% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@ARTICLE{Volkmann:273979,
author = {Volkmann, Heiko and Höglinger, Günter U and Grön, Georg
and Barlescu, Lavinia and Müller, Hans-Peter and Kassubek,
Jan},
collaboration = {group, DESCRIBE-PSP study},
title = {{MRI} classification of progressive supranuclear palsy,
{P}arkinson disease and controls using deep learning and
machine learning algorithms for the identification of
regions and tracts of interest as potential biomarkers.},
journal = {Computers in biology and medicine},
volume = {185},
issn = {0010-4825},
address = {Amsterdam [u.a.]},
publisher = {Elsevier Science},
reportid = {DZNE-2024-01428},
pages = {109518},
year = {2025},
abstract = {Quantitative magnetic resonance imaging (MRI) analysis has
shown promise in differentiating neurodegenerative
Parkinsonian syndromes and has significantly advanced our
understanding of diseases like progressive supranuclear
palsy (PSP) in recent years.The aim of this study was to
develop, implement and compare MRI analysis algorithms based
on artificial intelligence (AI) that can differentiate PSP
not only from healthy controls but also from Parkinson
disease (PD), by analyzing changes in brain structure and
microstructure. Specifically, this study focused on
identifying regions of interest (ROIs) and tracts of
interest (TOIs) that are crucial for the algorithms to
provide clinically relevant performance indices for the
distinction between disease variants.MR data comprised
diffusion tensor imaging (DTI - tractwise fractional
anisotropy statistics (TFAS)) and T1-weighted (T1-w) data
(texture analysis of the corpus callosum (CC)). One subject
sample with 74 PSP patients and 63 controls was recorded at
3.0T at multiple sites. The other sample came from a single
site, consisting of 66 PSP patients, 66 PD patients, and 44
controls, recorded at 1.5T. Four different machine learning
algorithms (ML) and a deep learning (DL) neural network
approach using Tensor Flow were implemented for the study.
The training of the algorithms was performed on 80 $\%$ of
the data, which included the entire single-site data and
parts of the multiple-site data. The validation process was
conducted on the remaining data, thereby consistently
separating training and validation data.A random forest
algorithm and a DL neural network classified PSP and healthy
controls with accuracies of 92 $\%$ and 95 $\%,$
respectively. Particularly, DTI derived measures for the
pons, midbrain tegmentum, superior cerebral peduncle,
putamen, and CC contributed to high accuracies. Furthermore,
DL neural network classification of PSP and PD with 86 $\%$
accuracy showed the importance of 19 structures. The four
most important features were DTI derived measures for
prefrontal white matter, the fasciculus frontooccipitalis,
the midbrain tegmentum, and the CC area II. This DL network
achieved a sensitivity of 88 $\%$ and specificity of 85
$\%,$ resulting in a Youden-index of 0.72.The primary goal
of the present study was to compare multiple ML-methods and
a DL approach to identify the least necessary set of brain
structures to classify PSP vs. controls and PSP vs. PD by
ranking them in a hierarchical order of importance. That
way, this study demonstrated the potential of AI approaches
to MRI as possible diagnostic and scientific tools to
differentiate variants of neurodegenerative Parkinsonism.},
keywords = {Deep learning (Other) / Diffusion tensor imaging (DTI)
(Other) / Machine learning (Other) / Magnetic resonance
imaging (MRI) (Other) / Neuropathology (Other) / Progressive
supranuclear palsy (Other) / tau protein (Other)},
cin = {Clinical Research (Munich)},
ddc = {570},
cid = {I:(DE-2719)1111015},
pnm = {353 - Clinical and Health Care Research (POF4-353)},
pid = {G:(DE-HGF)POF4-353},
experiment = {EXP:(DE-2719)DESCRIBE-PSP-20160101},
typ = {PUB:(DE-HGF)16},
pubmed = {pmid:39662313},
doi = {10.1016/j.compbiomed.2024.109518},
url = {https://pub.dzne.de/record/273979},
}