to those obtainable from CSE sequences, avoiding the need for the acquisition of additional, dedicated sequences for segmentation purposes.

Higher-resolution quantification of white matter hypointensities by large-scale transfer learning from 2D images on the JPSC-AD cohort.

White matter lesions (WML) commonly occur in older brains and are quantifiable on MRI, often used as a biomarker in Aging research. Although algorithms are regularly proposed that identify these lesions from T2‐fluid‐attenuated inversion recovery (FLAIR) sequences, none so far can estimate lesions directly from T1‐weighted images with acceptable accuracy. Since 3D T1 is a polyvalent and higher‐resolution sequence, it could be beneficial to obtain the distribution of WML directly from it. However a serious difficulty, both for algorithms and human, can be found in the ambiguities of brain signal intensity in T1 images. This manuscript shows that a cross‐domain ConvNet (Convolutional Neural Network) approach can help solve this problem. Still, this is non‐trivial, as it would appear to require a large and varied dataset (for robustness) labelled at the same high resolution (for spatial accuracy). Instead, our model was taught from two‐dimensional FLAIR images with a loss function designed to handle the super‐resolution need. And crucially, we leveraged a very large training set for this task, the recently assembled, multi‐sites Japan Prospective Studies Collaboration for Aging and Dementia (JPSC‐AD) cohort. We describe the two‐step procedure that we followed to handle such a large number of imperfectly labeled samples. A large‐scale accuracy evaluation conducted against FreeSurfer 7, and a further visual expert rating revealed that WML segmentation from our ConvNet was consistently better. Finally, we made a directly usable software program based on that trained ConvNet model, available at https://github.com/bthyreau/deep-T1-WMH.

Detection of subtle white matter lesions in MRI through texture feature extraction and boundary delineation using an embedded clustering strategy

White matter lesions (WML) underlie multiple brain disorders, and automatic WML segmentation is crucial to evaluate the natural disease course and effectiveness of clinical interventions, including drug discovery. Although recent research has achieved tremendous progress in WML segmentation, accurate detection of subtle WML present early in the disease course remains particularly challenging. Here we propose an approach to automatic WML segmentation of mild WML loads using an intensity standardisation technique, gray level co-occurrence matrix (GLCM) embedded clustering technique, and random forest (RF) classifier to extract texture features and identify morphology specific to true WML. We precisely define their boundaries through a local outlier factor (LOF) algorithm that identifies edge pixels by local density deviation relative to its neighbors. The automated approach was validated on 32 human subjects, demonstrating strong agreement and correlation (excluding one outlier) with manual delineation by a neuroradiologist through Intra-Class Correlation (ICC = 0.881, 95% CI 0.769, 0.941) and Pearson correlation (r = 0.895, p-value < 0.001), respectively, and outperforming three leading algorithms (Trimmed Mean Outlier Detection, Lesion Prediction Algorithm, and SALEM-LS) in five of the six established key metrics defined in the MICCAI Grand Challenge. By facilitating more accurate segmentation of subtle WML, this approach may enable earlier diagnosis and intervention.

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.

A deep learning algorithm for white matter hyperintensity lesion detection and segmentation.

White matter hyperintensity (WMHI) lesions on MR images are an important indication of various types of brain diseases that involve inflammation and blood vessel abnormalities. Automated quantification of the WMHI can be valuable for the clinical management of patients, but existing automated software is often developed for a single type of disease and may not be applicable for clinical scans with thick slices and different scanning protocols. The purpose of the study is to develop and validate an algorithm for automatic quantification of white matter hyperintensity suitable for heterogeneous MRI data with different disease types. We developed and evaluated "DeepWML", a deep learning method for fully automated white matter lesion (WML) segmentation of multicentre FLAIR images. We used MRI from 507 patients, including three distinct white matter diseases, obtained in 9 centres, with a wide range of scanners and acquisition protocols. The automated delineation tool was evaluated through quantitative parameters of Dice similarity, sensitivity and precision compared to manual delineation (gold standard). The overall median Dice similarity coefficient was 0.78 (range 0.64 ~ 0.86) across the three disease types and multiple centres. The median sensitivity and precision were 0.84 (range 0.67 ~ 0.94) and 0.81 (range 0.64 ~ 0.92), respectively. The tool's performance increased with larger lesion volumes. DeepWML was successfully applied to a wide spectrum of MRI data in the three white matter disease types, which has the potential to improve the practical workflow of white matter lesion delineation.

