Biology subjects

Ourselin, S.

Publications and source records attributed to Ourselin, S..

8 recordsLinked to original sources

bioRxiv2024

A cautionary tale on the cost-effectiveness of collaborative AI in real-world medical applications.

Federated learning (FL) has gained wide popularity as a collaborative learning paradigm enabling trustworthy AI in sensitive healthcare applications. Never-theless, the practical implementation of FL presents technical and organizational challenges, as it generally requires complex communication infrastructures. In this context, consensus-based learning (CBL) may represent a promising collaborative learning alternative, thanks to the ability of combining local knowledge into a federated decision system, while potentially reducing deployment over-head. In this work we propose an extensive benchmark of the accuracy and cost-effectiveness of a panel of FL and CBL methods in a wide range of collaborative medical data analysis scenarios. Our results reveal that CBL is a cost-effective alternative to FL, providing comparable accuracy and significantly reducing training and communication costs. This study opens a novel perspective on the deployment of collaborative AI in real-world applications, whereas the adoption of cost-effective methods is instrumental to achieve sustainability and democratisation of AI by alleviating the need for extensive computational resources.

bioinformatics↗

bioRxiv2019

Modeling longitudinal imaging biomarkers with parametric Bayesian multi-task learning

Longitudinal imaging biomarkers are invaluable for understanding the course of neurodegeneration, promising the ability to track disease progression and to detect disease earlier than cross-sectional biomarkers. To properly realize their potential, biomarker trajectory models must be robust to both under-sampling and measurement errors and should be able to integrate multi-modal information to improve trajectory inference and prediction. Here we present a parametric Bayesian multi-task learning based approach to modeling univariate trajectories across subjects that addresses these criteria.\n\nOur approach learns multiple subjects trajectories within a single model that allows for different types of information sharing, i.e. coupling, across subjects. It optimizes a combination of uncoupled, fully coupled and kernel coupled models. Kernel-based coupling allows linking subjects trajectories based on one or more biomarker measures. We demonstrate this using Alzheimers Disease Neuroimaging Initiative (ADNI) data, where we model longitudinal trajectories of MRI-derived cortical volumes in neurodegeneration, with coupling based on APOE genotype, cerebrospinal fluid (CSF) and amyloid PET-based biomarkers. In addition to detecting established disease effects, we detect disease related changes within the insula that have not received much attention within the literature.\n\nDue to its sensitivity in detecting disease effects, its competitive predictive performance and its ability to learn the optimal parameter covariance from data rather than choosing a specific set of random and fixed effects a priori, we propose that our model can be used in place of or in addition to linear mixed effects models when modeling biomarker trajectories. A software implementation of the method is publicly available.

neuroscience↗

bioRxiv2019

Data Resource Profile:The Dementias Platform UK (DPUK) Data Portal

The Dementias Platform UK (DPUK) Data Portal is a data repository facilitating access to data for 3 370 929 individuals in 42 cohorts. The Data Portal is an end-to-end data management solution providing a secure, fully auditable, remote access environment for the analysis of cohort data. All projects utilising the data are by default collaborations with the cohort research teams generating the data. The Data Portal uses UK Secure eResearch Platform (UKSeRP) infrastructure to provide three core utilities: data discovery, access, and analysis. These are delivered using a 7 layered architecture comprising: data ingestion, data curation, platform interoperability, data discovery, access brokerage, data analysis and knowledge preservation. Automated, streamlined, and standardised procedures reduce the administrative burden for all stakeholders, particularly for requests involving multiple independent datasets, where a single request may be forwarded to multiple data controllers. Researchers are provided with their own secure lab using VMware which is accessed using two factor authentication. Over the last 2 years, 160 project proposals involving 579 individual cohort data access requests were received. These were received from 268 applicants spanning 72 institutions (56 academic, 13 commercial, 3 government) in 16 countries with 84 requests involving multiple cohorts. Project are varied including multi-modal, machine learning, and Mendelian randomisation analyses. Data access is usually free at point of use although a small number of cohorts require a data access fee.

neuroscience↗

bioRxiv2018

Spatiotemporal analysis for detection of pre-symptomatic shape changes in neurodegenerative diseases: applied to GENFI study

