Background

A deep-learning prototype method, called CVSNet, was recently introduced for the automated detection of the central vein sign (CVS) in brain lesions and demonstrated effective and accurate discrimination of multiple sclerosis (MS) from its mimics. However, this method solely considered focal lesions displaying the central vein sign (CVS+) or not (CVS−), therefore requiring a manual pre-selection of the lesions to be evaluated by eliminating the so-called excluded lesions (CVSe) as defined by the NAIMS criteria. CVSe lesions may however play an important role in differential diagnosis. Moreover, extending the automated CVS classification to these lesions would facilitate the integration of CVSNet with existing MS lesion segmentation algorithms in a fully automated pipeline.

Objectives

To develop an improved version of the CVSNet prototype method able to classify all types of lesions (CVS+, CVS− and CVSe).

Methods

Patients with an established MS or CIS diagnosis (RRMS 29; SPMS 10; PPMS 10; CIS 1; mean ± SD age: 50 ± 11 years; male/female: 23/27), and healthy controls (n=8; mean ± SD age: 41 ± 9 years; male/female: 5/3), underwent 3T brain MRI (MAGNETOM Skyra and MAGNETOM Prisma, Siemens Healthcare, Erlangen, Germany, or Achieva, Philips Healthcare, Best, Netherlands). Brain lesions were automatically segmented and manually corrected by a single rater. CVS assessment was conducted on FLAIR* images by two raters, according to the NAIMS guidelines, yielding 1542 CVS+, 1004 CVS−, and 1131 CVSe lesions. A convolutional neural network (CNN) based on the CVSnet architecture was trained with different configurations using 3021 samples (1261 CVS+, 847 CVS−, and 913 CVSe) and evaluated in 656 unseen samples (281 CVS+, 157 CVS−, and 218 CVSe, from 13 patients) for final testing. The configurations relied on different combinations of the following channels as input: (i) FLAIR*, (ii) T2*, (iii) lesion mask, and (iv) CSF and brain tissue concentration maps obtained from a partial-volume estimation algorithm. Lesion-wise classification performance was evaluated for the different configurations by estimating the sensitivity, specificity, and accuracy for each lesion class.

Results

The results were similar across the different configurations. The best performance in the unseen testing set was obtained when all channels were used as input (sensitivity: 0.71, 0.73; specificity: 0.71, 0.81; and accuracy: 0.71, 0.79 for CVS+, CVS−, respectively). For CVSe, this approach achieved 0.52 sensitivity, 0.94 specificity, and 0.80 accuracy.

Conclusions

We introduced a modified CVSNet prototype method that can analyze the presence of the central vein for all types of brain lesions, enabling its integration with current MS lesion segmentation algorithms. This new feature will allow a fully automated assessment of the CVS in patients’ brains, speeding up the evaluation of CVS as a diagnostic biomarker for differentiating MS from mimicking diseases.

Background

In multiple sclerosis (MS), perilesional chronic inflammation appears on in vivo 3T susceptibility-based magnetic resonance imaging (MRI) as non-gadolinium-enhancing paramagnetic rim lesions (PRL). A higher PRL burden has been recently associated with a more aggressive disease course. The visual detection of PRL by experts is time-consuming and can be subjective.

Objectives

To develop a multimodal convolutional neural network (CNN) capable of automatically detecting PRL on 3D-T2*w-EPI unwrapped phase and 3D-T2w-FLAIR images.

Methods

124 MS cases (87 relapsing remitting MS, 16 primary progressive MS and 21 secondary progressive MS) underwent 3T MRI (MAGNETOM Prisma and MAGNETOM Skyra, Siemens Healthcare, Erlangen, Germany). Two neurologists visually inspected FLAIR magnitude and EPI phase images and annotated 462 PRL. 4857 lesions detected by an automatic segmentation (La Rosa et al. 2019) without overlap with PRL were considered non-PRL. The prototype RimNet was built upon two single CNNs, each fed with 3D patches centered on candidate lesions in phase and FLAIR images, respectively. A two-step feature-map fusion, initially after the first convolutional block and then before the fully connected layers, enhances the extraction of low and high-level multimodal features. For comparison, two unimodal CNNs were trained with phase and FLAIR images. The areas under the ROC curve (AUC) were used for evaluation (DeLong et al. 1988). The operating point was set at a lesion-wise specificity of 0.95. The patient-wise assessment was conducted by using a clinically relevant threshold of four rim+ lesions per patient (Absinta et al. 2019).

