Icometrix, Research and Development

Author Of 4 Presentations

Machine Learning/Network Science Poster Presentation

P0005 - Decoding the EDSS Scores of Multiple Sclerosis Patients from MRI Biomarkers (ID 1620)

Speakers
Presentation Number
P0005
Presentation Topic
Machine Learning/Network Science

Abstract

Background

Treatment response in multiple sclerosis (MS) is frequently suboptimal and, in many cases, different disease-modifying therapies need to be tested. The expanded disability status scale (EDSS) score and other markers of disease activity (such as relapses, new lesions, brain atrophy, etc.) are crucial for treatment decision making. However, EDSS suffers from poor reliability, repeatability, and high inter-rater variability. Therefore, automatic and objective disability scoring using MRI information could help to monitor disease progression reliably and optimize treatment.

Objectives

Develop a machine-learning model that learns relations between MRI-based brain volumes and clinical disability measured by EDSS.

Methods

Multi-center FLAIR and T1 MRI data from 325 MS patients were used. Individuals were rated in each center using EDSS within 0-89 days before or after the MRI scan. Automated image analysis was performed using icobrain, providing volumetric quantification of gray matter, white matter, whole brain, lateral ventricles, T1 hypointense and FLAIR hyperintense lesions. Moreover, other features, such as age, sex, and center, were available. A machine-learning model based on random forest regression was built for estimating EDSS automatically from these features. The model’s performance was assessed by means of mean squared error (MSE) and mean absolute error (MAE) evaluated overall, and on two EDSS subgroups, <=4 and >4,in a 100 repetition 10-fold-cross-validation fashion. Subsequently, the percentage of cases for which the automatic EDSS was within 1.5, 1 or 0.5 points, respectively, from the clinically reported EDSS was computed.

Results

The proposed automatic EDSS estimation model obtained MSE=2.36±0.03, MAE=1.24±0.89 for the overall interval, with MSE=1.83±0.04, MAE=1.11±0.76 for EDSS<=4 (N=200) and MSE=3.26±0.06, MAE=1.46±1.05 for EDSS>4 (N=118). The percentage of cases with absolute error strictly below 1.5, 1 and 0.5 EDSS points was 67%, 46% and 24%, respectively.

Conclusions

A good match between the automatic EDSS and the measured EDSS is only possible up to a certain extent, suggesting that the MRI-based EDSS score might also capture complementary information on disease activity compared to the clinically measured EDSS. Understanding such differences is a prerequisite for predicting future disability progression in MS.

Collapse
Machine Learning/Network Science Poster Presentation

P0015 - Predicted brain age as a cognitive biomarker in Multiple Sclerosis (ID 1388)

Speakers
Presentation Number
P0015
Presentation Topic
Machine Learning/Network Science

Abstract

Background

Brain-predicted age difference (BPAD) is the difference between chronological and brain age, the latter being decoded from brain MR images by a machine learning model. BPAD has been established as a biomarker for physical deterioration in multiple sclerosis (MS).

Objectives

The objective was to examine the value of brain-predicted age difference as a biomarker for cognitive deterioration in MS.

Methods

In the first phase we used supervised machine learning (ridge regression, 7-fold cross-validation) to predict chronological age from brain volumes. This was achieved on a sample of 1743 healthy controls (HC) with T1-weighted MR images from a range of public collections, using the icobrain software to compute normalized brain volumes (whole brain, white matter, (cortical) grey matter and lateral ventricles). The age range of this sample was 8 to 94 years. In the second phase we applied this algorithm to decode brain age in 231 T1-weighted MR images from MS patients from two clinical centers. The age range of this sample was 14 to 77 years. BPAD computed for HC (BPADHC) and MS (BPADMS) were compared with an independent student t-test. Cognitive functioning was assessed through the symbol digit modalities test (SDMT), available for all 231 included MS patients, the brief visuospatial memory test revised (BVMT-R) and California verbal learning test II (CVLT-II), the latter two being available for a subset of 97 patients from one center. Pearson correlation was computed between the BPAD values and scores on each cognitive test. P-values were corrected for multiple comparisons by the Benjamini/Hochberg method.

Results

After training, the mean (SD) BPADHC in the best-performing of seven folds was -0.5 (9.2) years, opposed to 9.7 (12.0) years for BPADMS. This difference was statistically significant (p < 0.001). Correlations between BPADMS and SDMT, BVMT-R and CVLT-II were -0.19 (p = 0.005), -0.14 (p = 0.157) and -0.30 (p = 0.005) respectively.

