Uneingeschränkter Zugang

Enhancing MRI diagnosis of myocarditis using deep learning and generative adversarial networks

Haifeng Gui

Haifeng Gui

Department of Nursing Cang Medical CollegeCangzhou, China
Suche nach diesem Autor auf
Sciendo|Google Scholar
Gui, Haifeng
 und 
Na Zhang

Na Zhang

Health Management Department Cang Medical CollegeCangzhou, China
Suche nach diesem Autor auf
Sciendo|Google Scholar
Zhang, Na
  
17. März 2025
Enhancing MRI diagnosis of myocarditis using deep learning and generative adversarial networks's Cover Image
Über diesen Artikel
Vorheriger Artikel
Nächster Artikel
Zitieren
COVER HERUNTERLADEN
Online veröffentlicht: 17. März 2025
Eingereicht: 06. Okt. 2024
Akzeptiert: 03. Feb. 2025
DOI: https://doi.org/10.2478/amns-2025-0206
Schlüsselwörter
© 2025 Haifeng Gui et al., published by Sciendo
This work is licensed under the Creative Commons Attribution 4.0 International License.

Figure 1.

The change of atomic nuclei under a strong magnetic field
The change of atomic nuclei under a strong magnetic field

Figure 2.

The phase change of the nucleus under RF pulse
The phase change of the nucleus under RF pulse

Figure 3.

Network structure of basic GAN model
Network structure of basic GAN model

Figure 4.

Generate a training process for adversarial networks (GAN)
Generate a training process for adversarial networks (GAN)

Figure 5.

Improved GAN network structure
Improved GAN network structure

Figure 6.

Analysis results of generator and discriminator loss function
Analysis results of generator and discriminator loss function

Figure 7.

Test and training loss rate analysis results
Test and training loss rate analysis results

Figure 8.

Quantitative evaluation of results by different methods on dataset A
Quantitative evaluation of results by different methods on dataset A

Figure 9.

Quantitative evaluation of results by different methods on dataset B
Quantitative evaluation of results by different methods on dataset B

Gray scale of normal human tissue on T1 weighted and T2 weighted

Name 1 2 3 4 5 6 7
T1 weighted White grey Black Gray White Black White Black
T2 weighted Gray Black White grey Gray White White grey Black

Comparison of MRI and CT performance

Imaging characteristics CT MRI
Imaging signal X-ray Radio-frequency energy
Imaging magnetic field No The superposition of static magnetic field and gradient magnetic field
Adopted electromagnetic wave A narrow beam of X-rays Radio-frequency wave
Fault direction Generally perpendicular to the body Arbitrary direction
Data acquisition mode Multidirectional projection Multidirectional or unidirectional projection
Imaging time for each layer Ultra-high speed CT can reach about 10ms It varies by scan sequence
Image reconstruction mode Back projection method, convolutional back projection method, iterative method, etc Two dimensional Fourier transform imaging is the main method
Ionizing radiation There’s X-ray radiation Very safe with very little RF radiation
Real-time imaging Realize Realize
Sprache:
Englisch
Zeitrahmen der Veröffentlichung:
1 Hefte pro Jahr
Fachgebiete der Zeitschrift:
Biologie, Biologie, andere, Mathematik, Angewandte Mathematik, Mathematik, Allgemeines, Physik, Physik, andere
Zeitschrift RSS Feed