1
|
Rebsamen M, Suter Y, Wiest R, Reyes M, Rummel C. Brain Morphometry Estimation: From Hours to Seconds Using Deep Learning. Front Neurol 2020; 11:244. [PMID: 32322235 PMCID: PMC7156625 DOI: 10.3389/fneur.2020.00244] [Citation(s) in RCA: 11] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/28/2019] [Accepted: 03/13/2020] [Indexed: 12/13/2022] Open
Abstract
Motivation: Brain morphometry from magnetic resonance imaging (MRI) is a promising neuroimaging biomarker for the non-invasive diagnosis and monitoring of neurodegenerative and neurological disorders. Current tools for brain morphometry often come with a high computational burden, making them hard to use in clinical routine, where time is often an issue. We propose a deep learning-based approach to predict the volumes of anatomically delineated subcortical regions of interest (ROI), and mean thicknesses and curvatures of cortical parcellations directly from T1-weighted MRI. Advantages are the timely availability of results while maintaining a clinically relevant accuracy. Materials and Methods: An anonymized dataset of 574 subjects (443 healthy controls and 131 patients with epilepsy) was used for the supervised training of a convolutional neural network (CNN). A silver-standard ground truth was generated with FreeSurfer 6.0. Results: The CNN predicts a total of 165 morphometric measures directly from raw MR images. Analysis of the results using intraclass correlation coefficients showed, in general, good correlation with FreeSurfer generated ground truth data, with some of the regions nearly reaching human inter-rater performance (ICC > 0.75). Cortical thicknesses predicted by the CNN showed cross-sectional annual age-related gray matter atrophy rates both globally (thickness change of -0.004 mm/year) and regionally in agreement with the literature. A statistical test to dichotomize patients with epilepsy from healthy controls revealed similar effect sizes for structures affecting all subtypes as reported in a large-scale epilepsy study. Conclusions: We demonstrate the general feasibility of using deep learning to estimate human brain morphometry directly from T1-weighted MRI within seconds. A comparison of the results to other publications shows accuracies of comparable magnitudes for the subcortical volumes and cortical thicknesses.
Collapse
Affiliation(s)
- Michael Rebsamen
- Support Center for Advanced Neuroimaging (SCAN), University Institute of Diagnostic and Interventional Neuroradiology, University of Bern, Inselspital, Bern University Hospital, Bern, Switzerland
- Graduate School for Cellular and Biomedical Sciences, University of Bern, Bern, Switzerland
| | - Yannick Suter
- Insel Data Science Center, Inselspital, Bern University Hospital, Bern, Switzerland
- ARTORG Center for Biomedical Research, University of Bern, Bern, Switzerland
| | - Roland Wiest
- Support Center for Advanced Neuroimaging (SCAN), University Institute of Diagnostic and Interventional Neuroradiology, University of Bern, Inselspital, Bern University Hospital, Bern, Switzerland
| | - Mauricio Reyes
- Insel Data Science Center, Inselspital, Bern University Hospital, Bern, Switzerland
- ARTORG Center for Biomedical Research, University of Bern, Bern, Switzerland
| | - Christian Rummel
- Support Center for Advanced Neuroimaging (SCAN), University Institute of Diagnostic and Interventional Neuroradiology, University of Bern, Inselspital, Bern University Hospital, Bern, Switzerland
| |
Collapse
|
2
|
Graham SA, Lee EE, Jeste DV, Van Patten R, Twamley EW, Nebeker C, Yamada Y, Kim HC, Depp CA. Artificial intelligence approaches to predicting and detecting cognitive decline in older adults: A conceptual review. Psychiatry Res 2020; 284:112732. [PMID: 31978628 PMCID: PMC7081667 DOI: 10.1016/j.psychres.2019.112732] [Citation(s) in RCA: 54] [Impact Index Per Article: 13.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/09/2019] [Revised: 12/04/2019] [Accepted: 12/07/2019] [Indexed: 12/13/2022]
Abstract
Preserving cognition and mental capacity is critical to aging with autonomy. Early detection of pathological cognitive decline facilitates the greatest impact of restorative or preventative treatments. Artificial Intelligence (AI) in healthcare is the use of computational algorithms that mimic human cognitive functions to analyze complex medical data. AI technologies like machine learning (ML) support the integration of biological, psychological, and social factors when approaching diagnosis, prognosis, and treatment of disease. This paper serves to acquaint clinicians and other stakeholders with the use, benefits, and limitations of AI for predicting, diagnosing, and classifying mild and major neurocognitive impairments, by providing a conceptual overview of this topic with emphasis on the features explored and AI techniques employed. We present studies that fell into six categories of features used for these purposes: (1) sociodemographics; (2) clinical and psychometric assessments; (3) neuroimaging and neurophysiology; (4) electronic health records and claims; (5) novel assessments (e.g., sensors for digital data); and (6) genomics/other omics. For each category we provide examples of AI approaches, including supervised and unsupervised ML, deep learning, and natural language processing. AI technology, still nascent in healthcare, has great potential to transform the way we diagnose and treat patients with neurocognitive disorders.
