Fully automated detection of paramagnetic rims in multiple sclerosis lesions on 3T susceptibility-based MR imaging

New approaches to lesion assessment in multiple sclerosis

PURPOSE OF REVIEW

To summarize recent advancements in artificial intelligence-driven lesion segmentation and novel neuroimaging modalities that enhance the identification and characterization of multiple sclerosis (MS) lesions, emphasizing their implications for clinical use and research.

RECENT FINDINGS

Artificial intelligence, particularly deep learning approaches, are revolutionizing MS lesion assessment and segmentation, improving accuracy, reproducibility, and efficiency. Artificial intelligence-based tools now enable automated detection not only of T2-hyperintense white matter lesions, but also of specific lesion subtypes, including gadolinium-enhancing, central vein sign-positive, paramagnetic rim, cortical, and spinal cord lesions, which hold diagnostic and prognostic value. Novel neuroimaging techniques such as quantitative susceptibility mapping (QSM), χ-separation imaging, and soma and neurite density imaging (SANDI), together with PET, are providing deeper insights into lesion pathology, better disentangling their heterogeneities and clinical relevance.

SUMMARY

Artificial intelligence-powered lesion segmentation tools hold great potential for improving fast, accurate and reproducible lesional assessment in the clinical scenario, thus improving MS diagnosis, monitoring, and treatment response assessment. Emerging neuroimaging modalities may contribute to advance the understanding MS pathophysiology, provide more specific markers of disease progression, and novel potential therapeutic targets.

The role of AI for MRI-analysis in multiple sclerosis-A brief overview

Magnetic resonance imaging (MRI) has played a crucial role in the diagnosis, monitoring and treatment optimization of multiple sclerosis (MS). It is an essential component of current diagnostic criteria for its ability to non-invasively visualize both lesional and non-lesional pathology. Nevertheless, modern day usage of MRI in the clinic is limited by lengthy protocols, error-prone procedures for identifying disease markers (e.g., lesions), and the limited predictive value of existing imaging biomarkers for key disability outcomes. Recent advances in artificial intelligence (AI) have underscored the potential for AI to not only improve, but also transform how MRI is being used in MS. In this short review, we explore the role of AI in MS applications that span the entire life-cycle of an MRI image, from data collection, to lesion segmentation, detection, and volumetry, and finally to downstream clinical and scientific tasks. We conclude with a discussion on promising future directions.

Conventional and Advanced Magnetic Resonance Imaging Biomarkers of Multiple Sclerosis in the Brain

Multiple sclerosis (MS) is a heterogeneous disease, and each MS patient exhibits different clinical symptoms that are reflected in their magnetic resonance imaging (MRI) results. Each MS lesion should be interpreted carefully and evaluated in conjunction with a clinical examination. MRI plays a major role in evaluating how MS lesions are aggregated in the central nervous system and how they change over time. There are several conventional MRI biomarkers of MS that could be utilized to evaluate each MS phenotype. MRI is useful for clinical decisions, aiding in the determination of disease-modifying treatment or disease prognosis. Despite its higher sensitivity, MRI provides low specificity due to the heterogeneity of MS lesions. However, advanced MRI biomarkers show promise in terms of defining MS lesions, as each imaging biomarker correlates differently with the clinical scenario of each MS phenotype. The aim of this review is to summarise the current state of MRI biomarkers for MS in the brain and how they relate to neurological disabilities.

Determinants of long-term paramagnetic rim lesion evolution in people with multiple sclerosis

OBJECTIVE

Baseline paramagnetic rim lesion (PRL) load predicts disease progression in people with multiple sclerosis (pwMS). Understanding how PRLs relate to other known MS-related factors, and the practical utility of PRLs in clinical trials, is crucial for informing clinical decision-making and guiding development of novel disease-modifying treatments (DMTs).

METHODS

This study included 152 pwMS enrolled in a larger prospective, longitudinal cohort study who had 3T MRI scans and clinical assessments at baseline and 5- or 10-year follow-ups. PRLs were identified on baseline 3T quantitative susceptibility maps and classified as persisting, disappearing, or newly appearing at follow-up. The relationships between PRL evolution and clinical, radiological, environmental, and genetic characteristics were assessed, and clinical trial sample sizes were estimated using PRL appearance or disappearance as outcome measures.

