Please use this identifier to cite or link to this item: http://dx.doi.org/10.14279/depositonce-9474
Main Title: Analyzing Neuroimaging Data Through Recurrent Deep Learning Models
Author(s): Thomas, Armin W.
Heekeren, Hauke R.
Müller, Klaus-Robert
Samek, Wojciech
Type: Article
Language Code: en
Abstract: The application of deep learning (DL) models to neuroimaging data poses several challenges, due to the high dimensionality, low sample size, and complex temporo-spatial dependency structure of these data. Even further, DL models often act as black boxes, impeding insight into the association of cognitive state and brain activity. To approach these challenges, we introduce the DeepLight framework, which utilizes long short-term memory (LSTM) based DL models to analyze whole-brain functional Magnetic Resonance Imaging (fMRI) data. To decode a cognitive state (e.g., seeing the image of a house), DeepLight separates an fMRI volume into a sequence of axial brain slices, which is then sequentially processed by an LSTM. To maintain interpretability, DeepLight adapts the layer-wise relevance propagation (LRP) technique. Thereby, decomposing its decoding decision into the contributions of the single input voxels to this decision. Importantly, the decomposition is performed on the level of single fMRI volumes, enabling DeepLight to study the associations between cognitive state and brain activity on several levels of data granularity, from the level of the group down to the level of single time points. To demonstrate the versatility of DeepLight, we apply it to a large fMRI dataset of the Human Connectome Project. We show that DeepLight outperforms conventional approaches of uni- and multivariate fMRI analysis in decoding the cognitive states and in identifying the physiologically appropriate brain regions associated with these states. We further demonstrate DeepLight's ability to study the fine-grained temporo-spatial variability of brain activity over sequences of single fMRI samples.
URI: https://depositonce.tu-berlin.de/handle/11303/10545
http://dx.doi.org/10.14279/depositonce-9474
Issue Date: 10-Dec-2019
Date Available: 20-Dec-2019
DDC Class: 610 Medizin und Gesundheit
Subject(s): decoding
neuroimaging
fMRI
whole-brain
deep learning
recurrent
interpretability
Sponsor/Funder: BMBF, 01IS14013A, BBDC - Berliner Kompetenzzentrum für Big Data
BMBF, 01IS18056A, TraMeExCo - Transparenter Begleiter für medizinische Anwendung
DFG, EXC 2046, MATH+: Berlin Mathematics Research Center
License: https://creativecommons.org/licenses/by/4.0/
Journal Title: Frontiers in Neuroscience
Publisher: Frontiers Media S.A.
Publisher Place: Lausanne
Volume: 13
Article Number: 1321
Publisher DOI: 10.3389/fnins.2019.01321
EISSN: 1662-453X
Appears in Collections:FG Maschinelles Lernen » Publications



This item is licensed under a Creative Commons License Creative Commons