Test–Retest Reliability of Deep Learning Analysis of Brain Volumes in Adolescent Brain

Magnetic resonance imaging (MRI) is essential for studying brain development and psychiatric disorders in adolescents. However, the imaging consistency remains challenging, highlighting the need for advanced methodologies to improve the diagnostic and research reliability in this unique developmenta...

Full description

Saved in:
Bibliographic Details
Main Authors: Anna-Maria Kasparbauer, Heidrun Lioba Wunram, Fabian Abuhsin, Friederike Körber, Eckhard Schönau, Stephan Bender, Ibrahim Duran
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Information
Subjects:
Online Access:https://www.mdpi.com/2078-2489/15/12/748
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850059139621847040
author Anna-Maria Kasparbauer
Heidrun Lioba Wunram
Fabian Abuhsin
Friederike Körber
Eckhard Schönau
Stephan Bender
Ibrahim Duran
author_facet Anna-Maria Kasparbauer
Heidrun Lioba Wunram
Fabian Abuhsin
Friederike Körber
Eckhard Schönau
Stephan Bender
Ibrahim Duran
author_sort Anna-Maria Kasparbauer
collection DOAJ
description Magnetic resonance imaging (MRI) is essential for studying brain development and psychiatric disorders in adolescents. However, the imaging consistency remains challenging, highlighting the need for advanced methodologies to improve the diagnostic and research reliability in this unique developmental period. Adolescence is marked by significant neuroanatomical changes, distinguishing adolescent brains from those of adults and making age-specific imaging research crucial for understanding the neuropsychiatric conditions in youth. This study examines the test–retest reliability of anatomical brain MRI scans in adolescents diagnosed with depressive disorders, emphasizing a developmental perspective on neuropsychiatric disorders. Using a sample of 42 adolescents, we assessed the consistency of structural imaging metrics across 95 brain regions with deep learning-based neuroimaging analysis pipelines. The results demonstrated moderate to excellent reliability, with the intraclass correlation coefficients (ICC) ranging from 0.57 to 0.99 across regions. Notably, regions such as the pallidum, amygdala, entorhinal cortex, and white matter hypointensities showed moderate reliability, likely reflecting the challenges in the segmentation or inherent anatomical variability unique to this age group. This study highlights the necessity of integrating advanced imaging technologies to enhance the accuracy and reliability of the neuroimaging data specific to adolescents. Addressing the regional variability and strengthening the methodological rigor are essential for advancing the understanding of brain development and psychiatric disorders in this distinct developmental stage. Future research should focus on larger, more diverse samples, multi-site studies, and emerging imaging techniques to further validate the neuroimaging biomarkers. Such advancements could improve the clinical outcomes and deepen our understanding of the neuropsychiatric conditions unique to adolescence.
format Article
id doaj-art-4e3978560bd44e3b96059abe55abc705
institution DOAJ
issn 2078-2489
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Information
spelling doaj-art-4e3978560bd44e3b96059abe55abc7052025-08-20T02:50:59ZengMDPI AGInformation2078-24892024-11-01151274810.3390/info15120748Test–Retest Reliability of Deep Learning Analysis of Brain Volumes in Adolescent BrainAnna-Maria Kasparbauer0Heidrun Lioba Wunram1Fabian Abuhsin2Friederike Körber3Eckhard Schönau4Stephan Bender5Ibrahim Duran6Department of Child and Adolescent Psychiatry, Psychosomatics and Psychotherapy, Faculty of Medicine and University Hospital Cologne, University of Cologne, 50931 Cologne, GermanyDepartment of Child and Adolescent Psychiatry, Psychosomatics and Psychotherapy, Faculty of Medicine and University Hospital Cologne, University of Cologne, 50931 Cologne, GermanyDepartment of General Pediatrics, Neonatology and Pediatric Cardiology, Medical Faculty, University Hospital, 40255 Düsseldorf, GermanyDepartment of Pediatric Radiology, Medical Faculty, University Hospital, 50931 Cologne, GermanyCenter of Prevention and Rehabilitation, Medical Faculty, University Hospital, University