Results

RimNet (AUC=0.943) outperformed the phase and FLAIR image unimodal networks (AUC=0.913 and 0.855, respectively, P’s <0.0001). At the operating point, RimNet showed higher lesion-wise sensitivity (70.6%) than the unimodal phase network (62.1%), but lower than the experts (77.7%). At the patient level, RimNet performed with sensitivity of 86.8% and specificity of 90.7%. Individual expert ratings yielded averaged sensitivity and specificity values of 76.3% and 99.4%, respectively.

Conclusions

The excellent performance of RimNet supports its further development as an assessment tool to automatically detect PRL in MS. Interestingly, the unimodal FLAIR network performed reasonably well despite the absence of a paramagnetic rim, suggesting that morphometric features such as volume or shape might be a distinguishable feature of PRL.

Background

Recent studies have described Multiple Sclerosis (MS) as a disconnection syndrome (Rocca et al. 2015). Modelling disconnectomes using brain networks enables to quantify connectivity loss using graph analysis. To build structural connectomes, high-quality diffusion Magnetic Resonance Imaging (dMRI) and robust tractography algorithms are typically required. However, high-quality dMRI is rarely acquired in clinical workups due to time constraints.

Objectives

We propose to use a tractography atlas to extract brain connectivity loss in response to lesions without requiring dMRI, and to model structural disconnectomes with brain graphs. Topological graph features are proposed as new radiological biomarkers and their relation with Total Lesion Volume (TLV) and Expanded Disability Status Scale (EDSS) are studied.

Methods

589 MS patients (159 males, age 28±8yo, EDSS 2.40±1.22, TLV 13.0±14.6mL) underwent MRI at 3T (MAGNETOM Skyra, Siemens Healthcare, Erlangen, Germany). Acquisition protocols included T1-weighted magnetization-prepared rapid gradient echo (MPRAGE) and fluid-attenuated inversion recovery (FLAIR).

Lesions were segmented using LeMan-PV, a prototype lesion segmentation algorithm (Fartaria et al. 2016). The lesion masks were registered to standard MNI space and overlapped with the HCP842 tractography atlas (Yeh et al. 2018). Streamlines passing through lesions were isolated to define the affected connectivity.

The disconnectome graph was built using brain regions from the Brainnetome atlas (Fan et al. 2016) as nodes, whilst edges were weighted by the percent of unaffected streamlines connecting two nodes relative to the atlas connectivity. Topological features were extracted from the disconnectome graph and their Spearman’s correlations with TLV and EDSS were computed.

Results

Transitivity (T) and global efficiency (GE) decreased for larger TLV (R=-0.42 and R=-0.78), whereas the average shortest path length (PL) increased (R=0.78). When looking at correlations with EDSS, T (R=-0.17), GE (R=-0.24) and PL (R=0.23) showed stronger associations than lesion count (R=0.14) but were comparable to TLV (R=0.23). All correlations were significant (p<0.001).

Conclusions

We proposed an atlas-based disconnectome model which allowed to study connectivity loss in MS patients without requiring dMRI. Overall, patients showed a lower small-worldness and efficiency for larger TLV and worse disability. These observations were consistent with previous studies on diffusion-based connectomes and open new avenues of research for routine clinical data.

Background

Regional brain atrophy is a sensitive disability marker for MS patients. A previous study has shown that atrophy of the corpus callosum is an early marker for disease progression. However, the relationship between diffuse pathology in specific brain regions and the course of regional atrophy development remains poorly understood.

Objectives

To investigate quantitative T1 maps and entropy (amount of T1 inhomogeneity) in regional brain structures from diagnostic MRI (performed at disease onset) of MS patients and compare these findings with healthy controls (HC).

