Beyond the AJR: “MRI signatures of brain age and disease over the lifespan based on a deep brain network and 14468 individuals worldwide”

2020 ◽  
Author(s):  
Cyrus A. Raji ◽  
Tammie L.S. Benzinger
Keyword(s):  
Brain Network ◽  
Brain Age ◽  
Deep Brain

scholarly journals MRI signatures of brain age and disease over the lifespan based on a deep brain network and 14 468 individuals worldwide

Brain ◽  
2020 ◽  
Vol 143 (7) ◽  
pp. 2312-2324 ◽  
Author(s):  
Vishnu M Bashyam ◽  
Guray Erus ◽  
Jimit Doshi ◽  
Mohamad Habes ◽  
Ilya M Nasrallah ◽  
...  
Keyword(s):  
Deep Learning ◽  
Image Data ◽  
Brain Network ◽  
Brain Diseases ◽  
Normal Brain ◽  
Brain Health ◽  
Brain Ageing ◽  
Brain Age ◽  
Age Estimates ◽  
Deep Brain

Abstract Deep learning has emerged as a powerful approach to constructing imaging signatures of normal brain ageing as well as of various neuropathological processes associated with brain diseases. In particular, MRI-derived brain age has been used as a comprehensive biomarker of brain health that can identify both advanced and resilient ageing individuals via deviations from typical brain ageing. Imaging signatures of various brain diseases, including schizophrenia and Alzheimer’s disease, have also been identified using machine learning. Prior efforts to derive these indices have been hampered by the need for sophisticated and not easily reproducible processing steps, by insufficiently powered or diversified samples from which typical brain ageing trajectories were derived, and by limited reproducibility across populations and MRI scanners. Herein, we develop and test a sophisticated deep brain network (DeepBrainNet) using a large (n = 11 729) set of MRI scans from a highly diversified cohort spanning different studies, scanners, ages and geographic locations around the world. Tests using both cross-validation and a separate replication cohort of 2739 individuals indicate that DeepBrainNet obtains robust brain-age estimates from these diverse datasets without the need for specialized image data preparation and processing. Furthermore, we show evidence that moderately fit brain ageing models may provide brain age estimates that are most discriminant of individuals with pathologies. This is not unexpected as tightly-fitting brain age models naturally produce brain-age estimates that offer little information beyond age, and loosely fitting models may contain a lot of noise. Our results offer some experimental evidence against commonly pursued tightly-fitting models. We show that the moderately fitting brain age models obtain significantly higher differentiation compared to tightly-fitting models in two of the four disease groups tested. Critically, we demonstrate that leveraging DeepBrainNet, along with transfer learning, allows us to construct more accurate classifiers of several brain diseases, compared to directly training classifiers on patient versus healthy control datasets or using common imaging databases such as ImageNet. We, therefore, derive a domain-specific deep network likely to reduce the need for application-specific adaptation and tuning of generic deep learning networks. We made the DeepBrainNet model freely available to the community for MRI-based evaluation of brain health in the general population and over the lifespan.

scholarly journals Deep brain stimulation of the fornix as a therapeutic approach for Alzheimer’s disease: Systematic Review

2021 ◽  
Author(s):  
Paloma Abrantes de Oliveira ◽  
Diogo Abrantes de Oliveira ◽  
Isabelle Magalhães Guedes Freitas
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Deep Brain Stimulation ◽  
Brain Stimulation ◽  
Randomized Clinical Trials ◽  
Anterior Commissure ◽  
Brain Network ◽  
Double Blind ◽  
Alzheimer Dementia ◽  
Deep Brain

