Convolutional Neural Networks for the segmentation of hippocampal structures in postmortem MRI scans
Journal of Neuroscience Methods · 2025
DOI: 10.1016/j.jneumeth.2024.110359 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Neuroscience Methods, 2025. Verfasst von Anoop B N und 15 weiteren Autor:innen. Beteiligte Einrichtung: Neuroimage Analytics Laboratory and Biggs Institute Neuroimaging Core, Glenn Biggs Institute for Neurodegenerative Disorders, University of Texas Hea…. Hauptthemen laut MEDLINE: Convolutional Neural Networks, Deep Learning, Hippocampus, Image Processing, Computer-Assisted. Die Arbeit nennt 120 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIA NIH HHS.
Abstract (Originalsprache)
BACKGROUND: The hippocampus plays a crucial role in memory and is one of the first structures affected by Alzheimer's disease. Postmortem MRI offers a way to quantify the alterations by measuring the atrophy of the inner structures of the hippocampus. Unfortunately, the manual segmentation of hippocampal subregions required to carry out these measures is very time-consuming. NEW METHOD: In this study, we explore the use of fully automated methods relying on state-of-the-art Deep Learning approaches to produce these annotations. More specifically, we propose a new segmentation framework made of a set of encoder-decoder blocks embedding self-attention mechanisms and atrous spatial pyramidal pooling to produce better maps of the hippocampus and identify four hippocampal regions: the dentate gyrus, the hippocampal head, the hippocampal body, and the hippocampal tail. RESULTS: Trained using slices extracted from 15 postmortem T1-weighted, T2-weighted, and susceptibility-weighted MRI scans, our new approach produces hippocampus parcellations that are better aligned with the manually delineated parcellations provided by neuroradiologists. COMPARISON WITH EXISTING METHODS: Four standard deep learning segmentation architectures: UNet, Double UNet, Attention UNet, and Multi-resolution UNet have been utilized for the qualitative and quantitative comparison of the proposed hippocampal region segmentation model. CONCLUSIONS: Postmortem MRI serves as a highly valuable neuroimaging technique for examining the effects of neurodegenerative diseases on the intricate structures within the hippocampus. This study opens the way to large sample-size postmortem studies of the hippocampal substructures.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Neuroimage Analytics Laboratory and Biggs Institute Neuroimaging Core, Glenn Biggs Institute for Neurodegenerative Disorders, University of Texas Health Science Center at San Antonio, San Antonio, TX, USA; Department of…
- Neuroimage Analytics Laboratory and Biggs Institute Neuroimaging Core, Glenn Biggs Institute for Neurodegenerative Disorders, University of Texas Health Science Center at San Antonio, San Antonio, TX, USA.
- Icahn School of Medicine at Mount Sinai, New York, NY, USA.
- Department of Neurology, University of Pennsylvania, Philadelphia, PA, USA.
- Research Imaging Institute, University of Texas Health Science Center at San Antonio, San Antonio, TX, USA.
- Department of Clinical Sciences Lund, Lund University, Lund, Sweden.
Förderung
- NIA NIH HHS
Zitieren
APA
B N, A., Li, K., Honnorat, N., Rashid, T., Wang, D., Li, J., Fadaee, E., Charisis, S., Walker, J. M., Richardson, T. E., Wolk, D. A., Fox, P. T., Cavazos, J. E., Seshadri, S., Wisse, L. E. M., & Habes, M. (2025). Convolutional Neural Networks for the segmentation of hippocampal structures in postmortem MRI scans. Journal of Neuroscience Methods. https://doi.org/10.1016/j.jneumeth.2024.110359
Vancouver
B N A, Li K, Honnorat N, Rashid T, Wang D, Li J, et al. Convolutional Neural Networks for the segmentation of hippocampal structures in postmortem MRI scans. Journal of Neuroscience Methods. 2025. doi:10.1016/j.jneumeth.2024.110359
BibTeX
@article{BN2025,
author = {B N, Anoop and Li, Karl and Honnorat, Nicolas and Rashid, Tanweer and Wang, Di and Li, Jinqi and Fadaee, Elyas and Charisis, Sokratis and Walker, Jamie M and Richardson, Timothy E and Wolk, David A and Fox, Peter T and Cavazos, José E and Seshadri, Sudha and Wisse, Laura E M and Habes, Mohamad},
title = {Convolutional Neural Networks for the segmentation of hippocampal structures in postmortem MRI scans},
journal = {Journal of Neuroscience Methods},
year = {2025},
doi = {10.1016/j.jneumeth.2024.110359}
}
EUVIMED