Dataset Information

Transfer Learning for Alzheimer's Disease through Neuroimaging Biomarkers: A Systematic Review.

ABSTRACT: Alzheimer's disease (AD) is a remarkable challenge for healthcare in the 21st century. Since 2017, deep learning models with transfer learning approaches have been gaining recognition in AD detection, and progression prediction by using neuroimaging biomarkers. This paper presents a systematic review of the current state of early AD detection by using deep learning models with transfer learning and neuroimaging biomarkers. Five databases were used and the results before screening report 215 studies published between 2010 and 2020. After screening, 13 studies met the inclusion criteria. We noted that the maximum accuracy achieved to date for AD classification is 98.20% by using the combination of 3D convolutional networks and local transfer learning, and that for the prognostic prediction of AD is 87.78% by using pre-trained 3D convolutional network-based architectures. The results show that transfer learning helps researchers in developing a more accurate system for the early diagnosis of AD. However, there is a need to consider some points in future research, such as improving the accuracy of the prognostic prediction of AD, exploring additional biomarkers such as tau-PET and amyloid-PET to understand highly discriminative feature representation to separate similar brain patterns, managing the size of the datasets due to the limited availability.

SUBMITTER: Agarwal D

PROVIDER: S-EPMC8587338 | biostudies-literature | 2021 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Transfer Learning for Alzheimer's Disease through Neuroimaging Biomarkers: A Systematic Review.

Agarwal Deevyankar D Marques Gonçalo G de la Torre-Díez Isabel I Franco Martin Manuel A MA García Zapiraín Begoña B Martín Rodríguez Francisco F

Sensors (Basel, Switzerland) 20211031 21

Alzheimer's disease (AD) is a remarkable challenge for healthcare in the 21st century. Since 2017, deep learning models with transfer learning approaches have been gaining recognition in AD detection, and progression prediction by using neuroimaging biomarkers. This paper presents a systematic review of the current state of early AD detection by using deep learning models with transfer learning and neuroimaging biomarkers. Five databases were used and the results before screening report 215 stud ...[more]

PMID: 34770565

Similar Datasets

Project description:BackgroundAcupuncture effectively improves cognitive function in Alzheimer's disease (AD). Many neuroimaging studies have found significant brain alterations after acupuncture treatment of AD, but the underlying central modulation mechanism is unclear.ObjectiveThis review aims to provide neuroimaging evidence to understand the central mechanisms of acupuncture in patients with AD.MethodsRelevant neuroimaging studies about acupuncture for AD were retrieved from eight English and Chinese medicine databases (PubMed, Embase, Cochrane Library, Web of Science, SinoMed, CNKI, WF, VIP) and other resources from inception of databases until June 1, 2022, and their methodological quality was assessed using RoB 2.0 and ROBINS - I. Brain neuroimaging information was extracted to investigate the potential neural mechanism of acupuncture for AD. Descriptive statistics were used for data analysis.ResultsThirteen neuroimaging studies involving 275 participants were included in this review, and the overall methodological quality of included studies was moderate. The approaches applied included task-state functional magnetic resonance imaging (ts-fMRI; n = 9 studies) and rest-state functional magnetic resonance imaging (rs-fMRI; n = 4 studies). All studies focused on the instant effect of acupuncture on the brains of AD participants, including the cingulate gyrus, middle frontal gyrus, and cerebellum, indicating that acupuncture may regulate the default mode, central executive, and frontoparietal networks.ConclusionThis study provides evidence of the neural mechanisms underlying the effect of acupuncture on AD involving cognitive- and motor-associated networks. However, this evidence is still in the preliminary investigation stage. Large-scale, well-designed, multimodal neuroimaging trials are still required to provide comprehensive insight into the central mechanism underlying the effect of acupuncture on AD. (Systematic review registration at PROSPERO, No. CRD42022331527).

