Related Experiment Video
Updated: Dec 6, 2025
10:44
Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging
Published on: June 21, 2024
934
Generation of High-resolution Lung Computed Tomography Images using Generative Adversarial Networks
Summary
This study introduces a generative adversarial network (GAN) method to create high-resolution medical images, addressing limited training data for deep learning models. The approach enhances medical imaging datasets for improved AI applications.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Computer Vision
Background:
- Limited high-resolution medical image data hinders deep learning model training.
- Generative Adversarial Networks (GANs) show promise in image generation tasks.
Purpose of the Study:
- To develop a novel method for generating high-resolution medical images.
- To augment datasets for deep learning applications in medical imaging.
Main Methods:
- Utilized Boundary Equilibrium Generative Adversarial Networks (BEGAN) for whole lung CT image generation.
- Integrated image inpainting with a coarse-refinement network for intricate lung detail generation.
Main Results:
- Successfully generated high-resolution lung CT images.
- Demonstrated the capability to produce intricate details through image inpainting.
Conclusions:
- The proposed GAN-based method effectively increases the quantity of high-resolution medical images.
- This technique has the potential to significantly benefit future deep learning applications in medical diagnostics.
