EUVIMEDEUVIMED entdecken
Open Access

ISOMAP and machine learning algorithms for the construction of embedded functional connectivity networks of anatomically separated brain regions from resting state fMRI data of patients with Schizophrenia

Ioannis K Gallos, Kostakis Gkiatis, George K Matsopoulos, Constantinos Siettos

AIMS Neuroscience · 2021 · 8 (2) · 295-321

DOI: 10.3934/neuroscience.2021016 ↗

Kurz gefasst

Fachartikel in der Zeitschrift AIMS Neuroscience, 2021. Verfasst von Ioannis K Gallos und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Applied Mathematical and Physical Sciences, National Technical University of Athens, Greece. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 82 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We construct Functional Connectivity Networks (FCN) from resting state fMRI (rsfMRI) recordings towards the classification of brain activity between healthy and schizophrenic subjects using a publicly available dataset (the COBRE dataset) of 145 subjects (74 healthy controls and 71 schizophrenic subjects). First, we match the anatomy of the brain of each individual to the Desikan-Killiany brain atlas. Then, we use the conventional approach of correlating the parcellated time series to construct FCN and ISOMAP, a nonlinear manifold learning algorithm to produce low-dimensional embeddings of the correlation matrices. For the classification analysis, we computed five key local graph-theoretic measures of the FCN and used the LASSO and Random Forest (RF) algorithms for feature selection. For the classification we used standard linear Support Vector Machines. The classification performance is tested by a double cross-validation scheme (consisting of an outer and an inner loop of "Leave one out" cross-validation (LOOCV)). The standard cross-correlation methodology produced a classification rate of 73.1%, while ISOMAP resulted in 79.3%, thus providing a simpler model with a smaller number of features as chosen from LASSO and RF, namely the participation coefficient of the right thalamus and the strength of the right lingual gyrus.

Schlagwörter

Stichwörter der Autor:innen

ISOMAPLASSOSchizophreniafeature selectionfunctional connectivity networksmachine learningmanifold learningnumerical analysisrandom forestsresting state fMRI

Autor:innen und Institutionen

  • School of Applied Mathematical and Physical Sciences, National Technical University of Athens, Greece.
  • School of Electrical and Computer Engineering, National Technical University of Athens, Greece.
  • Dipartimento di Matematica e Applicazioni "Renato Caccioppoli", Università degli Studi di Napoli Federico II, Italy.

Zitieren

APA

Gallos, I. K., Gkiatis, K., Matsopoulos, G. K., & Siettos, C. (2021). ISOMAP and machine learning algorithms for the construction of embedded functional connectivity networks of anatomically separated brain regions from resting state fMRI data of patients with Schizophrenia. AIMS Neuroscience, 8(2), 295-321. https://doi.org/10.3934/neuroscience.2021016

Vancouver

Gallos IK, Gkiatis K, Matsopoulos GK, Siettos C. ISOMAP and machine learning algorithms for the construction of embedded functional connectivity networks of anatomically separated brain regions from resting state fMRI data of patients with Schizophrenia. AIMS Neuroscience. 2021;8(2):295-321. doi:10.3934/neuroscience.2021016

BibTeX
@article{Gallos2021,
  author = {Gallos, Ioannis K and Gkiatis, Kostakis and Matsopoulos, George K and Siettos, Constantinos},
  title = {ISOMAP and machine learning algorithms for the construction of embedded functional connectivity networks of anatomically separated brain regions from resting state fMRI data of patients with Schizophrenia},
  journal = {AIMS Neuroscience},
  year = {2021},
  volume = {8},
  number = {2},
  pages = {295--321},
  doi = {10.3934/neuroscience.2021016}
}
Kostenlos starten →