BIANCA-MS: A novel artificial intelligence tool for multiple sclerosis automated lesions segmentation

Automated white matter lesions segmentation in multiple sclerosis (MS) is still an open field and no standardized approach has been widely employed yet. We aim to validate BIANCA-MS, a novel tool for MS lesions segmentation on brain MRI, based on the original version of BIANCA (https://fsl.fmrib.ox.ac.uk/fsl/fslwiki) and which implemented: i) a harmonized setting tested under different conditions, avoiding the need to further tune algorithm parameters to each dataset; ii) a post-processing cleaning step to refine lesion segmentation.

Automated quantification of deep grey matter structures and white matter lesions using magnetic resonance imaging in relapsing remission multiple sclerosis

BackgroundBrain volume loss (BVL) is widespread in MS and occurs throughout the disease course at a rate considerably greater than in the general population. In MS, brain volume correlates with and predicts future disability, making BVL a relevant measure of diffuse CNS damage leading to clinical disease progression, as well as serving as a useful outcome in evaluating MS therapies. The aim of our study was to evaluate the role of automated segmentation and quantification of deep grey matter structures and white matter lesions in Relapsing Remitting Multiple Sclerosis patients using MR images and to correlate the volumetric results with different degrees of disability based on expanded disability status scale (EDSS) scores.ResultsAll the patients in our study showed relative atrophy of the thalamus and the putamen bilaterally when compared with the normal control group. Statistical analysis was significant for the thalamus and the putamen atrophy (P value < 0.05). On the other hand, statistical analysis was not significant for the caudate and the hippocampus (P value > 0.05); there was a significant positive correlation between the white matter lesions volume and EDSS scores (correlation coefficient of 0.7505). On the other hand, there was a significant negative correlation between the thalamus and putamen volumes, and EDSS scores (correlation coefficients < − 0.9), while the volumes of the caudate and the hippocampus had a very weak and non-significant correlation with the EDSS scores (correlation coefficients > − 0.35).ConclusionsThe automated segmentation and quantification tools have a great role in the assessment of brain structural changes in RRMS patients, and that it became essential to integrate these tools in the daily medical practice for the great value they add to the current evaluation measures.

Segmentation of white matter lesions in multicentre FLAIR MRI

White matter lesions (WML) in the brain are thought to be related to ischemic processes, demyelination, and axonal degeneration. The presence of WML predict cognitive decline, dementia, stroke, and death. Lesion progression increases these risks, making WML significant clinical biomarkers for investigation. To analyze WML objectively, consistently, and efficiently, automated WML segmentation methods for neurological MRI have been the focus of extensive research efforts. There have been many unsupervised and traditional machine learning methods proposed over the years. Recently, deep learning architectures have been utilized for WML segmentation with promising results. In this work, we evaluate seven WML segmentation tools for multicentre fluid attenuated inversion recovery (FLAIR) MRI. Two traditional methods were evaluated, one unsupervised method and the other a traditional machine learning approach. The traditional methods were compared to five deep learning-based approaches. FLAIR MRI have the advantage of highlighting WML lesions robustly and are used routinely in neurological workflows. Automated WML segmentation tools for FLAIR MRI could optimize clinical workflows and improve patient care. The WML segmentation algorithms were evaluated on a multicentre, multi-disease FLAIR MRI database acquired with varying scanners and protocols. In total 252 imaging volumes (~13 K image slices) with annotations, from 5 multicentre datasets (33 imaging centres) were used to train, validate and test the WML segmentation methods. Two clinical datasets, which include dementia and vascular disease pathologies, and three open-source datasets were used. To examine clinical utility of each algorithm and establish proof of effectiveness, algorithms were evaluated over several dimensions related to accuracy, generalizability, and robustness to pathology. This work presents a framework for evaluating the efficacy of WML segmentation algorithms for improved reliability, patient safety and clinical trials. Of all methods, SC U-Net was found to be the best algorithm for WML segmentation in terms of highest Dice similarity coefficient (DSC) over most dimensions (mean DSC = 0.71 over all volumes). Deep learning methods outperformed traditional methods, especially in lower lesion loads, but were not able to generalize across all disease categories or datasets.