Conclusions

Our results showed a significant association between BPADMS and two cognitive measures in MS, information processing speed and verbal memory. These findings support a potential role for BPADMS as a cognitive biomarker in MS.

Collapse
Imaging Poster Presentation

P0632 - Reduced brain integrity slows down and increases low alpha power in multiple sclerosis (ID 891)

Abstract

Background

In multiple sclerosis, the interplay of neurodegeneration, demyelination and inflammation leads to changes in neurophysiological functioning.

Objectives

This study aims to characterise the relation between reduced brain volumes and spectral power in multiple sclerosis patients and matched healthy subjects.

Methods

During resting-state eyes closed, we collected magnetoencephalographic data in 67 multiple sclerosis patients and 47 healthy subjects, matched for age and gender. Additionally, we quantified different brain volumes (white matter, cortical and deep grey matter, FLAIR lesion load and volume of black holes) and calculated the power spectral density. Instead of using the traditionally used frequency bands, we calculated the source reconstructed power spectral density in frequency bins of 0.25 Hz (range: 0-40 Hz) and corrected for multiple comparisons through permutation testing.

Results

First, a principal component analysis (PCA) of brain volumes demonstrates that atrophy can be largely described by two components: one overall degenerative component that is indicative of brain integrity and correlates strongly with different cognitive tests, and one component that mainly captures degeneration of the cortical grey matter that strongly correlates with age. As the first PC was observed both when performing the PCA on the full cohort and on the two subcohorts, we denote this component as an index of brain integrity. Logically, this component was more strongly expressed in the MS cohort.

Next, a multimodal correlation analysis indicates that reduced brain integrity is accompanied by increased alpha1 power in the temporoparietal junction (TPJ). Patients showing this local increase in alpha-peak also scored significantly worse on different cognitive tests and reduced thalamic volumes. The increase in alpha1-power comes from both a slowing of the main alpha-peak and an increase in power.

Conclusions

MS patients with reduced brain integrity demonstrated increased alpha1 power in the TPJ and impaired cognitive functioning.

Collapse
Imaging Poster Presentation

P0636 - Relationship of real-world brain atrophy to MS disability using icobrain: 4 centre pilot study (ID 716)

Abstract

Background

To date, no studies have explored the relationship between brain atrophy and MS disability using differing MRI protocols and scanners at multiple sites.

Objectives

To assess the association between brain atrophy and MS disability, as measured by EDSS and 6-month confirmed disability progression (CDP).

Methods

In this retrospective study at 4 MS centres, a total of 1300 patients had brain MRI imaging assessed by icobrain. Relapse-onset MS patients were included if they had two clinical MRIs 12 (±3) months apart and ≥2 EDSS scores post MRI-2, the first ≤3 months from MRI-2, with ≥6 months between first and last EDSS. Volumetric data were analysed if the alignment similarity between two images was as good as that of same-scanner scan-rescan images (normalised mutual information ≥0.2). The percentage brain volume change (PBVC), percentage grey matter change (PGMC), FLAIR lesion volume change, whole brain volume, grey matter volume, FLAIR lesion volume and T1 hypointense lesion volume at MRI-2 were calculated. Ordinal mixed effect models were used to determine the association between these volumetric MRI measures and all EDSS scores post MRI-2. Cox proportional hazards models were used for the 6-month CDP outcome, using a subset of patients with ≥3 EDSS. Models were adjusted for proportion of time spent on disease-modifying therapy during MRIs ± whole brain/grey matter volume at baseline MRI.

Results

Of the 260 relapse-onset MS patients included, 204 (78%) MRI pairs were performed in the same scanner and 56 (22%) pairs were from different scanners. During the follow-up period (median 3.8 years, range 1.3-8.9), 29 of 244 (12%) patients experienced 6-month CDP. There was no evidence for association between annualised PBVC or PGMC and CDP or EDSS (p>0.05). Cross-sectional whole brain and grey matter volume (at MRI-2) tended to associate with CDP (HR 0.99, 95% CI 0.98-1.00, p=0.06). Every 1ml of whole brain or grey matter volume lost represented a 1% higher chance of reaching 6-month CDP. Only whole brain volume (at MRI-2) was associated with EDSS score (β -0.03, SE 0.01, p<0.001) and the slope of EDSS change over time (β -0.001, SE 0.0003, p=0.02). On average, every 33ml reduction of brain volume was associated with a 1 step increase in EDSS.

Conclusions

In this real-world clinical setting where a fifth of the brain atrophy analysis were performed on different scanners, we found no association between individual brain atrophy and MS disability. However, there was an association between cross-sectional whole brain volume with EDSS and slope of EDSS change.

Collapse