Methods

Fifty MS patients and 102 HC were examined on a 3T MRI scanner (MAGNETOM Skyra, Siemens Healthcare, Erlangen, Germany). The MRI protocol comprised 3D MP2RAGE, 3D MPRAGE, 3D FLAIR and 3D DIR. The calculation of T1 maps, brain structure segmentations and brain volume measurements were obtained from a single MP2RAGE scan. Lesion segmentation masks were obtained using the LeManPV prototype software (Siemens Healthcare, Erlangen, Germany). We evaluated T1 maps from normal-appearing white matter (excluding lesions) in the corpus callosum, the brain lobes, brainstem and cerebellum, as well as from normal-appearing gray matter (excluding lesions) in the thalami, basal ganglia, and cortical gray matter. We calculated median regional T1 relaxation times, T1 entropy and volume for the above-mentioned structures for the early-MS group and 50 age- and sex-matched HC subjects. Statistical comparison was performed using t-tests.

Results

The median T1 of the corpus callosum in the early MS group was 838 ms (SD 38.5), with entropy 8.42 (SD 0.24); compared to 810 ms (SD 25.2) and 8.23 (SD 0.13) in the HC group. Statistically significant differences were found in T1 times and entropy between the groups (p<0.001); volumes were, however, not statistically different. Smaller but also statistically significant differences in T1 maps and entropy were found for white matter of the brain lobes (p<0.001). Thalami volumes showed statistically significant differences between groups, but not median T1 times (MS group 1055 ms, SD 32.6 vs. HC 1049 ms, SD 21.2).

Conclusions

Pathology of the normal-appearing white matter in T1 relaxometry can already be detected at MS disease onset. In particular, corpus callosum T1 times were considerably higher at clinical onset of MS compared to HC. We hypothesize that early microstructural changes detected at disease onset lead to evolution of regional brain atrophy.

Background

LeMan-PV is a prototype that performs cross-sectional and longitudinal detection of Multiple Sclerosis (MS) lesions, which has been validated on conventional (cMRI) and advanced magnetic resonance imaging at 3T (Fartaria et al. 2019). Since this software provides a report that is available shortly after image acquisition, it may be ideal as clinical decision-support tool.

Objectives

To assess LeMan-PV as clinical decision-support tool in a monocentric real-world cMRI dataset from the Swiss Multiple Sclerosis Cohort.

Methods

262 MS patients underwent cMRI at Basel University Hospital in a mean of 3.5 follow-up sessions, with an average of 399 days between two consecutive sessions. cMRI sequences were acquired at 1.5T and 3T in 725 and 195 sessions, respectively. Cross-sectional and longitudinal MS lesions segmentation (i.e. identification of new and enlarging lesions - NLs, ELs) was performed using the LeMAN-PV prototype software. An expert neuroradiologist performed a radiological reading of the number of NLs and ELs in the most recent acquisition by comparing it to the previous one (ground truth, GT), considering only lesions with a diameter larger than 3 mm. The minimum volume thresholds to identify an NL and an EL were chosen by minimizing the patient-wise error between the automated count and the expert ground truth. Two scenarios were evaluated by first assuming disease activity if one or more EL were present, and second by considering activity if NL were present in the new acquisition.

Results

The volume thresholds chosen were 11 and 12 mm³ for ELs and NLs, respectively. For those, LeMan-PV detected 11% more of both ELs and NLs than the neuroradiologist. In the patient-wise evaluation of cases with both sessions acquired at 1.5T (70%), LeMan-PV showed sensitivities of 93% and 78% and specificities of 62% and 43% when evaluating ELs and NLs. For the 3T pairs of sessions (8%), values were 68% and 72% for ELs and 73% and 68% for NLs. Finally, for cases with a first acquisition at 1.5T and a second at 3T (22%), values were 76% and 73% for ELs and 71% and 65% for NLs.

Conclusions

The count of new and enlarging MS lesions using LeMan-PV were close to the one performed by an expert neuroradiologist; the software performed better when assessing disease activity via detection of enlarging lesions rather than by identifying new lesions. More 3T data is being currently collected at 3T to provide a size-matched inter-scanner comparison.