INTRODUCTION: Alzheimer’s disease (AD) is a disorder characterized by cognitive impairment. The brain network in DA can be interrupted by deficiencies in glucose metabolismo. Deep brain stimulation (DBS) is used in Parkinson’s disease (PM), once it modulates motor circuits. Considering this potential, the benefits of this approach in DA must be evaluated1,2. OBJECTIVE: To investigate the potential benefit of stimulating the cerebral fornix (CF) through DBS for patients with AD. METHODS: Controlled and randomized clinical trials (ECCR), in English, performed on humans, in the last 5 years, indexed on PubMed, were selected from the keywords “Deep brain Stimulation” and “Alzheimer Dementia”. This review was registered on PROSPERO by protocol 254506 and the PRISMA recommendation was used to improve its organization. RESULTS: Deeb W et al. (2019) conducted an ECCR on 42 patients with AD receiving DBS in CF, anterior commissure, corpus and sub-corpus callosum, demonstrating that in 48% of them, old experiences were reported. Furthermore, the memories became better as the stimulation increased. Lozano AM et al. (2016), in turn, developed an ECCR on 6 patients receiving DBS in CF, showing increases in glucose metabolism in some cerebral areas after 12 months, contrasting to the expected reduction in AD, especially in > 65 years. It’s noteworthy that the multicenter and double-blind ECCR by Ponce FA (2016) showed the safety of DBS in CF as therapy for AD, similar to that verified in the MP. CONCLUSION: The analyzed evidences suggest a potential cognitive benefit of DBS in the therapeutic management of AD.

scholarly journals Abnormal Functional Brain Network in Parkinson's Disease and the Effect of Acute Deep Brain Stimulation

2021 ◽  
Vol 12 ◽  
Author(s):  
Zhibao Li ◽  
Chong Liu ◽  
Qiao Wang ◽  
Kun Liang ◽  
Chunlei Han ◽  
...  
Keyword(s):  
Deep Brain Stimulation ◽  
Functional Connectivity ◽  
Frequency Band ◽  
Brain Regions ◽  
Brain Network ◽  
Clustering Coefficient ◽  
Functional Brain ◽  
Frequency Bands ◽  
The Brain ◽  
Deep Brain

Objective: The objective of this study was to use functional connectivity and graphic indicators to investigate the abnormal brain network topological characteristics caused by Parkinson's disease (PD) and the effect of acute deep brain stimulation (DBS) on those characteristics in patients with PD.Methods: We recorded high-density EEG (256 channels) data from 21 healthy controls (HC) and 20 patients with PD who were in the DBS-OFF state and DBS-ON state during the resting state with eyes closed. A high-density EEG source connectivity method was used to identify functional brain networks. Power spectral density (PSD) analysis was compared between the groups. Functional connectivity was calculated for 68 brain regions in the theta (4–8 Hz), alpha (8–13 Hz), beta1 (13–20 Hz), and beta2 (20–30 Hz) frequency bands. Network estimates were measured at both the global (network topology) and local (inter-regional connection) levels.Results: Compared with HC, PSD was significantly increased in the theta (p = 0.003) frequency band and was decreased in the beta1 (p = 0.009) and beta2 (p = 0.04) frequency bands in patients with PD. However, there were no differences in any frequency bands between patients with PD with DBS-OFF and DBS-ON. The clustering coefficient and local efficiency of patients with PD showed a significant decrease in the alpha, beta1, and beta2 frequency bands (p < 0.001). In addition, edgewise statistics showed a significant difference between the HC and patients with PD in all analyzed frequency bands (p < 0.005). However, there were no significant differences between the DBS-OFF state and DBS-ON state in the brain network, except for the functional connectivity in the beta2 frequency band (p < 0.05).Conclusion: Compared with HC, patients with PD showed the following characteristics: slowed EEG background activity, decreased clustering coefficient and local efficiency of the brain network, as well as both increased and decreased functional connectivity between different brain areas. Acute DBS induces a local response of the brain network in patients with PD, mainly showing decreased functional connectivity in a few brain regions in the beta2 frequency band.