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

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. 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. 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). 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.

Bioinspired Inference System for MR Image Segmentation and Multiple Sclerosis Detection

Multiple sclerosis (MS) is a chronic autoimmune and inflammatory disease affecting the central nervous system (CNS). Magnetic resonance imaging (MRI) provides sufficient imaging contrast to visualize and detect MS lesions, particularly those in the white matter (WM). A robust and precise segmentation of WM lesions from MRI provide essential information about the disease status and evolution. The proposed FPSOPCM segmentation algorithm included an initial segmentation step using fuzzy particle swarm optimization (FPSO). After extraction of WM, atypical data (outliers) is eliminated using possibilistic C-means (PCM) algorithm, and finally, a Mamdani-type fuzzy model was applied to identify MS. The objective of the work presented in this paper is to obtain an improved accuracy in segmentation of MR images for MS detection.

Simultaneous lesion and brain segmentation in multiple sclerosis using deep neural networks

Segmentation of white matter lesions and deep grey matter structures is an important task in the quantification of magnetic resonance imaging in multiple sclerosis. In this paper we explore segmentation solutions based on convolutional neural networks (CNNs) for providing fast, reliable segmentations of lesions and grey-matter structures in multi-modal MR imaging, and the performance of these methods when applied to out-of-centre data. We trained two state-of-the-art fully convolutional CNN architectures on the 2016 MSSEG training dataset, which was annotated by seven independent human raters: a reference implementation of a 3D Unet, and a more recently proposed 3D-to-2D architecture (DeepSCAN). We then retrained those methods on a larger dataset from a single centre, with and without labels for other brain structures. We quantified changes in performance owing to dataset shift, and changes in performance by adding the additional brain-structure labels. We also compared performance with freely available reference methods. Both fully-convolutional CNN methods substantially outperform other approaches in the literature when trained and evaluated in cross-validation on the MSSEG dataset, showing agreement with human raters in the range of human inter-rater variability. Both architectures showed drops in performance when trained on single-centre data and tested on the MSSEG dataset. When trained with the addition of weak anatomical labels derived from Freesurfer, the performance of the 3D Unet degraded, while the performance of the DeepSCAN net improved. Overall, the DeepSCAN network predicting both lesion and anatomical labels was the best-performing network examined.

FLAIR-only joint volumetric analysis of brain lesions and atrophy in clinically isolated syndrome (CIS) suggestive of multiple sclerosis

