Diagnostic neuroimaging across diseases

• Published in: NeuroImage (Orlando, Fla.) Vol. 61; no. 2; pp. 457 - 463
• Main Authors: Klöppel, Stefan, Abdulkadir, Ahmed, Jack, Clifford R., Koutsouleris, Nikolaos, Mourão-Miranda, Janaina, Vemuri, Prashanthi
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01.06.2012; Elsevier Limited
• Subjects: Accuracy; Algorithms; Alzheimer Disease - pathology; Automated diagnosing; Classification; Dementia; Dementia - diagnosis; Dementia - pathology; Depression; Depressive Disorder - diagnosis; Depressive Disorder - pathology; Disease; Humans; Image Processing, Computer-Assisted; Medical imaging; Mental Disorders - diagnosis; Mental Disorders - pathology; Methods; MRI; Nervous System Diseases - diagnosis; Nervous System Diseases - pathology; Neuroimaging - classification; Neuroimaging - methods; Neurosciences; NMR; Nuclear magnetic resonance; Patients; Pipelines; Schizophrenia; Schizophrenia - diagnosis; Schizophrenia - pathology; Support Vector Machine; SVM; Schizophrenia; Depression; SVM; Automated diagnosing; MRI; Dementia
• ISSN: 1053-8119; 1095-9572; 1095-9572
• DOI: 10.1016/j.neuroimage.2011.11.002

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. ► Overview of clinical applications of classification methods. ► Description of current limitations. ► Outlook and future directions.