Semi-Nonlinear Deep Efficient Reconstruction for Unveiling Linear and Nonlinear Spatial Features of the Human Brain
Open Access
- 30 January 2025
- journal article
- research article
- Published by MDPI AG in Electronics
- Vol. 14 (3) , 554
Abstract
Deep learning has become indispensable for identifying hierarchical spatial features (SFs), which are crucial for linking neurological disorders to brain functionality, from functional Magnetic Resonance Imaging (fMRI). Unfortunately, existing methods are constrained by architectures that are either linear or nonlinear, limiting a comprehensive categorization of spatial features. To overcome this limitation, we introduce the Semi-Nonlinear Deep Efficient Reconstruction (SENDER) framework, a novel hybrid approach designed to simultaneously capture both linear and nonlinear spatial features, providing a holistic understanding of brain functionality. In our approach, linear SFs are formed by directly integrating multiple spatial features at shallow layers, whereas nonlinear SFs emerge from combining partial regions of these features, yielding complex patterns at deeper layers. We validated SENDER through extensive qualitative and quantitative evaluations with four state-of-the-art methods. Results demonstrate its superior performance, identifying five reproducible linear SFs and eight reproducible nonlinear SFs.Keywords
Funding Information
- AU-GSU Seed Award Program for Collaborative Clinical and Translational Research (AUGSU00016)
This publication has 64 references indexed in Scilit:
- A smoothing proximal gradient algorithm with extrapolation for the relaxation of ${\ell_{0}}$ regularization problemComputational Optimization and Applications, 2023
- Nonlinear functional network connectivity in resting functional magnetic resonance imaging dataHuman Brain Mapping, 2022
- Resting fMRI-guided TMS results in subcortical and brain network modulation indexed by interleaved TMS/fMRIExperimental Brain Research, 2021
- Detecting Task Functional MRI Activation Using the Multiband Multiecho (MBME) Echo‐Planar Imaging (EPI) SequenceJournal of Magnetic Resonance Imaging, 2020
- Somatosensory-Motor Dysconnectivity Spans Multiple Transdiagnostic Dimensions of PsychopathologyBiological Psychiatry, 2019
- Spatial dynamics within and between brain functional domains: A hierarchical approach to study time‐varying brain functionHuman Brain Mapping, 2018
- A Connectome-wide Functional Signature of Transdiagnostic Risk for Mental IllnessBiological Psychiatry, 2018
- Latent source mining in FMRI via restricted Boltzmann machineHuman Brain Mapping, 2018
- Motion artifact in studies of functional connectivity: Characteristics and mitigation strategiesHuman Brain Mapping, 2017
- Solving a low-rank factorization model for matrix completion by a nonlinear successive over-relaxation algorithmMathematical Programming Computation, 2012