PMID- 33829386
OWN - NLM
STAT- MEDLINE
DCOM- 20221010
LR  - 20230104
IS  - 1559-0089 (Electronic)
IS  - 1539-2791 (Linking)
VI  - 20
IP  - 1
DP  - 2022 Jan
TI  - Volume Reduction Techniques for the Classification of Independent Components of 
      rs-fMRI Data: a Study with Convolutional Neural Networks.
PG  - 73-90
LID - 10.1007/s12021-021-09524-9 [doi]
AB  - In the last decade, neurosciences have had an increasing interest in resting 
      state functional magnetic resonance imaging (rs-fMRI) as a result of its 
      advantages, such as high spatial resolution, compared to other brain exploration 
      techniques. To improve the technique, the elimination of artifacts through 
      Independent Components Analysis (ICA) has been proposed, as this can separate 
      neural signal and noise, opening possibilities for automatic classification. The 
      main classification techniques have focused on processes based on typical machine 
      learning. However, there are currently more robust approaches such as 
      convolutional neural networks, which can deal with complex problems directly from 
      the data without feature selection and even with data that does not have a simple 
      interpretation, being limited by the amount of data necessary for training and 
      its high computational cost. This research focused on studying four methods of 
      volume reduction mitigating the computational cost for the training of 3 models 
      based on convolutional neural networks. One of the reduction techniques is a 
      novel approach that we call Reduction by Consecutive Binary Patterns (RCBP), 
      which was shown to preserve the spatial features of the independent components. 
      In addition, the RCBP showed networks in components associated with neuronal 
      activity more clearly. The networks achieved accuracy above 98 % in 
      classification, and one network was even found to be over 99 % accurate, 
      outperforming most machine learning-based classification algorithms.
CI  - (c) 2021. The Author(s), under exclusive licence to Springer Science+Business 
      Media, LLC, part of Springer Nature.
FAU - Mera Jimenez, Leonel
AU  - Mera Jimenez L
AD  - Bioinstrumentation and Clinical Engineering Research Group, Bioengineering 
      Program, Universidad de Antioquia, Calle 70 No. 52-21, Medellin, Colombia. 
      leonel.mera@udea.edu.co.
AD  - Facultad de Ingenieria, Cl. 67 #53-108, Medellin, Colombia. 
      leonel.mera@udea.edu.co.
FAU - Ochoa Gomez, John F
AU  - Ochoa Gomez JF
AD  - Bioinstrumentation and Clinical Engineering Research Group, Bioengineering 
      Program, Universidad de Antioquia, Calle 70 No. 52-21, Medellin, Colombia.
AD  - Neuropsychology and Behavior Group, Medicine Program, Universidad de Antioquia, 
      Calle 70 No. 52-21, Medellin, Colombia.
LA  - eng
PT  - Journal Article
PT  - Research Support, Non-U.S. Gov't
PT  - Review
DEP - 20210407
PL  - United States
TA  - Neuroinformatics
JT  - Neuroinformatics
JID - 101142069
SB  - IM
MH  - Artifacts
MH  - Brain/physiology
MH  - Brain Mapping/methods
MH  - *Magnetic Resonance Imaging/methods
MH  - *Neural Networks, Computer
OTO - NOTNLM
OT  - Convolutional neural network
OT  - Deep learning
OT  - Denoising
OT  - Independent component analysis
OT  - rs-fMRI
EDAT- 2021/04/09 06:00
MHDA- 2022/10/12 06:00
CRDT- 2021/04/08 06:41
PHST- 2021/03/31 00:00 [accepted]
PHST- 2021/04/09 06:00 [pubmed]
PHST- 2022/10/12 06:00 [medline]
PHST- 2021/04/08 06:41 [entrez]
AID - 10.1007/s12021-021-09524-9 [pii]
AID - 10.1007/s12021-021-09524-9 [doi]
PST - ppublish
SO  - Neuroinformatics. 2022 Jan;20(1):73-90. doi: 10.1007/s12021-021-09524-9. Epub 
      2021 Apr 7.