of Cologne, UniReha, 50931 Cologne, GermanyDepartment of Child and Adolescent Psychiatry, Psychosomatics and Psychotherapy, Faculty of Medicine and University Hospital Cologne, University of Cologne, 50931 Cologne, GermanyDepartment of Pediatrics, Medical Faculty, University Hospital, University of Cologne, 50931 Cologne, GermanyMagnetic resonance imaging (MRI) is essential for studying brain development and psychiatric disorders in adolescents. However, the imaging consistency remains challenging, highlighting the need for advanced methodologies to improve the diagnostic and research reliability in this unique developmental period. Adolescence is marked by significant neuroanatomical changes, distinguishing adolescent brains from those of adults and making age-specific imaging research crucial for understanding the neuropsychiatric conditions in youth. This study examines the test–retest reliability of anatomical brain MRI scans in adolescents diagnosed with depressive disorders, emphasizing a developmental perspective on neuropsychiatric disorders. Using a sample of 42 adolescents, we assessed the consistency of structural imaging metrics across 95 brain regions with deep learning-based neuroimaging analysis pipelines. The results demonstrated moderate to excellent reliability, with the intraclass correlation coefficients (ICC) ranging from 0.57 to 0.99 across regions. Notably, regions such as the pallidum, amygdala, entorhinal cortex, and white matter hypointensities showed moderate reliability, likely reflecting the challenges in the segmentation or inherent anatomical variability unique to this age group. This study highlights the necessity of integrating advanced imaging technologies to enhance the accuracy and reliability of the neuroimaging data specific to adolescents. Addressing the regional variability and strengthening the methodological rigor are essential for advancing the understanding of brain development and psychiatric disorders in this distinct developmental stage. Future research should focus on larger, more diverse samples, multi-site studies, and emerging imaging techniques to further validate the neuroimaging biomarkers. Such advancements could improve the clinical outcomes and deepen our understanding of the neuropsychiatric conditions unique to adolescence.https://www.mdpi.com/2078-2489/15/12/748test–retest reliabilityadolescentsdepressive disorderneuroimaging biomarkersbrain volume measurementstructural MRI
spellingShingle Anna-Maria Kasparbauer
Heidrun Lioba Wunram
Fabian Abuhsin
Friederike Körber
Eckhard Schönau
Stephan Bender
Ibrahim Duran
Test–Retest Reliability of Deep Learning Analysis of Brain Volumes in Adolescent Brain
Information
test–retest reliability
adolescents
depressive disorder
neuroimaging biomarkers
brain volume measurement
structural MRI
title Test–Retest Reliability of Deep Learning Analysis of Brain Volumes in Adolescent Brain
title_full Test–Retest Reliability of Deep Learning Analysis of Brain Volumes in Adolescent Brain
title_fullStr Test–Retest Reliability of Deep Learning Analysis of Brain Volumes in Adolescent Brain
title_full_unstemmed Test–Retest Reliability of Deep Learning Analysis of Brain Volumes in Adolescent Brain
title_short Test–Retest Reliability of Deep Learning Analysis of Brain Volumes in Adolescent Brain
title_sort test retest reliability of deep learning analysis of brain volumes in adolescent brain
topic test–retest reliability
adolescents
depressive disorder
neuroimaging biomarkers
brain volume measurement
structural MRI
url https://www.mdpi.com/2078-2489/15/12/748
work_keys_str_mv AT annamariakasparbauer testretestreliabilityofdeeplearninganalysisofbrainvolumesinadolescentbrain
AT heidrunliobawunram testretestreliabilityofdeeplearninganalysisofbrainvolumesinadolescentbrain
AT fabianabuhsin testretestreliabilityofdeeplearninganalysisofbrainvolumesinadolescentbrain
AT friederikekorber testretestreliabilityofdeeplearninganalysisofbrainvolumesinadolescentbrain
AT eckhardschonau testretestreliabilityofdeeplearninganalysisofbrainvolumesinadolescentbrain
AT stephanbender testretestreliabilityofdeeplearninganalysisofbrainvolumesinadolescentbrain
AT ibrahimduran testretestreliabilityofdeeplearninganalysisofbrainvolumesinadolescentbrain