RESULTS

DMT use was associated with lower odds of new PRL appearance (for high-efficacy DMTs: odds ratio = 0.088, p = 0.024), but not disappearance. Current smoking status was associated with greater baseline PRL number (B = 0.527 additional PRLs, p = 0.013). A 24-month clinical trial in people with progressive MS for a DMT that doubles the rate of PRL rim disappearance would require an estimated 118 people with progressive MS per group at 80% statistical power.

INTERPRETATION

Early MS diagnosis and subsequent DMT initiation may reduce new chronic active inflammation. However, the utility of PRL disappearance or new PRL appearance as outcome measures in clinical trials is limited by potentially large sample sizes that are needed for moderate efficacy drugs.

Reliability of paramagnetic rim lesion detection at 1.5T MRI in multiple sclerosis patients

BACKGROUND

Paramagnetic rim lesions (PRL) are valuable for diagnosing and prognosing multiple sclerosis (MS) and detectable at 7T and 3T MRI. For translation into clinical practice, it is essential assessing their visibility on 1.5T clinical scanners.

OBJECTIVE

To evaluate the reliability of detecting PRL using commercially available susceptibility-weighted imaging (SWI) at 1.5 versus 3T MRI.

METHODS

SWI images were obtained in 20 people with MS at 1.5T and 3T MRI, with an average scan interval of 1.1 years. Only stable, non-enhancing lesions visible on both scans were analyzed. PRL at 3T were identified by two expert raters using NAIMS PRL criteria and used as a reference. Four raters, blinded to 3T results, assessed PRL at 1.5T. Discrepancies were resolved by consensus.

RESULTS

PRL were identified in 16 of 20 patients. At 3T, 95 PRL were identified by consensus (mean 5 PRL per patient, range 0-30). Blinded to 3T scans, 82% of PRL were visible at 1.5T (78 of 95 PRL). Interrater reliability was "almost perfect" for both 1.5 and 3T scans. Raters accurately classified all patients as having ⩾1PRL or not at 1.5T.

CONCLUSION

The majority of PRL are detectable at 1.5T without significantly reducing the specificity of PRL identification or increasing the detection of pseudo-PRL. This may facilitate their clinical use in MS diagnosis and prognosis.

Chronic active lesions in multiple sclerosis: classification, terminology, and clinical significance

In multiple sclerosis (MS), increasing disability is considered to occur due to persistent, chronic inflammation trapped within the central nervous system (CNS). This condition, known as smoldering neuroinflammation, is present across the clinical spectrum of MS and is currently understood to be relatively resistant to treatment with existing disease-modifying therapies. Chronic active white matter lesions represent a key component of smoldering neuroinflammation. Initially characterized in autopsy specimens, multiple approaches to visualize chronic active lesions (CALs) in vivo using advanced neuroimaging techniques and postprocessing methods are rapidly emerging. Among these in vivo imaging correlates of CALs, paramagnetic rim lesions (PRLs) are defined by the presence of a perilesional rim formed by iron-laden microglia and macrophages, whereas slowly expanding lesions are identified based on linear, concentric lesion expansion over time. In recent years, several longitudinal studies have linked the occurrence of in vivo detected CALs to a more aggressive disease course. PRLs are highly specific to MS and therefore have recently been incorporated into the MS diagnostic criteria. They also have prognostic potential as biomarkers to identify patients at risk of early and severe disease progression. These developments could significantly affect MS care and the evaluation of new treatments. This review describes the latest knowledge on CAL biology and imaging and the relevance of CALs to the natural history of MS. In addition, we outline considerations for current and future in vivo biomarkers of CALs, emphasizing the need for validation, standardization, and automation in their assessment.

Imaging Outcomes for Phase 2 Trials Targeting Compartmentalized Inflammation

This comprehensive review aims to explore imaging outcome measures targeting compartmentalized inflammation in Phase 2 clinical trials for multiple sclerosis (MS). The traditional primary imaging outcomes used in Phase 2 MS trials, new or enhancing white matter lesions on MRI, target the effects of peripheral inflammation, but the widespread inflammation behind a mostly closed blood-brain barrier is not captured. This review discusses several emerging imaging technologies that could be used as surrogate markers of compartmentalized inflammation, targeting chronic active lesions, meningeal inflammation, and innate immune activation within the normal-appearing white matter and gray matter. The integration of specific imaging outcomes into Phase 2 trials can provide a more accurate assessment of treatment efficacy, ultimately contributing to the development of more effective therapies for MS.

