Analysis of MRI Data in Diagnostic Neuroradiology

Rathore, Saima; Abdulkadir, Ahmed; Davatzikos, Christos (2020). Analysis of MRI Data in Diagnostic Neuroradiology. Annual Review of Biomedical Data Science, 3(1), pp. 365-390. 10.1146/annurev-biodatasci-022620-015538

[img] Text
annurev-biodatasci-022620-015538.pdf - Published Version
Restricted to registered users only
Available under License Publisher holds Copyright.

Download (1MB) | Request a copy

Magnetic resonance imaging (MRI) is a noninvasive imaging tool for neuro-radiological diagnosis. Numerous concepts of automated MRI analysis andthe use of machine learning have been proposed to assist diagnosis and prog-nosis. While these academic innovations have proven effective in principlewithin controlled environments, their application to clinical practice hasfaced unmet requirements, such as the ability to perform reliably across aheterogeneous population, to work robustly in the presence of comorbidi-ties, and to be invariant to scanner hardware and image quality. The lack ofrealistic confidence bounds and the inability to handle missing data have alsoreduced the application of most of these methods outside of academic stud-ies. Mastering the complex challenges in the diagnostic process may helpresearchers discover novel biological constructs in multimodal data and im-prove stratification for clinical trials, paving the way for precision medicine.This review presents the state of the art of computerized brain MRI analysisfor diagnostic purposes. We critically evaluate the current clinical usefulnessof the methods and highlight challenges and future perspectives of the field.

Item Type:

Journal Article (Review Article)

Division/Institute:

04 Faculty of Medicine > University Psychiatric Services > University Hospital of Geriatric Psychiatry and Psychotherapy

UniBE Contributor:

Abdulkadir, Ahmed

Subjects:

600 Technology > 610 Medicine & health

ISSN:

2574-3414

Language:

English

Submitter:

Katharina Klink

Date Deposited:

12 May 2020 14:59

Last Modified:

26 Jul 2020 02:48

Publisher DOI:

10.1146/annurev-biodatasci-022620-015538

BORIS DOI:

10.7892/boris.143961

URI:

https://boris.unibe.ch/id/eprint/143961

Actions (login required)

Edit item Edit item
Provide Feedback