Background

Automated and reproducible measures of MS severity and subclinical inflammatory activity and neurodegeneration in routine practice could support therapeutic decisions and accelerate research. Toward this goal, we developed and validated a software prototype, MSPie (MS PATHS Image Evaluation). MSPie runs on syngo.via Frontier (Siemens Healthcare, Erlangen, Germany) and processes standardized T2 FLAIR and T1-weighted MRIs to quantify brain parenchymal fraction (BPF), T2 lesion volume, and #new/enlarging T2 lesions (NET2L). Results are reviewable by radiologists through an interface that displays current, prior, and subtraction images, as well as overlays of brain and lesion segmentations, and allows +/- corrections of NET2L.

Objectives

To assess an image analysis prototype integrated into radiological practice to generate quantitative brain volume and lesion measurements at the point of care.

Methods

MSPie was installed at 2 MS Partners Advancing Technology and Health Solutions (MS PATHS) institutions. 3 neuroradiologists per institution used MSPie to review 40 longitudinal pairs of routine MS PATHS MRIs. For each case, radiologists performed a visual assessment of the brain segmentation used for BPF, manually corrected NET2L if needed, approved or rejected the results, and completed a performance evaluation survey.

Results

MSPie performance was assessed in 240 cases. Radiologists accepted MSPie-generated BPF and lesion results for 230/240 cases (96%). 38.8% of cases required corrections of false positive (FP) or false negative (FN) NET2L, with a mean of 2.5 (FP+FN) NET2L per case. In 94% of cases, NET2L FP+FN was £3, a prespecified design target based on radiologists’ input. MSPie detected 221/229 true NET2L, yielding a sensitivity of 96.2%. In 18% of cases, radiologists reported MSPie-detected NET2L they would have missed. Mean performance ratings on a scale of 1(poor) to 5(excellent) were: 3.9 for overall performance; 3.9 for brain segmentation; 3.9 for T2 lesion segmentation.

Conclusions

Incorporation of brain volume and T2 lesion quantification into MS imaging practice is feasible. MSPie demonstrated a high sensitivity for disease activity, detecting some NET2L that might have been missed by radiologists. MSPie achieved the prespecified target rate of acceptable false positive NET2L. MSPie might allow neuroradiologists to provide quantitative brain atrophy and T2 lesion metrics in clinical practice and to increase their diagnostic precision.

Disclosures: MS PATHS is sponsored by Biogen.

Background

Mean rates of brain atrophy in healthy controls range from 0.05-0.5%, depending on age and technical factors, including scanner, acquisition sequences, and image analysis techniques. In MS PATHS (MS Partners Advancing Technology for Health Solutions), standardized MRIs are analyzed using a software prototype (MSPie, MS PATHS Image Evaluation) that incorporates a novel approach to calculate BPF. Normative ranges measured using MSPie are needed to distinguish age- and disease-related changes.

Objectives

To establish a normative reference for interpretation of brain parenchymal fraction (BPF) in individual MS patients relative to age-matched healthy volunteers (HV).

Methods

HV aged 21-60 were recruited at 6 MS PATHS sites to be age-, race-, and gender-matched to the MS PATHS cohort. HVs were imaged at baseline and once/year using 3T scanners (Siemens Healthcare, Erlangen, Germany) and standardized acquisitions (3DFLAIR and 3DT1), as in routine MRIs in MS PATHS. MRIs from UK Biobank supplemented the normative dataset past the age of 60. All MRIs were analyzed with MSPie to calculate BPF. BPF normative percentile were calculated for each age using quantile regression. Mean annualized rate of brain atrophy was estimated from HVs with follow-up MRIs. BPF percentiles were applied to the MS PATHS cohort. Mean Processing Speed Test (PST) z-scores were compared in MS patients stratified based on BPF percentiles.