Project description:Alzheimer's disease can present clinically with either the typical amnestic phenotype or with atypical phenotypes, such as logopenic progressive aphasia and posterior cortical atrophy. We have recently described longitudinal patterns of flortaucipir PET uptake and grey matter atrophy in the atypical phenotypes, demonstrating a longitudinal regional disconnect between flortaucipir accumulation and brain atrophy. However, it is unclear how these longitudinal patterns differ from typical Alzheimer's disease, to what degree flortaucipir and atrophy mirror clinical phenotype in Alzheimer's disease, and whether optimal longitudinal neuroimaging biomarkers would also differ across phenotypes. We aimed to address these unknowns using a cohort of 57 participants diagnosed with Alzheimer's disease (18 with typical amnestic Alzheimer's disease, 17 with posterior cortical atrophy and 22 with logopenic progressive aphasia) that had undergone baseline and 1-year follow-up MRI and flortaucipir PET. Typical Alzheimer's disease participants were selected to be over 65 years old at baseline scan, while no age criterion was used for atypical Alzheimer's disease participants. Region and voxel-level rates of tau accumulation and atrophy were assessed relative to 49 cognitively unimpaired individuals and among phenotypes. Principal component analysis was implemented to describe variability in baseline tau uptake and rates of accumulation and baseline grey matter volumes and rates of atrophy across phenotypes. The capability of the principal components to discriminate between phenotypes was assessed with logistic regression. The topography of longitudinal tau accumulation and atrophy differed across phenotypes, with key regions of tau accumulation in the frontal and temporal lobes for all phenotypes and key regions of atrophy in the occipitotemporal regions for posterior cortical atrophy, left temporal lobe for logopenic progressive aphasia and medial and lateral temporal lobe for typical Alzheimer's disease. Principal component analysis identified patterns of variation in baseline and longitudinal measures of tau uptake and volume that were significantly different across phenotypes. Baseline tau uptake mapped better onto clinical phenotype than longitudinal tau and MRI measures. Our study suggests that optimal longitudinal neuroimaging biomarkers for future clinical treatment trials in Alzheimer's disease are different for MRI and tau-PET and may differ across phenotypes, particularly for MRI. Baseline tau tracer retention showed the highest fidelity to clinical phenotype, supporting the important causal role of tau as a driver of clinical dysfunction in Alzheimer's disease.

Project description:BackgroundUsing surrogate biomarkers for disease progression as endpoints in neuroprotective clinical trials may help differentiate symptomatic effects of potential neuroprotective agents from true slowing of the neurodegenerative process. A systematic review was undertaken to determine what biomarkers for disease progression in Alzheimer's disease exist and how well they perform.MethodsMEDLINE and Embase (1950-2011) were searched using five search strategies. Abstracts were assessed to identify papers meriting review in full. Studies of participants with probable Alzheimer's disease diagnosed by formal criteria were included. We made no restriction on age, disease duration, or drug treatment. We only included studies with a longitudinal design, in which the putative biomarker and clinical measure were both measured at least twice, as this is the only appropriate study design to use when developing a disease progression biomarker. We included studies which attempted to draw associations between the changes over time in the biomarker used to investigate disease progression and a clinical measure of disease progression.ResultsFifty-nine studies were finally included. The commonest biomarker modality examined was brain MRI (17/59, 29% of included studies). Median follow-up in included studies was only 1.0 (IQR 0.8-1.7) year and most studies only measured the putative biomarker and clinical measure twice. Included studies were generally of poor quality with small numbers of participants (median 31 (IQR 17 to 64)), applied excessively restrictive study entry criteria, had flawed methodologies and conducted overly simplistic statistical analyses without adjusting for confounding factors.ConclusionsWe found insufficient evidence to recommend the use of any biomarker as an outcome measure for disease progression in Alzheimer's disease trials. However, further investigation into the efficacy of using MRI measurements of ventricular volume and whole brain volume appeared to be merited. A provisional 'roadmap' to improve the quality of future disease progression biomarker studies is presented.

Dataset Information

Transfer Learning for Alzheimer's Disease through Neuroimaging Biomarkers: A Systematic Review.

Publications

Transfer Learning for Alzheimer's Disease through Neuroimaging Biomarkers: A Systematic Review.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets