Brain. 2018 Jun; 141(6): 1665–1677.
Published online 2018 May 8. doi: 10.1093/brain/awy088
Progression of regional grey matter atrophy in multiple sclerosis
Arman Eshaghi, Razvan V Marinescu, Alexandra L Young, Nicholas C Firth, Ferran Prados, M Jorge Cardoso, Carmen Tur, Floriana De Angelis, Niamh Cawley, Wallace J Brownlee, Nicola De Stefano, M Laura Stromillo, Marco Battaglini, Serena Ruggieri, Claudio Gasperini, Massimo Filippi, Maria A Rocca, Alex Rovira, Jaume Sastre-Garriga, Jeroen J G Geurts, Hugo Vrenken, Viktor Wottschel, Cyra E Leurs, Bernard Uitdehaag, Lukas Pirpamer, Christian Enzinger, Sebastien Ourselin, Claudia A Gandini Wheeler-Kingshott, Declan Chard, Alan J Thompson, Frederik Barkhof, Daniel C Alexander, and Olga Ciccarelli
Abstract
Grey matter atrophy is present from the earliest stages of multiple sclerosis, but its temporal ordering is poorly understood. We aimed to determine the sequence in which grey matter regions become atrophic in multiple sclerosis and its association with disability accumulation. In this longitudinal study, we included 1417 subjects: 253 with clinically isolated syndrome, 708 with relapsing-remitting multiple sclerosis, 128 with secondary-progressive multiple sclerosis, 125 with primary-progressive multiple sclerosis, and 203 healthy control subjects from seven European centres. Subjects underwent repeated MRI (total number of scans 3604); the mean follow-up for patients was 2.41 years (standard deviation = 1.97). Disability was scored using the Expanded Disability Status Scale. We calculated the volume of brain grey matter regions and brainstem using an unbiased within-subject template and used an established data-driven event-based model to determine the sequence of occurrence of atrophy and its uncertainty. We assigned each subject to a specific event-based model stage, based on the number of their atrophic regions. Linear mixed-effects models were used to explore associations between the rate of increase in event-based model stages, and T2 lesion load, disease-modifying treatments, comorbidity, disease duration and disability accumulation. The first regions to become atrophic in patients with clinically isolated syndrome and relapse-onset multiple sclerosis were the posterior cingulate cortex and precuneus, followed by the middle cingulate cortex, brainstem and thalamus. A similar sequence of atrophy was detected in primary-progressive multiple sclerosis with the involvement of the thalamus, cuneus, precuneus, and pallidum, followed by the brainstem and posterior cingulate cortex. The cerebellum, caudate and putamen showed early atrophy in relapse-onset multiple sclerosis and late atrophy in primary-progressive multiple sclerosis. Patients with secondary-progressive multiple sclerosis showed the highest event-based model stage (the highest number of atrophic regions, P < 0.001) at the study entry. All multiple sclerosis phenotypes, but clinically isolated syndrome, showed a faster rate of increase in the event-based model stage than healthy controls. T2 lesion load and disease duration in all patients were associated with increased event-based model stage, but no effects of disease-modifying treatments and comorbidity on event-based model stage were observed. The annualized rate of event-based model stage was associated with the disability accumulation in relapsing-remitting multiple sclerosis, independent of disease duration (P < 0.0001). The data-driven staging of atrophy progression in a large multiple sclerosis sample demonstrates that grey matter atrophy spreads to involve more regions over time. The sequence in which regions become atrophic is reasonably consistent across multiple sclerosis phenotypes. The spread of atrophy was associated with disease duration and with disability accumulation over time in relapsing-remitting multiple sclerosis.
Figure: The event-based model steps to estimate the most likely sequence of atrophy progression. The three steps are: (A) adjusting for nuisance variables, and region selection; (B) calculating the best-fit probability distributions for normal and atrophic brain regions; searching for the most likely sequence; and (C) quantifying the uncertainty with cross-validation. [B(i)] The distribution of the volume in an example region in healthy controls and patients and the corresponding mixture model. (ii) The steps for greedy ascent search. (iii) A matrix showing a sequence of atrophy progression on the y-axis, and the position in the sequence of each region ranging from 1 to the total number of regions on the x-axis. The intensity of each matrix entry corresponds to the proportion of Markov Chain Monte Carlo samples of the posterior distribution where a certain region of y-axis appears at the respective stage of x-axis.
Years of research into MS hasn't solved the mystery that is progressive disease in MS, it would seem that there's always more mystery. Like pieces of an incomplete puzzle, the face of true MS remains hidden. Is it one disease entity? Or is it like people, you only see the facets that you understand?
Our therapeutic strategy for MS unfortunately has been hampered by our lack of understanding of this process. The slow burn neurodegeneration leading to brain volume loss is such a subtle process. and clinically at its earliest stages an undefinable milieu of cognitive and psychiatric dysfunctions, that we have yet to define where MS starts or even the MS prodrome.
Looking at large data sets and developing new methods of analysing data within this might me the answer.
Here researchers use a strategy called event-based modelling in longitudinal data sets (serial MRI imaging) to stage the progression of grey matter (where the neuronal cells in the brain sit, as opposed to the the white matter, which comprises of the tracts or axons) volume loss in all forms of MS (see figure above). Of course, in this type of strategy, a couple of a priori assumptions have to be made: a) that the information derived from these images is representative of the entire disease trajectory, b) that it occurs the same way in everyone, and c) that it is irreversible! Although, by no means perfect it's an interesting strategy to deploy in understanding the progression patterns of neurodegeneration in MS.
There were some notable findings from the study:
- Brain atrophy is fairly homogeneous in MS - CIS/RRMS/SPMS: posterior cingulate and precuneus > middle cingulate > brainstem > thalamus; PPMS: thalamus, cuneus and precuneus, and pallidum > brainstem, precentral gyrus, posterior cingulate > frontal operculum, middle temporal gyrus.
- T2 lesion load was associated with event-based model stage, but there was no association with the rate of change in lesion load over time (i.e. increase in lesion load over time doesn't lead to a change in the rate of progression of grey matter neurodegeneration over time).
- In RRMS but not SPMS/PPMS there was an association between EDSS (clinical score of disability level) and event-based model stage. This assumes a linear relationship between the two, which we know from experience is not the case at extremes of the EDSS scale.
- Annual rate of change in event-based model stage was not significantly different between those on treatment (Disease modifying therapies) and those not on treatment. Similarly, they found no association with the existence of co-morbidities. I don't believe this study was of sufficiently powered to answer these two final questions.
What is notable is that the regions initially affected happen to be relay hubs for the brain, and just may be more vulnerable to damage because of their greater metabolic load than other areas of brain.
So is the MS prodrome simply one of disconnection?Labels: event-based modelling, grey matter atrophy, Neurodegeneration