Results

209 HVs were enrolled, 590 UKBiobank HVs were selected, and 9479 MS patients had at least one MRI. HV BPF values ranged from 0.855-0.895 in the 21-30 age group to 0.796-0.882 in the 61-73 age group, demonstrating accelerating and more variable atrophy with increasing age. For MS patients age 21-73 years (n=6791), mean age-adjusted BPF percentile was 27.8%, where BPF values fell above the 50^th%-ile in 23.4% (“mild MS”) and below the 25^th%-ile in 57.6% (“severe MS”). Mean PST z-scores differed in BPF-based mild MS vs. severe MS groups (-0.15 and -0.83; p<0.001). Mean annualized BPF change in HV was -0.08% (range: -0.71% to +0.57%) based on 71 subjects (mean age: 41.1 years) with >2 MRIs.

Conclusions

Incorporating normative reference data into MSPie will aid clinicians with interpretation of individual patients’ BPF in clinical practice and may enable patient stratification based on BPF and other predictors. Additional longitudinal normative data are being collected to contextualize disease progression as measured by BPF change over time.

Disclosures: MS PATHS is sponsored by Biogen.

Background

The presence of infratentorial lesions early in the disease has been shown to have prognostic value for future disability in multiple sclerosis (MS). Quantitative imaging metrics such as T1 relaxometry might contribute to understanding the relationship between supratentorial (ST), infratentorial (IT), and spinal cord (SC) pathology.

Objectives

Our aim was to explore the association between ST, IT and SC pathology and microstructural tissue alterations assessed with T1 relaxometry in T2-hyperintense lesions as well as cerebral and cerebellar normal-appearing white matter (NAWM) in patients with recently diagnosed MS with- and without IT lesions.

Methods

Microstructural tissue alterations were assessed in 42 patients (mean age 33.6±8.0 years, median MS duration 0.2 years (0-2.3)) as deviations from normative T1 times, both obtained from the MP2RAGE sequence at 3T (MAGNETOM Skyra, Siemens Healthcare, Erlangen, Germany). The normative T1 values were voxel-wise modelled via a study-specific atlas based on spatially normalized data from 102 healthy individuals (21-59 years). Relationship between normalized IT volumes (mesencephalon, pons, medulla oblongata, cerebellum), SC volume, ST and IT lesion loads estimated by the Morphobox prototype, Scanview and LemanPV prototype, respectively and the deviations from normative T1 times expressed as z-score-derived metrics (volumes and means of voxels with z-scores above z-score 2 and below z-score 2) in lesions, cerebral and cerebellar NAWM were studied by partial correlations adjusted for age and brain lesion volume.

Results

Patients with IT lesions (n=23, 33.0±8.5 years) had larger lesion load, higher volumes of voxels with positive z-scores (> 2), higher mean of z-scores above 2 in lesions, and larger thalami than patients without IT lesions (n=19, 34.3±7.7 years). The remaining volumes and z-scores derived metrics did not differ between groups. Cerebellar volume correlated negatively with volume of voxels with negative z-scores (< 2) in cerebellar NAWM (partial correlation coefficient r=-.437, p=.005) only in patients with IT lesions. In patients without IT lesions, SC and pons volumes correlated negatively with volume of voxels with positive z-scores corresponding to areas of supratentorial T2 lesions (SC: r=-.669, p=.003, pons: r=-0.606, p=0.01).

Conclusions

Microstructural alterations identified as T1 z-scores relate differently to IT and SC volumes in MS patients with and without IT lesions. In the presence of IT lesions, changes in cerebellar NAWM (T1 shortening relative to healthy controls) are associated with lower cerebellar volume. In the absence of IT lesions, the association of cerebellar NAWM and cerebellar volume is not present. In patients without IT lesions, microstructural alterations in ST lesions (T1 prolongation) that might indicate the extent of tissue damage in lesions, are associated with lower pontine and SC volumes regardless of the T2 lesion load.

Background

Although conventional MRI acquisitions are of essence in the monitoring of MS, they show low specificity towards the microstructural nature of tissue alterations and exhibit rather low correlations with clinical metrics (“clinico-radiological paradox”). Conversely, recent advances in brain relaxometry allow characterizing microstructural alterations on a single-subject basis; the question yet remains whether such quantitative measurements can help bridging the gap between radiological and clinical findings.

Objectives

This study investigates whether automatically assessed alterations of T₁ relaxation times in brain lesions and normal-appearing white matter (NAWM) improve clinico–radiological correlations in early MS with respect to conventional measures.