Brain atrophy as measured from structural MR images, is one of the primary imaging biomarkers used to track neurodegenerative disease progression. In diseases such as frontotemporal dementia or Alzheimers disease, atrophy can be observed in key brain structures years before any clinical symptoms are present. Atrophy is most commonly captured as volume change of key structures and the shape changes of these structures are typically not analysed despite being potentially more sensitive than summary volume statistics over the entire structure.\n\nIn this paper we propose a spatiotemporal analysis pipeline based Large Diffeomorphic Deformation Metric Mapping (LDDMM) to detect shape changes from volumetric MRI scans. We applied our framework to a cohort of individuals with genetic variants of frontotemporal dementia and healthy controls from the Genetic FTD Initiative (GENFI) study. Our method, take full advantage of the LDDMM framework, and relies on the creation of a population specific average spatiotemporal trajectory of a relevant brain structure of interest, the thalamus in our case. The residuals from each patient data to the average spatiotemporal trajectory are then clustered and studied to assess when presymptomatic mutation carriers differ from healthy control subjects.\n\nWe found statistical differences in shape in the anterior region of the thalamus at least five years before the mutation carrier subjects develop any clinical symptoms. This region of the thalamus has been shown to be predominantly connected to the frontal lobe, consistent with the pattern of cortical atrophy seen in the disease.

neuroscience↗

bioRxiv2018

Application of mechanistic methods to clinical trials in multiple sclerosis: the simvastatin case

The analysis of clinical trials is limited to pre-specified outcomes, thereby precluding a mechanistic understanding of the treatment response. Multivariate mechanistic models can elucidate the causal chain of events by simultaneous analysis of multimodal data that link intermediate variables to outcomes of interest. A double-blind, randomised, controlled, phase 2 clinical trial in secondary progressive multiple sclerosis (MS-STAT, NCT00647348) demonstrated that simvastatin (80mg/day) over two years reduced the brain atrophy rate and was associated with beneficial effects on cognitive and disability outcomes. Therefore, this trial offers an opportunity to apply mechanistic models to investigate the hypothesised pathways that link simvastatin to clinical outcome measures, either directly or indirectly via changes in serum total cholesterol levels and to determine which is the more likely.

neuroscience↗

bioRxiv2017

Uncovering the heterogeneity and temporal complexity of neurodegenerative diseases with Subtype and Stage Inference

The heterogeneity of neurodegenerative diseases is a key confound to disease understanding and treatment development, as study cohorts typically include multiple phenotypes on distinct disease trajectories. Here we present a new machine learning technique - Subtype and Stage Inference (SuStaIn) - able to uncover data-driven disease phenotypes with distinct temporal progression patterns, from widely available crosssectional patient studies. Results from imaging studies in two neurodegenerative diseases reveal new subgroups and their distinct trajectories of regional neurodegeneration. In genetic frontotemporal dementia, SuStaIn identifies genotypes from imaging alone, validating its ability to identify subtypes, and characterises within-group heterogeneity for the first time. In Alzheimers disease, SuStaIn uncovers three subtypes, uniquely revealing their temporal complexity. SuStaIn provides fine-grained patient stratification, which substantially enhances the ability to predict conversion between diagnostic categories over standard models that ignore subtype (p=7.18x10--4) or temporal stage (p=3.96x10-5). SuStaIn thus offers new promise for enabling disease subtype discovery and precision medicine.

