Diagnostic neuroimaging across diseases

Stefan Klöppel, Ahmed Abdulkadir, Clifford R Jr. Jack, Nikolaos Koutsouleris, Janaina Mourão-Miranda, Prashanthi D Vemuri

Research output: Contribution to journalArticle

165 Citations (Scopus)

Abstract

Fully automated classification algorithms have been successfully applied to diagnose a wide range of neurological and psychiatric diseases. They are sufficiently robust to handle data from different scanners for many applications and in specific cases outperform radiologists. This article provides an overview of current applications taking structural imaging in Alzheimer's disease and schizophrenia as well as functional imaging to diagnose depression as examples. In this context, we also report studies aiming to predict the future course of the disease and the response to treatment for the individual. This has obvious clinical relevance but is also important for the design of treatment studies that may aim to include a cohort with a predicted fast disease progression to be more sensitive to detect treatment effects.In the second part, we present our own opinions on i) the role these classification methods can play in the clinical setting; ii) where their limitations are at the moment and iii) how those can be overcome. Specifically, we discuss strategies to deal with disease heterogeneity, diagnostic uncertainties, a probabilistic framework for classification and multi-class classification approaches.

Original languageEnglish (US)
Pages (from-to)457-463
Number of pages7
JournalNeuroImage
Volume61
Issue number2
DOIs
StatePublished - Jun 2012

Fingerprint

Neuroimaging
Uncertainty
Psychiatry
Disease Progression
Schizophrenia
Alzheimer Disease
Therapeutics
Depression

Keywords

  • Automated diagnosing
  • Dementia
  • Depression
  • MRI
  • Schizophrenia
  • SVM

ASJC Scopus subject areas

  • Cognitive Neuroscience
  • Neurology

Cite this

Klöppel, S., Abdulkadir, A., Jack, C. R. J., Koutsouleris, N., Mourão-Miranda, J., & Vemuri, P. D. (2012). Diagnostic neuroimaging across diseases. NeuroImage, 61(2), 457-463. https://doi.org/10.1016/j.neuroimage.2011.11.002

Diagnostic neuroimaging across diseases. / Klöppel, Stefan; Abdulkadir, Ahmed; Jack, Clifford R Jr.; Koutsouleris, Nikolaos; Mourão-Miranda, Janaina; Vemuri, Prashanthi D.

In: NeuroImage, Vol. 61, No. 2, 06.2012, p. 457-463.

Research output: Contribution to journalArticle

Klöppel, S, Abdulkadir, A, Jack, CRJ, Koutsouleris, N, Mourão-Miranda, J & Vemuri, PD 2012, 'Diagnostic neuroimaging across diseases', NeuroImage, vol. 61, no. 2, pp. 457-463. https://doi.org/10.1016/j.neuroimage.2011.11.002
Klöppel S, Abdulkadir A, Jack CRJ, Koutsouleris N, Mourão-Miranda J, Vemuri PD. Diagnostic neuroimaging across diseases. NeuroImage. 2012 Jun;61(2):457-463. https://doi.org/10.1016/j.neuroimage.2011.11.002
Klöppel, Stefan ; Abdulkadir, Ahmed ; Jack, Clifford R Jr. ; Koutsouleris, Nikolaos ; Mourão-Miranda, Janaina ; Vemuri, Prashanthi D. / Diagnostic neuroimaging across diseases. In: NeuroImage. 2012 ; Vol. 61, No. 2. pp. 457-463.
@article{3a84dd81fc634f5dada6cbc4fc11f843,
title = "Diagnostic neuroimaging across diseases",
abstract = "Fully automated classification algorithms have been successfully applied to diagnose a wide range of neurological and psychiatric diseases. They are sufficiently robust to handle data from different scanners for many applications and in specific cases outperform radiologists. This article provides an overview of current applications taking structural imaging in Alzheimer's disease and schizophrenia as well as functional imaging to diagnose depression as examples. In this context, we also report studies aiming to predict the future course of the disease and the response to treatment for the individual. This has obvious clinical relevance but is also important for the design of treatment studies that may aim to include a cohort with a predicted fast disease progression to be more sensitive to detect treatment effects.In the second part, we present our own opinions on i) the role these classification methods can play in the clinical setting; ii) where their limitations are at the moment and iii) how those can be overcome. Specifically, we discuss strategies to deal with disease heterogeneity, diagnostic uncertainties, a probabilistic framework for classification and multi-class classification approaches.",
keywords = "Automated diagnosing, Dementia, Depression, MRI, Schizophrenia, SVM",
author = "Stefan Kl{\"o}ppel and Ahmed Abdulkadir and Jack, {Clifford R Jr.} and Nikolaos Koutsouleris and Janaina Mour{\~a}o-Miranda and Vemuri, {Prashanthi D}",
year = "2012",
month = "6",
doi = "10.1016/j.neuroimage.2011.11.002",
language = "English (US)",
volume = "61",
pages = "457--463",
journal = "NeuroImage",
issn = "1053-8119",
publisher = "Academic Press Inc.",
number = "2",

}

TY - JOUR

T1 - Diagnostic neuroimaging across diseases

AU - Klöppel, Stefan

AU - Abdulkadir, Ahmed

AU - Jack, Clifford R Jr.

AU - Koutsouleris, Nikolaos

AU - Mourão-Miranda, Janaina

AU - Vemuri, Prashanthi D

PY - 2012/6

Y1 - 2012/6

N2 - Fully automated classification algorithms have been successfully applied to diagnose a wide range of neurological and psychiatric diseases. They are sufficiently robust to handle data from different scanners for many applications and in specific cases outperform radiologists. This article provides an overview of current applications taking structural imaging in Alzheimer's disease and schizophrenia as well as functional imaging to diagnose depression as examples. In this context, we also report studies aiming to predict the future course of the disease and the response to treatment for the individual. This has obvious clinical relevance but is also important for the design of treatment studies that may aim to include a cohort with a predicted fast disease progression to be more sensitive to detect treatment effects.In the second part, we present our own opinions on i) the role these classification methods can play in the clinical setting; ii) where their limitations are at the moment and iii) how those can be overcome. Specifically, we discuss strategies to deal with disease heterogeneity, diagnostic uncertainties, a probabilistic framework for classification and multi-class classification approaches.

AB - Fully automated classification algorithms have been successfully applied to diagnose a wide range of neurological and psychiatric diseases. They are sufficiently robust to handle data from different scanners for many applications and in specific cases outperform radiologists. This article provides an overview of current applications taking structural imaging in Alzheimer's disease and schizophrenia as well as functional imaging to diagnose depression as examples. In this context, we also report studies aiming to predict the future course of the disease and the response to treatment for the individual. This has obvious clinical relevance but is also important for the design of treatment studies that may aim to include a cohort with a predicted fast disease progression to be more sensitive to detect treatment effects.In the second part, we present our own opinions on i) the role these classification methods can play in the clinical setting; ii) where their limitations are at the moment and iii) how those can be overcome. Specifically, we discuss strategies to deal with disease heterogeneity, diagnostic uncertainties, a probabilistic framework for classification and multi-class classification approaches.

KW - Automated diagnosing

KW - Dementia

KW - Depression

KW - MRI

KW - Schizophrenia

KW - SVM

UR - http://www.scopus.com/inward/record.url?scp=84860734393&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84860734393&partnerID=8YFLogxK

U2 - 10.1016/j.neuroimage.2011.11.002

DO - 10.1016/j.neuroimage.2011.11.002

M3 - Article

VL - 61

SP - 457

EP - 463

JO - NeuroImage

JF - NeuroImage

SN - 1053-8119

IS - 2

ER -