EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Brain MR image simulation for deep learning based medical image analysis networks

Aymen Ayaz, Yasmina Al Khalil, Sina Amirrajab, Cristian Lorenz, Jürgen Weese, Josien Pluim, Marcel Breeuwer

Computer Methods and Programs in Biomedicine · 2024

DOI: 10.1016/j.cmpb.2024.108115 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computer Methods and Programs in Biomedicine, 2024. Verfasst von Aymen Ayaz und 6 weiteren Autor:innen. Beteiligte Einrichtung: Biomedical Engineering Department, Eindhoven University of Technology, Eindhoven, the Netherlands. Electronic address: a.ayaz@tue.nl. Hauptthemen laut MEDLINE: Deep Learning. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Commission, EU Framework Programme for Research and Innovation Marie Sklodowska-Curie Actions.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND AND OBJECTIVE: As large sets of annotated MRI data are needed for training and validating deep learning based medical image analysis algorithms, the lack of sufficient annotated data is a critical problem. A possible solution is the generation of artificial data by means of physics-based simulations. Existing brain simulation data is limited in terms of anatomical models, tissue classes, fixed tissue characteristics, MR sequences and overall realism. METHODS: We propose a realistic simulation framework by incorporating patient-specific phantoms and Bloch equations-based analytical solutions for fast and accurate MRI simulations. A large number of labels are derived from open-source high-resolution T1w MRI data using a fully automated brain classification tool. The brain labels are taken as ground truth (GT) on which MR images are simulated using our framework. Moreover, we demonstrate that the T1w MR images generated from our framework along with GT annotations can be utilized directly to train a 3D brain segmentation network. To evaluate our model further on larger set of real multi-source MRI data without GT, we compared our model to existing brain segmentation tools, FSL-FAST and SynthSeg. RESULTS: Our framework generates 3D brain MRI for variable anatomy, sequence, contrast, SNR and resolution. The brain segmentation network for WM/GM/CSF trained only on T1w simulated data shows promising results on real MRI data from MRBrainS18 challenge dataset with a Dice scores of 0.818/0.832/0.828. On OASIS data, our model exhibits a close performance to FSL, both qualitatively and quantitatively with a Dice scores of 0.901/0.939/0.937. CONCLUSIONS: Our proposed simulation framework is the initial step towards achieving truly physics-based MRI image generation, providing flexibility to generate large sets of variable MRI data for desired anatomy, sequence, contrast, SNR, and resolution. Furthermore, the generated images can effectively train 3D brain segmentation networks, mitigating the reliance on real 3D annotated data.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningHumansBrainMagnetic Resonance ImagingAlgorithmsNeuroimagingImage Processing, Computer-Assisted

Stichwörter der Autor:innen

Brain MRI segmentationBrain MRI simulationLarge synthetic populationWM/GM/CSF segmentation

Autor:innen und Institutionen

  • Biomedical Engineering Department, Eindhoven University of Technology, Eindhoven, the Netherlands. Electronic address: a.ayaz@tue.nl.
  • Biomedical Engineering Department, Eindhoven University of Technology, Eindhoven, the Netherlands. Electronic address: y.al.khalil@tue.nl.
  • Biomedical Engineering Department, Eindhoven University of Technology, Eindhoven, the Netherlands. Electronic address: s.amirrajab@tue.nl.
  • Philips Research Laboratories, Hamburg, Germany. Electronic address: cristian.lorenz@philips.com.
  • Philips Research Laboratories, Hamburg, Germany. Electronic address: juergen.weese@philips.com.
  • Biomedical Engineering Department, Eindhoven University of Technology, Eindhoven, the Netherlands. Electronic address: j.pluim@tue.nl.

Förderung

  • European Commission
  • EU Framework Programme for Research and Innovation Marie Sklodowska-Curie Actions

Zitieren

APA

Ayaz, A., Al Khalil, Y., Amirrajab, S., Lorenz, C., Weese, J., Pluim, J., & Breeuwer, M. (2024). Brain MR image simulation for deep learning based medical image analysis networks. Computer Methods and Programs in Biomedicine. https://doi.org/10.1016/j.cmpb.2024.108115

Vancouver

Ayaz A, Al Khalil Y, Amirrajab S, Lorenz C, Weese J, Pluim J, et al. Brain MR image simulation for deep learning based medical image analysis networks. Computer Methods and Programs in Biomedicine. 2024. doi:10.1016/j.cmpb.2024.108115

BibTeX
@article{Ayaz2024,
  author = {Ayaz, Aymen and Al Khalil, Yasmina and Amirrajab, Sina and Lorenz, Cristian and Weese, Jürgen and Pluim, Josien and Breeuwer, Marcel},
  title = {Brain MR image simulation for deep learning based medical image analysis networks},
  journal = {Computer Methods and Programs in Biomedicine},
  year = {2024},
  doi = {10.1016/j.cmpb.2024.108115}
}
Kostenlos starten →