Prognostic significance of paramagnetic rim lesions in multiple sclerosis: A systematic review

The diagnostic potential of paramagnetic rim lesions (PRLs) has been previously established; however, the prognostic significance of these lesions has not previously been consistently described. This study aimed to establish the prognostic role of PRLs in MS with respect to the Expanded Disability Status Scale (EDSS) and rates of disability progression. Databases of PubMed, EMBASE, Scopus and reference lists of selected articles were searched up to 29/04/2023. The review was conducted in accordance with PRISMA guidelines and was registered prospectively on PROSPERO (CRD42023422052). 7 studies were included in the final review. All of the eligible studies found that patients with PRLs tend to have higher baseline EDSS scores. Longitudinal assessments revealed greater EDSS progression in patients with PRLs over time in most studies. However, the effect of location of PRLs within the central nervous system were not assessed across the studies. Only one study investigated progression independent of relapse activity (PIRA) and showed that this clinical entity occurred in a greater proportion in patients with PRLs. This review supports PRLs as a predictor of EDSS progression. This measure has widespread applicability, however further multicentre studies are needed. Future research should explore the impact of PRLs on silent disability, PIRA, take into account different MS phenotypes and the topography of PRLs in prognosis.

Multicenter validation of automated detection of paramagnetic rim lesions on brain MRI in multiple sclerosis

BACKGROUND AND PURPOSE

Paramagnetic rim lesions (PRLs) are an MRI biomarker of chronic inflammation in people with multiple sclerosis (MS). PRLs may aid in the diagnosis and prognosis of MS. However, manual identification of PRLs is time-consuming and prone to poor interrater reliability. To address these challenges, the Automated Paramagnetic Rim Lesion (APRL) algorithm was developed to automate PRL detection. The primary objective of this study is to evaluate the accuracy of APRL for detecting PRLs in a multicenter setting.

METHODS

We applied APRL to a multicenter dataset, which included 3-Tesla MRI acquired in 92 participants (43 with MS, 14 with clinically isolated syndrome [CIS]/radiologically isolated syndrome [RIS], 35 without RIS/CIS/MS). Subsequently, we assessed APRL's performance by comparing its results with manual PRL assessments carried out by a team of trained raters.

RESULTS

Among the 92 participants, expert raters identified 5637 white matter lesions and 148 PRLs. The automated segmentation method successfully captured 115 (78%) of the manually identified PRLs. Within these 115 identified lesions, APRL differentiated between manually identified PRLs and non-PRLs with an area under the curve (AUC) of .73 (95% confidence interval [CI]: [.68, .78]). At the subject level, the count of APRL-identified PRLs predicted MS diagnosis with an AUC of .69 (95% CI: [.57, .81]).

CONCLUSION

Our study demonstrated APRL's capability to differentiate between PRLs and lesions without paramagnetic rims in a multicenter study. Automated identification of PRLs offers greater efficiency over manual identification and could facilitate large-scale assessments of PRLs in clinical trials.

Imaging chronic active lesions in multiple sclerosis: a consensus statement

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

The T1-dark-rim: A novel imaging sign for detecting smoldering inflammation in multiple sclerosis

PURPOSE

Paramagnetic rim lesions (PRLs), usually identified in susceptibility-weighted imaging (SWI), are a promising prognostic biomarker of disability progression in multiple sclerosis (MS). However, SWI is not routinely performed in clinical practice. The objective of this study is to define a novel imaging sign, the T1-dark rim, identifiable in a standard 3DT1 gradient-echo inversion-recovery sequence, such as 3D T1 turbo field echo (3DT1FE) and explore its performance as a SWI surrogate to define PRLs.

METHODS

This observational cross-sectional study analyzed MS patients who underwent 3T magnetic resonance imaging (MRI) including 3DT1TFE and SWI. Rim lesions were evaluated in 3DT1TFE, processed SWI, and SWI phase and categorized as true positive, false positive, or false negative based on the value of the T1-dark rim in predicting SWI phase PRLs. Sensitivity and positive predictive values of the T1-dark rim for detecting PRLs were calculated.