Collapse
Affiliation(s)
- Sarah A Graham
- Department of Psychiatry, University of California San Diego, La Jolla, CA, United States; Sam and Rose Stein Institute for Research on Aging, University of California San Diego, La Jolla, CA, United States; IBM-UCSD Artificial Intelligence for Healthy Living Program, La Jolla, CA, United States
| | - Ellen E Lee
- Department of Psychiatry, University of California San Diego, La Jolla, CA, United States; Sam and Rose Stein Institute for Research on Aging, University of California San Diego, La Jolla, CA, United States; IBM-UCSD Artificial Intelligence for Healthy Living Program, La Jolla, CA, United States; VA San Diego Healthcare System, San Diego, CA, United States
| | - Dilip V Jeste
- Department of Psychiatry, University of California San Diego, La Jolla, CA, United States; Sam and Rose Stein Institute for Research on Aging, University of California San Diego, La Jolla, CA, United States; IBM-UCSD Artificial Intelligence for Healthy Living Program, La Jolla, CA, United States; Department of Neurosciences, University of California San Diego, La Jolla, CA, United States.
| | - Ryan Van Patten
- Department of Psychiatry, University of California San Diego, La Jolla, CA, United States; Sam and Rose Stein Institute for Research on Aging, University of California San Diego, La Jolla, CA, United States; IBM-UCSD Artificial Intelligence for Healthy Living Program, La Jolla, CA, United States
| | - Elizabeth W Twamley
- Department of Psychiatry, University of California San Diego, La Jolla, CA, United States; Sam and Rose Stein Institute for Research on Aging, University of California San Diego, La Jolla, CA, United States; IBM-UCSD Artificial Intelligence for Healthy Living Program, La Jolla, CA, United States; VA San Diego Healthcare System, San Diego, CA, United States
| | - Camille Nebeker
- Sam and Rose Stein Institute for Research on Aging, University of California San Diego, La Jolla, CA, United States; IBM-UCSD Artificial Intelligence for Healthy Living Program, La Jolla, CA, United States; Department of Family Medicine and Public Health, University of California San Diego, La Jolla, CA, United States
| | | | - Ho-Cheol Kim
- IBM-UCSD Artificial Intelligence for Healthy Living Program, La Jolla, CA, United States; Scalable Knowledge Intelligence, IBM Research-Almaden, San Jose, CA, United States
| | - Colin A Depp
- Department of Psychiatry, University of California San Diego, La Jolla, CA, United States; Sam and Rose Stein Institute for Research on Aging, University of California San Diego, La Jolla, CA, United States; IBM-UCSD Artificial Intelligence for Healthy Living Program, La Jolla, CA, United States; VA San Diego Healthcare System, San Diego, CA, United States
| |
Collapse
|
3
|
Nowrangi MA, Lyketsos CG, Rosenberg PB. Principles and management of neuropsychiatric symptoms in Alzheimer's dementia. Alzheimers Res Ther 2015; 7:12. [PMID: 27391771 PMCID: PMC4571139 DOI: 10.1186/s13195-015-0096-3] [Citation(s) in RCA: 77] [Impact Index Per Article: 8.6] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/14/2023]
Abstract
Neuropsychiatric symptoms of Alzheimer's disease (NPS-AD) are highly prevalent and lead to poor medical and functional outcomes. In spite of the burdensome nature of NPS-AD, we are continuing to refine the nosology and only beginning to understand the underlying pathophysiology. Cluster analyses have frequently identified three to five subsyndromes of NPS-AD: behavioral dysfunction (for example, agitation/aggressiveness), psychosis (for example, delusions and hallucinations), and mood disturbance (for example, depression or apathy). Recent neurobiological studies have used new neuroimaging techniques to elucidate behaviorally relevant circuits and networks associated with these subsyndromes. Several fronto-subcortical circuits, cortico-cortical networks, and neurotransmitter systems have been proposed as regions and mechanisms underlying NPS-AD. Common to most of these subsyndromes is the broad overlap of regions associated with the salience network (anterior cingulate and insula), mood regulation (amygdala), and motivated behavior (frontal cortex). Treatment strategies for dysregulated mood syndromes (depression and apathy) have primarily targeted serotonergic mechanisms with antidepressants or dopaminergic mechanisms with psychostimulants. Psychotic symptoms have largely been targeted with anti-psychotic medications despite controversial risk/benefit tradeoffs. Management of behavioral dyscontrol, including agitation and aggression in AD, has encompassed a wide range of psychoactive medications as well as non-pharmacological approaches. Developing rational therapeutic approaches for NPS-AD will require a firmer understanding of the underlying etiology in order to improve nosology as well as provide the empirical evidence necessary to overcome regulatory and funding challenges to further study these debilitating symptoms.
Collapse
Affiliation(s)
- Milap A Nowrangi
- Division of Geriatric Psychiatry and Neuropsychiatry, Department of Psychiatry and Behavioral Sciences, Johns Hopkins University School of Medicine, 5300 Alpha Commons Dr, 4th Floor, Baltimore, MD 21225 USA
| | - Constantine G Lyketsos
- Division of Geriatric Psychiatry and Neuropsychiatry, Department of Psychiatry and Behavioral Sciences, Johns Hopkins University School of Medicine, 5300 Alpha Commons Dr, 4th Floor, Baltimore, MD 21225 USA
| | - Paul B Rosenberg
- Division of Geriatric Psychiatry and Neuropsychiatry, Department of Psychiatry and Behavioral Sciences, Johns Hopkins University School of Medicine, 5300 Alpha Commons Dr, 4th Floor, Baltimore, MD 21225 USA
| |
Collapse
|