BackgroundMRI assessment in multiple sclerosis (MS) focuses on the presence of typical white matter (WM) lesions. Neurodegeneration characterised by brain atrophy is recognised in the research field as an important prognostic factor. It is not routinely reported clinically, in part due to difficulty in achieving reproducible measurements. Automated MRI quantification of WM lesions and brain volume could provide important clinical monitoring data. In general, lesion quantification relies on both T1 and FLAIR input images, while tissue volumetry relies on T1. However, T1-weighted scans are not routinely included in the clinical MS protocol, limiting the utility of automated quantification. ObjectivesWe address an aspect of this important translational challenge by assessing the performance of FLAIR-only lesion and brain segmentation, against a conventional approach requiring multi-contrast acquisition. We explore whether FLAIR-only grey matter (GM) segmentation yields more variability in performance compared with two-channel segmentation; whether this is related to field strength; and whether the results meet a level of clinical acceptability demonstrated by the ability to reproduce established biological associations. MethodsWe used a multicentre dataset of subjects with a CIS suggestive of MS scanned at 1.5T and 3T in the same week. WM lesions were manually segmented by two raters, ‘manual 1′ guided by consensus reading of CIS-specific lesions and ‘manual 2′ by any WM hyperintensity. An existing brain segmentation method was adapted for FLAIR-only input. Automated segmentation of WM hyperintensity and brain volumes were performed with conventional (T1/T1 + FLAIR) and FLAIR-only methods. ResultsWM lesion volumes were comparable at 1.5T between ‘manual 2′ and FLAIR-only methods and at 3T between ‘manual 2′, T1 + FLAIR and FLAIR-only methods. For cortical GM volume, linear regression measures between conventional and FLAIR-only segmentation were high (1.5T: α = 1.029, R2 = 0.997, standard error (SE) = 0.007; 3T: α = 1.019, R2 = 0.998, SE = 0.006). Age-associated change in cortical GM volume was a significant covariate in both T1 (p = 0.001) and FLAIR-only (p = 0.005) methods, confirming the expected relationship between age and GM volume for FLAIR-only segmentations. ConclusionsFLAIR-only automated segmentation of WM lesions and brain volumes were consistent with results obtained through conventional methods and had the ability to demonstrate biological effects in our study population. Imaging protocol harmonisation and validation with other MS phenotypes could facilitate the integration of automated WM lesion volume and brain atrophy analysis as clinical tools in radiological MS reporting.

Performance comparison of automated white matter lesion segmentation algorithms in the DELCODE Study

AbstractBackgroundWhite matter hyperintensities (WMH), derived from T2‐weighted MRI, represent a sensitive imaging marker of cerebrovascular disease. To investigate WMH in large‐scale multicenter clinical studies, appropriate automated WMH segmentation algorithms are required. Therefore, prior evaluation of these methods is important, especially due to additional challenges posed by the multicenter acquisition. We assessed performance of different WMH segmentation algorithms compared to manual segmentation (reference) in the multicenter DZNE‐Longitudinal Cognitive Impairment and Dementia Study (DELCODE).MethodWMH segmentations were performed on a preliminary randomly‐selected dataset of 20 participants that included FLAIR images from different diagnostic groups across the AD continuum, various study sites and Siemens 3T scanner models. We used freely‐available and fully‐automated WMH segmentation methods, i.e. LST‐LGA, LST‐LPA, and Sysu_Media, the winner of the MICCAI WMH segmentation challenge. Performance of the algorithms was compared to reference segmentation using volumetric and spatial correspondence indices, intraclass correlation coefficient (ICC), Dice’s similarity coefficients (DSC), recall (sensitivity), and precision (positive predictive value), across the whole brain and with respect to the number of detected clusters.ResultPreliminary analyses (n=20, example in Fig.1) indicated that mean WMH volumes, estimated by the algorithms, were lower compared to reference, except for Sysu_Media. Volumetric agreement with reference segmentation was moderate‐to‐high across methods (best: Sysu_Media, ICC=0.9). Mean global DSCs were moderate (best: Sysu_Media, DSC=0.6±0.2), with better performance for larger compared to lower WMH load. Mean number of clusters, detected by the algorithms, was lower compared to reference, except for Sysu_Media that overestimated this value. Mean DSCs for clusters were also moderate for all algorithms (best: Sysu_Media, DSC=0.5±0.2). Mean precision of detected WMH load and number of clusters was higher than mean recall (sensitivity) across all methods, except for Sysu_Media.ConclusionThese preliminary findings show that performance of different automated WMH segmentations is relatively similar. Although most algorithms correctly identify WMH (higher precision), the methods underestimate total WMH load (lower sensitivity). The Sysu_Media algorithm performs best in many indices, however, it yielded lowest precision in number of clusters. Results of the final sample (n=40) will be presented, intended to serve as a method guide for conducting WMH segmentations in the multicenter DELCODE study.