Format

Send to

Choose Destination
Addict Biol. 2017 Sep;22(5):1459-1472. doi: 10.1111/adb.12418. Epub 2016 Jun 8.

Multi-modal MRI classifiers identify excessive alcohol consumption and treatment effects in the brain.

Author information

1
Instituto de Neurociencias, Consejo Superior de Investigaciones Científicas and Universidad Miguel Hernández, Sant Joan d'Alacant, Spain.
2
Center for Biomaterials and Tissue Engineering, Universitat Politècnica de València, Valencia, Spain.
3
School of Pharmacy University of Camerino, Camerino, Italy.
4
Department of Pharmacology, Faculty of Medicine, University of Helsinki, Helsinki, Finland.
5
Department of Psychopharmacology, Central Institute of Mental Health, University of Heidelberg, Mannheim, Germany.

Abstract

Robust neuroimaging markers of neuropsychiatric disorders have proven difficult to obtain. In alcohol use disorders, profound brain structural deficits can be found in severe alcoholic patients, but the heterogeneity of unimodal MRI measurements has so far precluded the identification of selective biomarkers, especially for early diagnosis. In the present work we used a combination of multiple MRI modalities to provide comprehensive and insightful descriptions of brain tissue microstructure. We performed a longitudinal experiment using Marchigian-Sardinian (msP) rats, an established model of chronic excessive alcohol consumption, and acquired multi-modal images before and after 1 month of alcohol consumption (6.8 ± 1.4 g/kg/day, mean ± SD), as well as after 1 week of abstinence with or without concomitant treatment with the antirelapse opioid antagonist naltrexone (2.5 mg/kg/day). We found remarkable sensitivity and selectivity to accurately classify brains affected by alcohol even after the relative short exposure period. One month drinking was enough to imprint a highly specific signature of alcohol consumption. Brain alterations were regionally specific and affected both gray and white matter and persisted into the early abstinence state without any detectable recovery. Interestingly, naltrexone treatment during early abstinence resulted in subtle brain changes that could be distinguished from non-treated abstinent brains, suggesting the existence of an intermediate state associated with brain recovery from alcohol exposure induced by medication. The presented framework is a promising tool for the development of biomarkers for clinical diagnosis of alcohol use disorders, with capacity to further inform about its progression and response to treatment.

KEYWORDS:

alcohol use disorders; classification algorithms; machine learning; multi-modal MRI; naltrexone; rat

PMID:
27273582
DOI:
10.1111/adb.12418
[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for Wiley
Loading ...
Support Center