neuroscience↗

bioRxiv2017

Progression of regional grey matter atrophy in multiple sclerosis

Grey matter atrophy is present from the earliest clinical stages of multiple sclerosis (MS), but the temporal ordering is poorly understood. We aimed to determine the sequence in which grey matter regions become atrophic in MS, and its association with disability accumulation.\n\nIn this longitudinal study, we included 1,417 subjects: 253 with clinically-isolated syndrome (CIS), 708 relapsing-remitting MS (RRMS), 128 secondary-progressive MS (SPMS), 125 primary-progressive MS (PPMS), and 203 healthy controls from 7 European centres. Subjects underwent repeated MRI scanning (total number of scans 3,604); the mean follow-up for patients was 2.41yrs (SD{+/-}1.97). Disability was scored using the Expanded Disability Status Scale (EDSS). We calculated the volume of brain grey matter regions and brainstem using an unbiased within-subject template. We used an established data-driven event-based model (EBM) to determine the sequence of occurrence of atrophy and its uncertainty. We assigned each subject to a specific EBM stage, based on the number of their atrophic regions. We used nested linear mixed-effects regression models to explore the associations between the rate of increase in the EBM stages over time, disease duration and annual rate of EDSS gain.\n\nThe first regions to become atrophic in CIS and relapse-onset MS patients (RRMS and SPMS) were the posterior cingulate cortex and precuneus, followed by the middle cingulate cortex, brainstem and thalamus. The sequence of atrophy in PPMS showed a similar 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 MS and late atrophy in PPMS. Patients with SPMS showed the highest EBM stages (highest number of atrophic regions, all p<0.001) at study entry. Rates of increase in EBM stages were significantly different from healthy controls in all MS phenotypes, except for CIS. The increase in the number of atrophic regions (EBM stage) was associated with disease duration in all patients. EBM stage was associated with disability accumulation in RRMS independent of disease duration (p<0.0001).\n\nThis data-driven staging of atrophy progression in a large MS sample demonstrates that grey matter atrophy spreads to involve more regions over time. The sequence in which regions become atrophic is reasonably consistent across MS phenotypes. The spread of atrophy was associated with disease duration, and disability accumulation in RRMS.\n\nAbbreviations

neuroscience↗

bioRxiv2017

Deep grey matter volume loss drives disability worsening in multiple sclerosis

ObjectiveGrey matter (GM) atrophy occurs in all multiple sclerosis (MS) phenotypes. We investigated whether there is a spatiotemporal pattern of GM atrophy that is associated with faster disability accumulation in MS.\n\nMethodsWe analysed 3,604 brain high-resolution T1-weighted MRI scans from 1,417 participants: 1,214 MS patients (253 clinically-isolated syndrome[CIS], 708 relapsingremitting[RRMS], 128 secondary-progressive[SPMS], 125 primary-progressive[PPMS]), over an average follow-up of 2.41 years (standard deviation[SD]=1.97), and 203 healthy controls (HCs) [average follow-up=1.83 year, SD=1.77], attending 7 European centres. Disability was assessed with the Expanded-Disability Status Scale (EDSS). We obtained volumes of the deep GM (DGM), temporal, frontal, parietal, occipital and cerebellar GM, brainstem and cerebral white matter. Hierarchical mixed-models assessed annual percentage rate of regional tissue loss and identified regional volumes associated with time-to-EDSS progression.\n\nResultsSPMS showed the lowest baseline volumes of cortical GM and DGM. Of all baseline regional volumes, only that of the DGM predicted time-to-EDSS progression (hazard ratio=0.73, 95% CIs 0.65, 0.82; p<0.001): for every standard deviation decrease in baseline DGM volume, the risk of presenting a shorter time to EDSS worsening during follow-up increased by 27%. Of all longitudinal measures, DGM showed the fastest annual rate of atrophy, which was faster in SPMS (-1.45%), PPMS (-1.66%), and RRMS (-1.34%) than CIS (-0.88%) and HCs (-0.94%)[p<0.01]. The rate of temporal GM atrophy in SPMS (-1.21%) was significantly faster than RRMS (-0.76%), CIS (-0.75%), and HCs (-0.51%). Similarly, the rate of parietal GM atrophy in SPMS (-1.24-%) was faster than CIS (-0.63%) and HCs (-0.23%) (all p values <0.05). Only the atrophy rate in DGM in patients was significantly associated with disability accumulation (beta=0.04, p<0.001).\n\nInterpretationThis large multi-centre and longitudinal study shows that DGM volume loss drives disability accumulation in MS, and that temporal cortical GM shows accelerated atrophy in SPMS than RRMS. The difference in regional GM atrophy development between phenotypes needs to be taken into account when evaluating treatment effect of therapeutic interventions.

neuroscience↗