Fig. 2 Architectures of generative AI models in medical imaging. (IMAGE)

Research

Fig. 2 Architectures of generative AI models in medical imaging.

Caption

Fig. 2 Architectures of generative AI models in medical imaging. (A) Generative adversarial network (GAN) comprising a generator and a discriminator. (B) Variational autoencoder (VAE) with an encoder–decoder structure and latent space mapping. (C) Diffusion probabilistic model (DPM) featuring forward diffusion and a denoising network (e.g., U-Net and DiT). (D) Sequence modeling architectures utilizing Transformer, Mamba, or autoregressive networks on image patches. (E) Foundation model pretraining architectures aligning vision and language encoders.

Credit

Copyright © 2025 Shanshan Wang et al.

Usage Restrictions

Credit must be given to the creator.

License

CC BY

Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.