Project

Back to overview

MRI-based characterization of subgroups in aging and dementia

English title MRI-based characterization of subgroups in aging and dementia
Applicant Abdulkadir Ahmed
Number 191026
Funding scheme Postdoc.Mobility
Research institution Center for Biomedical Image Computing and Analytics (CBICA) University of Pennsylvania
Institution of higher education Institution abroad - IACH
Main discipline Neurophysiology and Brain Research
Start/End 01.02.2020 - 31.01.2022
Show all

All Disciplines (2)

Discipline
Neurophysiology and Brain Research
Information Technology

Keywords (6)

aging; dementia ; statistical analysis; magnetic resonance imaging; machine learning; heterogeneity

Lay Summary (German)

Lead
Neuro-degenerative Erkrankungen gefährden die psychische Gesundheit im Alter. Wie schnell der Abbau von Nervenzellen voranschreitet und wie stark sich dieser auf die kognitiven Fähigkeiten auswirkt ist sehr unterschiedlich. Dieses Projekt leistet einen Beitrag zur Ergründung von Zusammenhängen zwischen kognitiver Leistungsfähigkeiten und biologischen Messwerten aus bildgebenden Verfahren um künftig Prognosen zu verbessern.
Lay summary

Neurodegenerativen Erkrankungen, darunter auch die Alzheimer Krankheit, werden anhand klinischer Symptome sowie biologischer Charakteristiken beschrieben. Zu den klinischen Symptomen zählen zum Beispiel Schwierigkeiten sich Dinge zu merken oder sich zu orientieren. Biologische Eigenschaften sind zum Beispiel die Form und Grösse einzelner Gehirnregionen oder die Dosis gewisser Proteinaggregate in der Gehirnflüssigkeit. Für das das Wohlbefinden der kranken und deren Angehörigen sind die klinischen Symptome entscheidend, und diese verändern sich oft später als biologischen Eigenschaften. Der Zusammenhang zwischen der Biologie (Ursache) und der Kognition (Wirkung) ist komplex und vielfältig. Dieses Forschungsprojekt soll die Vielfältigkeit in der Population untersuchen. Um eine genügend breite und variable Population abzubilden, werden Daten aus mehrerer Datenbanken zusammengeführt und analysiert. Etablierte statistische Verfahren, maschinelles lernen und tiefes Lernen mittels künstlicher neuronalen Netzen werden kombiniert um neue Erkenntnisse zu gewinnen. Die Resultate werden in frei verfügbaren wissenschaftlichen Publikationen präsentiert und diskutiert werden. Dies wird zu einem besseren Verständnis vom gesundem Altern des Gehirns und den Effekten neurodegenerativer Krankheiten führen. Diese Erkenntnisse können zur bessern Auswahl von geeigneten Probanden für klinische Studien beitragen und durch genauere Prognosen die Patienten, Angehörige und Betreuer unterstützen.

Direct link to Lay Summary Last update: 10.02.2020

Lay Summary (English)

Lead
Neuro-degenerative disorders threaten the mental health of elderly people. The rate of loss of neurons and its effect to the cognitive capacity varies strongly across individuals.This project aims to improve our understanding of the interplay of cognitive performance and biological measures obtained from non-invasive brain imaging which eventually will result in more accurate prognosis.
Lay summary

Neuro-degenerative disorders, including Alzheimer's disease, are characterized by clinical symptoms and biological characteristics. Clinical symptoms include difficulties in remembering or spatial orientation. Biological characteristics include for instance size and shape of certain brain regions or the concentration of certain protein aggregates in the cerebro-spinal fluid. Clinical symptoms are most relevant for the patients and their relatives, whereas biological signs often appear earlier. The interplay between the biology (cause) and cognition (effect) is complex and heterogeneous. This project aims at studying the heterogeneity in the population. To cover a wide spectrum of the population, we will pool and analyze data from multiple data bases. Established statistical methods, machine learning, and deep learning are combined to obtain novel insights. The results will be presented and discussed in publicly available research articles. This will contribute to a better understanding of healthy aging as well as effects of neuro-degenerative disorders on individual clinical profiles. The findings will help to better select patients for clinical studies and thanks to more accurate prognosis also support patients, relatives, and caregivers.

Direct link to Lay Summary Last update: 10.02.2020

Responsible applicant and co-applicants

Abstract

The state and progression of the cognitive profile of elderly individuals is highly variable and clinically relevant. Sources of variability include effects of healthy aging (including experience and education), acute brain damage, and multiple effects of pathological neuro-degeneration attributed to clinical syndromes. Another part of the variability can be attributed to individual biomarkers. However, a considerable amount of variability in the cognitive profiles and their prognosis remains unexplained. If a disease manifests in a discrete number of sub-types, the implicit characteristics encoded in the grouping may be an additional source of variability. To test this hypothesis, we propose to group individuals based on a detailed biomarker characterization and assess the effect of the grouping variable on the prediction accuracy of the cognitive profile and the prognosis thereof. We propose to implement the grouping with a framework for a data-driven characterization of individuals based on their profile of biomarkers. While biomarkers derived from standard structural MRI are readily available, biomarkers from invasive and expensive procedures are not routinely acquired. The limited set of biomarkers still contains relevant information. To extend the field of application of the characterization to settings with missing data, we propose to use the hidden activation pattern of a deep neural multi-task encoder-decoder network trained with missing data and soft constraints as signature feature representation that is robust to missing data. To characterize the individuals, we first extract multiple morphological markers from structural MRI including regional brain volume, regional atrophy, and lesion load. The extracted biomarkers are then used to group individuals using a probabilistic staging model, a model of clustered trajectories, and a model of semi-supervised learning. We then assess the variations in biomarker and cognitive variables across groups and whether the grouping variables contribute to a better prognosis. Our contribution is combining our own recently developed state-of-the-art computerized brain morphometry algorithms and alternative promising markers based on MRI with three existing sophisticated grouping methods and the application/validation to/with a large data set. We evaluate the correlations on a large (N>5000) heterogeneous data set from elderly individuals and on a data set with age range between 22 and 84 years (N=1836). Using longitudinal data (N>200), we will assess the stability of the grouping and the contribution of the grouping to the quality of prognosis. To produce consistent groupings under presence of missing data, we propose the use of a deep encoder-decoder artificial neural network that extracts signature features that are robust to missing data and preserve the cross-subject variance to obtain the same grouping. The level of consistency between the prediction with and without a set of variables is an indirect measure of redundancy. We validate the use case of discovery of biological and cognitive correlates of subgroups in an independent sample after the grouping model was transferred from a large heterogeneous data set to the target sample with missing modalities. We expect that the biologically motivated data-driven stratification framework enables the discovery of variants of manifestations of brain pathologies and subsequently increased accuracy in estimating the disease progression. When applied to specific research question, the grouping can lead to the discovery of correlates (for instance a protecting factor) that are present in a certain subgroup. In the long term, refined tools and methods from this project could help to identify non-trivial characteristics that determine the efficacy of an intervention
-