RESULTS

Overall, 80 rim lesions were identified in 63 patients (60 in the SWI phase and 78 in 3DT1TFE; 58 true positives, 20 false positives, and two false negatives). The T1-dark rim demonstrated 97% sensitivity and 74% positive predictive value for detecting PRLs. More PRLs were detected in the SWI phase than in processed SWI (60 and 57, respectively).

CONCLUSION

The T1-dark rim sign is a promising and accessible novel imaging marker to detect PRLs whose high sensitivity may enable earlier detection of chronic active lesions to guide MS treatment escalation. The relevance of T1-dark rim lesions that are negative on SWI opens up a new field for analysis.

Neuroimaging characterization of multiple sclerosis lesions in pediatric patients: an exploratory radiomics approach

Introduction

Multiple sclerosis (MS), a chronic inflammatory immune-mediated disease of the central nervous system (CNS), is a common condition in young adults, but it can also affect children. The aim of this study was to construct radiomic models of lesions based on magnetic resonance imaging (MRI, T2-weighted-Fluid-Attenuated Inversion Recovery), to understand the correlation between extracted radiomic features, brain and lesion volumetry, demographic, clinical and laboratorial data.

Methods

The neuroimaging data extracted from eleven scans of pediatric MS patients were analyzed. A total of 60 radiomic features based on MR T2-FLAIR images were extracted and used to calculate gray level co-occurrence matrix (GLCM). The principal component analysis and ROC analysis were performed to select the radiomic features, respectively. The realized classification task by the logistic regression models was performed according to these radiomic features.

Results

Ten most relevant features were selected from data extracted. The logistic regression applied to T2-FLAIR radiomic features revealed significant predictor for multiple sclerosis (MS) lesion detection. Only the variable "contrast" was statistically significant, indicating that only this variable played a significant role in the model. This approach enhances the classification of lesions from normal tissue.

Discussion and conclusion

Our exploratory results suggest that the radiomic models based on MR imaging (T2-FLAIR) may have a potential contribution to characterization of brain tissues and classification of lesions in pediatric MS.

Central vein sign and paramagnetic rim sign: From radiologically isolated syndrome to multiple sclerosis

The widespread use of magnetic resonance imaging (MRI) has led to an increase in incidental findings in the central nervous system. Radiologically isolated syndrome (RIS) is a condition where imaging reveals lesions suggestive of demyelinating disease without any clinical episodes consistent with multiple sclerosis (MS). The prognosis for RIS patients is uncertain, with some remaining asymptomatic while others progress to MS. Several risk factors for disease progression have been identified, including male sex, younger age at diagnosis, and spinal cord lesions. This article reviews two promising biomarkers, the central vein sign (CVS) and the paramagnetic rim sign (PRS), and their potential role in the diagnosis and prognosis of MS and RIS. Both CVS and PRS have been shown to be accurate diagnostic markers in MS, with high sensitivity and specificity, and have been useful in distinguishing MS from other disorders. Further research is needed to validate these findings and determine the clinical utility of these biomarkers in routine practice.

Present and future of the diagnostic work-up of multiple sclerosis: the imaging perspective

In recent years, the use of magnetic resonance imaging (MRI) for the diagnostic work-up of multiple sclerosis (MS) has evolved considerably. The 2017 McDonald criteria show high sensitivity and accuracy in predicting a second clinical attack in patients with a typical clinically isolated syndrome and allow an earlier diagnosis of MS. They have been validated, are evidence-based, simplify the clinical use of MRI criteria and improve MS patients' management. However, to limit the risk of misdiagnosis, they should be applied by expert clinicians only after the careful exclusion of alternative diagnoses. Recently, new MRI markers have been proposed to improve diagnostic specificity for MS and reduce the risk of misdiagnosis. The central vein sign and chronic active lesions (i.e., paramagnetic rim lesions) may increase the specificity of MS diagnostic criteria, but further effort is necessary to validate and standardize their assessment before implementing them in the clinical setting. The feasibility of subpial demyelination assessment and the clinical relevance of leptomeningeal enhancement evaluation in the diagnostic work-up of MS appear more limited. Artificial intelligence tools may capture MRI attributes that are beyond the human perception, and, in the future, artificial intelligence may complement human assessment to further ameliorate the diagnostic work-up and patients' classification. However, guidelines that ensure reliability, interpretability, and validity of findings obtained from artificial intelligence approaches are still needed to implement them in the clinical scenario. This review provides a summary of the most recent updates regarding the application of MRI for the diagnosis of MS.