Methods

102 healthy controls (65% female, [21-59] y/o) and 50 early-MS patients (76% female, [19-52] y/o) underwent MRI at 3T (MAGNETOM Skyra, Siemens Healthcare, Erlangen, Germany). The employed 3D protocol comprised MPRAGE, FLAIR (both used for lesion segmentation as in [Fartaria et al., 2017, MICCAI]), and MP2RAGE for T₁ mapping.

After the healthy controls’ data were spatially normalized into a study-specific template, reference T₁ values in healthy tissues were established by linear, voxel-wise modelling of the T₁ inter-subject variability [Piredda et al., MRM, 2020]. In the MS cohort, T₁ deviations from the established references were calculated as z-score maps.

Correlations between the EDSS and conventional measures, i.e. lesion volume and count, were compared against correlations with z-score-derived metrics in lesions and NAWM, namely the volume of voxels exceeding a given z-score threshold.

Results

Correlations between EDSS and lesion volume and count were found to be 0.23 and 0.18, respectively. Higher correlations were found between EDSS and the volume of voxels exceeding an absolute z-score threshold of 2, both in lesions and NAWM, with ρ=0.3 and ρ=0.33, respectively. Correlation further improved when considering only negative z-scores, ρ=0.36 for lesions and ρ=0.39 for NAWM. The highest correlation was found when considering absolute z-scores in the occipital lobe NAWM, ρ=0.47.

Conclusions

Microstructural alterations identified as T₁ z-scores were found to improve clinico–radiological correlation in comparison to conventional measures (lesion volume and count). Of notice, negative z-scores (i.e. abnormal T₁ shortening), which may be due to an increase in iron content, appear to be a potential predictor for the clinical state of an early MS patient.

Background

SC pathology occurs early in the course of MS. However, few studies have investigated the relationship between lesions, diffuse changes and mean upper cervical cord area (MUCCA) in MS patients with different levels of disability in detail.

Objectives

To explore spinal cord (SC) pathology in multiple sclerosis (MS) patients with different levels of disability and MS phenotypes.

Methods

638 MS patients with different degrees of disability and 102 healthy controls (HC) underwent MRI on a 3T (MAGNETOM Skyra, Siemens Healthcare, Erlangen, Germany). The MRI protocol comprised transversal 3D-T2WI for MUCCA, sagittal T2WI-Fat-Sat and PDWI for SC pathology, and 3D-MPRAGE for regional brain volume (BV). MUCCA was measured automatically between the C3 and C4 vertebra (ScanView.cz). Global and regional BVs were estimated by the fully automated MorphoBox prototype (Siemens Healthcare, Erlangen, Germany). Diffuse changes, number and location of SC lesions were assessed manually. Patients and HC were matched by sex and age using propensity scores. MUCCA, regional BVs and SC pathology were compared among matched subgroups of: 54 patients with mild disability (EDSS=<1.5), 54 patients with mild-to-moderate disability (EDSS 2-3.5), 54 patients with severe disability (EDSS 4-4.5), 54 patients with very severe disability (EDSS>=5), 18 primary progressive (PP) patients, and 54 controls from the HC group. ANOVA test was used for between-group comparison.

Results

There was a trend of lower MUCCA with higher disability level. Mean MUCCA was 76.5±10.8 mm² invery severe, 80.1±9.6 mm² in severe, 85.7±8.0 mm² in moderate, 85.6±8.5 mm² in mild disability, and 90±7.7 mm² in HC groups. There was a significant difference in MUCCA between HC and mild disability group (p<0.001). SC pathology was prominent in 64.1% of the patients with mild disability, compared to 90.4% patients with very severe disability. The percentage of diffuse changes varied greatly between the groups, with prevalence increasing almost four times between patients with mild and very severe disability.

Conclusions

SC pathology is present in all disability MS groups. MUCCA differentiated between patients with mild disability and healthy controls, suggesting that it may be promising for the implementation in diagnostic protocols. The evaluation of diffuse changes can help to predict disability. Low MUCCA together with prominent diffuse changes could help differentiate PP MS from other MS phenotypes.