EUVIMEDEUVIMED entdecken
Open Access

The Use of fMRI Regional Analysis to Automatically Detect ADHD Through a 3D CNN-Based Approach

Perihan Gülşah Gülhan, Güzin Özmen

Journal of Imaging Informatics in Medicine · 19.07.2024 · 38 (1) · 203-216

DOI: 10.1007/s10278-024-01189-5 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Imaging Informatics in Medicine, online erschienen am 19.07.2024. Verfasst von Perihan Gülşah Gülhan und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical and Electronics Engineering, Institute of Science, Selcuk University, Konya, Turkey. Hauptthemen laut MEDLINE: Attention Deficit Disorder with Hyperactivity, Magnetic Resonance Imaging, Neural Networks, Computer, Imaging, Three-Dimensional. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Attention deficit hyperactivity disorder (ADHD) is a neurodevelopmental disorder characterized by a reduced attention span, hyperactivity, and impulsive behaviors, which typically manifest during childhood. This study employs functional magnetic resonance imaging (fMRI) to use spontaneous brain activity for classifying individuals with ADHD, focusing on a 3D convolutional neural network (CNN) architecture to facilitate the design of decision support systems. We developed a novel deep learning model based on 3D CNNs using the ADHD-200 database, which comprises datasets from NeuroImage (NI), New York University (NYU), and Peking University (PU). We used fractional amplitude of low-frequency fluctuations (fALFF) and regional homogeneity (ReHo) data in three dimensions and performed a fivefold cross-validation to address the dataset imbalance. We aimed to verify the efficacy of our proposed 3D CNN by contrasting it with a fully connected neural network (FCNN) architecture. The 3D CNN achieved accuracy rates of 76.19% (NI), 69.92% (NYU), and 70.77% (PU) for fALFF data. The FCNN model yielded lower accuracy rates across all datasets. For generalizability, we trained on NI and NYU datasets and tested on PU. The 3D CNN achieved 69.48% accuracy on fALFF outperforming the FCNN. Our results demonstrate that using 3D CNNs for classifying fALFF data is an effective approach for diagnosing ADHD. Also, FCNN confirmed the efficiency of the designed model.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Attention Deficit Disorder with HyperactivityMagnetic Resonance ImagingNeural Networks, ComputerImaging, Three-DimensionalHumansMaleFemaleChildDeep LearningBrainAdolescentDatabases, Factual

Stichwörter der Autor:innen

3D CNNAttention deficit hyperactive disorderFunctional MRIRegional Analysis

Autor:innen und Institutionen

  • Department of Electrical and Electronics Engineering, Institute of Science, Selcuk University, Konya, Turkey.
  • Department of Biomedical Engineering, Faculty of Technology, Selcuk University, Konya, Turkey. gozmen@selcuk.edu.tr.

Zitieren

APA

Gülhan, P. G., & Özmen, G. (2024). The Use of fMRI Regional Analysis to Automatically Detect ADHD Through a 3D CNN-Based Approach. Journal of Imaging Informatics in Medicine, 38(1), 203-216. https://doi.org/10.1007/s10278-024-01189-5

Vancouver

Gülhan PG, Özmen G. The Use of fMRI Regional Analysis to Automatically Detect ADHD Through a 3D CNN-Based Approach. Journal of Imaging Informatics in Medicine. 2024;38(1):203-216. doi:10.1007/s10278-024-01189-5

BibTeX
@article{Glhan2024,
  author = {Gülhan, Perihan Gülşah and Özmen, Güzin},
  title = {The Use of fMRI Regional Analysis to Automatically Detect ADHD Through a 3D CNN-Based Approach},
  journal = {Journal of Imaging Informatics in Medicine},
  year = {2024},
  volume = {38},
  number = {1},
  pages = {203--216},
  doi = {10.1007/s10278-024-01189-5}
}
Kostenlos starten →