Targeted Circuit Manipulations in the Modeling of OCD

2017 ◽  
Author(s):  
Susanne E. Ahmari
Keyword(s):  
Neural Circuit ◽  
Brain Network ◽  
Repetitive Behaviors ◽  
Imaging Studies ◽  
Targeted Treatments ◽  
Excessive Grooming ◽  
The Brain ◽  
Shed Light ◽  
Deep Brain

Work in animal models has great potential to shed light on the neural circuit perturbations that lead to OCD-related behaviors. Circuit-specific manipulations allow testing of the causal role of the brain network abnormalities observed in clinical imaging studies, with a precision that is not possible in investigations in humans. In recent years, circuit-specific manipulations in animals using a range of technologies have confirmed that abnormalities in the cortico-striatal circuitry can produce repetitive behaviors, such as excessive grooming. This chapter summarizes these advances. Refining our understanding of the contribution of particular neural circuits to OCD-relevant behaviors can inform the development of anatomically targeted treatments, such as deep brain stimulation.

scholarly journals Recent advances in understanding and managing dystonia

F1000Research ◽  
2018 ◽  
Vol 7 ◽  
pp. 1124 ◽  
Author(s):  
Stephen Tisch
Keyword(s):  
Focused Ultrasound ◽  
Brain Network ◽  
Imaging Genetics ◽  
Treatment Modalities ◽  
Biological Processes ◽  
New Treatment ◽  
Clinical Advances ◽  
Deep Brain ◽  
Made In

Within the field of movement disorders, the conceptual understanding of dystonia has continued to evolve. Clinical advances have included improvements in recognition of certain features of dystonia, such as tremor, and understanding of phenotypic spectrums in the genetic dystonias and dystonia terminology and classification. Progress has also been made in the understanding of underlying biological processes which characterize dystonia from discoveries using approaches such as neurophysiology, functional imaging, genetics, and animal models. Important advances include the role of the cerebellum in dystonia, the concept of dystonia as an aberrant brain network disorder, additional evidence supporting the concept of dystonia endophenotypes, and new insights into psychogenic dystonia. These discoveries have begun to shape treatment approaches as, in parallel, important new treatment modalities, including magnetic resonance imaging-guided focused ultrasound, have emerged and existing interventions such as deep brain stimulation have been further refined. In this review, these topics are explored and discussed.

Structural Deep Brain Network Mining

2017 ◽  
Author(s):  
Shen Wang ◽  
Lifang He ◽  
Bokai Cao ◽  
Chun-Ta Lu ◽  
Philip S. Yu ◽  
...  
Keyword(s):  
Brain Network ◽  
Network Mining ◽  
Deep Brain

scholarly journals Brain age prediction using fMRI network coupling in youths and associations with psychiatric symptoms

2021 ◽  
Author(s):  
Martina J. Lund ◽  
Dag Alnæs ◽  
Ann-Marie de Lange ◽  
Ole A. Andreassen ◽  
Lars T. Westlye ◽  
...  
Keyword(s):  
Functional Connectivity ◽  
Psychiatric Symptoms ◽  
Model Performance ◽  
Symptom Burden ◽  
Brain Network ◽  
Brain Maturation ◽  
Age Gap ◽  
Age Range ◽  
Brain Age ◽  
Age Prediction

AbstractObjectiveMagnetic resonance imaging (MRI) has shown that estimated brain age is deviant from chronological age in various common brain disorders. Brain age estimation could be useful for investigating patterns of brain maturation and integrity, aiding to elucidate brain mechanisms underlying these heterogeneous conditions. Here, we examined functional brain age in two large samples of children and adolescents and its relation to mental health.MethodsWe used resting-state fMRI data from the Philadelphia Neurodevelopmental Cohort (PNC; n=1126, age range 8-22 years) to estimate functional connectivity between brain networks, and utilized these as features for brain age prediction. We applied the prediction model to 1387 individuals (age range 8-22 years) in the Healthy Brain Network sample (HBN). In addition, we estimated brain age in PNC using a cross-validation framework. Next, we tested for associations between brain age gap and various aspects of psychopathology and cognitive performance.ResultsOur model was able to predict age in the independent test samples, with a model performance of r=0.54 for the HBN test set, supporting consistency in functional connectivity patterns between samples and scanners. Linear models revealed a significant association between brain age gap and psychopathology in PNC, where individuals with a lower estimated brain age, had a higher overall symptom burden. These associations were not replicated in HBN.DiscussionOur findings support the use of brain age prediction from fMRI-based connectivity. While requiring further extensions and validations, the approach may be instrumental for detecting brain phenotypes related to intrinsic connectivity and could assist in characterizing risk in non-typically developing populations.

Sign in / Sign up

Export Citation Format

Share Document