EUVIMEDEUVIMED entdecken
ValidierungsstudieOpen Access · CC BY 4.0

Enhanced U-Net for Infant Brain MRI Segmentation: A (2+1)D Convolutional Approach

Lehel Dénes-Fazakas iD, Levente Kovács iD, György Eigner iD, László Szilágyi iD

Sensors · 2025

DOI: 10.3390/s25051531 ↗

Kurz gefasst

Validierungsstudie in der Zeitschrift Sensors, 2025. Verfasst von Lehel Dénes-Fazakas und 3 weiteren Autor:innen. Beteiligte Einrichtung: Physiological Controls Research Center, University Research and Innovation Center, Obuda University, 1034 Budapest, Hungary. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Convolutional Neural Networks, Image Processing, Computer-Assisted, Brain. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research, Development and Innovation Fund of Hungary, National Research, Development, and Innovation Fund of Hungary, Researcher Program of Óbuda University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Infant brain tissue segmentation from MRI data is a critical task in medical imaging, particularly challenging due to the evolving nature of tissue contrasts in the early months of life. The difficulty increases as gray matter (GM) and white matter (WM) intensities converge, making accurate segmentation challenging. This study aims to develop an improved U-net-based model to enhance the precision of automatic segmentation of cerebro-spinal fluid (CSF), GM, and WM in 10 infant brain MRIs using the iSeg-2017 dataset.

Methods

The proposed method utilizes a U-net architecture with (2+1)Dconvolutional layers and skip connections. Preprocessing includes intensity normalization using histogram alignment to standardize MRI data across different records. The model was trained on the iSeg-2017 dataset, which comprises T1-weighted and T2-weighted MRI data from ten infant subjects. Cross-validation was performed to evaluate the model’s segmentation performance.

Results

The model achieved an average accuracy of 92.2%, improving on previous methods by 0.7%. Sensitivity, precision, and Dice similarity scores were used to evaluate the performance, showing high levels of accuracy across different tissue types. The model demonstrated a slight bias toward misclassifying GM and WM, indicating areas for potential improvement.

Conclusions

The results suggest that the U-net architecture is highly effective in segmenting infant brain tissues from MRI data. Future work will explore enhancements such as attention mechanisms and dual-network processing for further improving segmentation accuracy.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Magnetic Resonance ImagingConvolutional Neural NetworksImage Processing, Computer-AssistedBrainImaging, Three-DimensionalHumansGray MatterWhite MatterCerebrospinal FluidDatasets as TopicSpatio-Temporal AnalysisDeep LearningInfant

Stichwörter der Autor:innen

(2+1)D convolutionMRI dataU-net architecturebrain tissue segmentationconvolutional neural networksdeep learningiSeg-2017 datasetinfant brainsmedical image processingneural networks

Autor:innen und Institutionen

  • Physiological Controls Research Center, University Research and Innovation Center, Obuda University, 1034 Budapest, Hungary.
  • Biomatics and Applied Artificial Intelligence Institute, John von Neumann Faculty of Informatics, Obuda University, 1034 Budapest, Hungary.
  • Doctoral School of Applied Informatics and Applied Mathematics, Obuda University, 1034 Budapest, Hungary.
  • Computational Intelligence Research Group, Sapientia Hungarian University of Transylvania, 547366 Targu Mures, Romania.

ORCID-Profile: Lehel Dénes-Fazakas, Levente Kovács, György Eigner, László Szilágyi

Förderung

  • National Research, Development and Innovation Fund of Hungary
  • National Research, Development, and Innovation Fund of Hungary
  • Researcher Program of Óbuda University

Zitieren

APA

Dénes-Fazakas, L., Kovács, L., Eigner, G., & Szilágyi, L. (2025). Enhanced U-Net for Infant Brain MRI Segmentation: A (2+1)D Convolutional Approach. Sensors. https://doi.org/10.3390/s25051531

Vancouver

Dénes-Fazakas L, Kovács L, Eigner G, Szilágyi L. Enhanced U-Net for Infant Brain MRI Segmentation: A (2+1)D Convolutional Approach. Sensors. 2025. doi:10.3390/s25051531

BibTeX
@article{DnesFazakas2025,
  author = {Dénes-Fazakas, Lehel and Kovács, Levente and Eigner, György and Szilágyi, László},
  title = {Enhanced U-Net for Infant Brain MRI Segmentation: A (2+1)D Convolutional Approach},
  journal = {Sensors},
  year = {2025},
  doi = {10.3390/s25051531}
}
Kostenlos starten →