What is the potential of paramagnetic rim lesions as diagnostic indicators in multiple sclerosis?

INTRODUCTION

In multiple sclerosis (MS), paramagnetic rim lesions (PRLs) on MRI identify a subset of chronic active lesions (CALs), which have been linked through clinical and pathological studies to more severe disease course and greater disability accumulation. Beside their prognostic relevance, increasing evidence supports the use of PRL as a diagnostic biomarker.

AREAS COVERED

This review summarizes the most recent updates regarding the MRI pathophysiology of PRL, their prevalence in MS (by clinical phenotypes) vs mimicking conditions, and their potential role as diagnostic MS biomarkers. We searched PubMed with terms including 'multiple sclerosis' AND 'paramagnetic rim lesions' OR 'iron rim lesions' OR 'rim lesions' for manuscripts published between January 2008 and July 2022.

EXPERT OPINION

Current research suggests that PRL can improve the diagnostic specificity and the overall accuracy of MS diagnosis when used together with the dissemination in space MRI criteria and the central vein sign. Nevertheless, future prospective multicenter studies should further define the real-world prevalence and specificity of PRL. International guidelines are needed to establish methodological criteria for PRL identification before its implementation into clinical practice.

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.

From pathology to MRI and back: Clinically relevant biomarkers of multiple sclerosis lesions

Focal lesions in both white and gray matter are characteristic of multiple sclerosis (MS). Histopathological studies have helped define the main underlying pathological processes involved in lesion formation and evolution, serving as a gold standard for many years. However, histopathology suffers from an intrinsic bias resulting from over-reliance on tissue samples from late stages of the disease or atypical cases and is inadequate for routine patient assessment. Pathological-radiological correlative studies have established advanced MRI's sensitivity to several relevant MS-pathological substrates and its practicality for assessing dynamic changes and following lesions over time. This review focuses on novel imaging techniques that serve as biomarkers of critical pathological substrates of MS lesions: the central vein, chronic inflammation, remyelination and repair, and cortical lesions. For each pathological process, we address the correlative value of MRI to MS pathology, its contribution in elucidating MS pathology in vivo, and the clinical utility of the imaging biomarker.

QSMRim-Net: Imbalance-aware learning for identification of chronic active multiple sclerosis lesions on quantitative susceptibility maps

BACKGROUND AND PURPOSE

Chronic active multiple sclerosis (MS) lesions are characterized by a paramagnetic rim at the edge of the lesion and are associated with increased disability in patients. Quantitative susceptibility mapping (QSM) is an MRI technique that is sensitive to chronic active lesions, termed rim + lesions on the QSM. We present QSMRim-Net, a data imbalance-aware deep neural network that fuses lesion-level radiomic and convolutional image features for automated identification of rim + lesions on QSM.

METHODS

QSM and T2-weighted-Fluid-Attenuated Inversion Recovery (T2-FLAIR) MRI of the brain were collected at 3 T for 172 MS patients. Rim + lesions were manually annotated by two human experts, followed by consensus from a third expert, for a total of 177 rim + and 3986 rim negative (rim-) lesions. Our automated rim + detection algorithm, QSMRim-Net, consists of a two-branch feature extraction network and a synthetic minority oversampling network to classify rim + lesions. The first network branch is for image feature extraction from the QSM and T2-FLAIR, and the second network branch is a fully connected network for QSM lesion-level radiomic feature extraction. The oversampling network is designed to increase classification performance with imbalanced data.

RESULTS

On a lesion-level, in a five-fold cross validation framework, the proposed QSMRim-Net detected rim + lesions with a partial area under the receiver operating characteristic curve (pROC AUC) of 0.760, where clinically relevant false positive rates of less than 0.1 were considered. The method attained an area under the precision recall curve (PR AUC) of 0.704. QSMRim-Net out-performed other state-of-the-art methods applied to the QSM on both pROC AUC and PR AUC. On a subject-level, comparing the predicted rim + lesion count and the human expert annotated count, QSMRim-Net achieved the lowest mean square error of 0.98 and the highest correlation of 0.89 (95% CI: 0.86, 0.92).

CONCLUSION

This study develops a novel automated deep neural network for rim + MS lesion identification using T2-FLAIR and QSM images.