variational autoencoder (vaes)  (Meso Scale Diagnostics LLC)

Journal: Scientific Reports

Article Title: A multimodal comparison of latent denoising diffusion probabilistic models and generative adversarial networks for medical image synthesis

doi: 10.1038/s41598-023-39278-0

Figure Lengend Snippet: Numerical evaluation of Medfusion’s autoencoder reconstruction quality.

Article Snippet: Therefore, we performed an additional experiment: Figure 1 Reconstruction quality of Medfusion Variational Autoencoder (VAE).

Techniques:

Journal: Scientific Reports

Article Title: A multimodal comparison of latent denoising diffusion probabilistic models and generative adversarial networks for medical image synthesis

doi: 10.1038/s41598-023-39278-0

Figure Lengend Snippet: Reconstruction quality of Medfusion Variational Autoencoder (VAE). Original images (first row) and reconstructed images (second row) by the VAE in the AIRGOS, CRCDX, and CheXpert dataset. In the eye fundus images, fine deviations from the original images were apparent in the veins of the optical disc (green arrow). Slight deviations in the color tone (green arrow) could be observed in the CRCDX dataset. In the CheXpert dataset, letters (green arrow) became blurry after reconstruction.

Article Snippet: Therefore, we performed an additional experiment: Figure 1 Reconstruction quality of Medfusion Variational Autoencoder (VAE).

Techniques:

Journal: Scientific Reports

Article Title: A multimodal comparison of latent denoising diffusion probabilistic models and generative adversarial networks for medical image synthesis

doi: 10.1038/s41598-023-39278-0

Figure Lengend Snippet: Illustration of the Medfusion model. ( A ) General overview of the architecture. \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$x$$\end{document} x and \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\widetilde{x}$$\end{document} x ~ are the input and output images. ( B ) Details of the autoencoder with a sampling of the latent space via the reparameterization trick at the end of the encoder and a direct connection (dashed lines) into the decoder (only active for training the autoencoder). ( C ) Detailed view of the denoising UNet with a linear layer for time and label embedding. ( D ) Detailed view of the submodules inside the autoencoder and UNet. If not specified otherwise, a convolution kernel size of 3 × 3, GroupNorm with 8 groups, and Swish activation was used.

Article Snippet: Therefore, we performed an additional experiment: Figure 1 Reconstruction quality of Medfusion Variational Autoencoder (VAE).

Techniques: Sampling, Activation Assay

Journal: Scientific Reports

Article Title: A multimodal comparison of latent denoising diffusion probabilistic models and generative adversarial networks for medical image synthesis

doi: 10.1038/s41598-023-39278-0

Figure Lengend Snippet: Numerical evaluation of Stable Diffusion’s autoencoder reconstruction quality.

Article Snippet: Therefore, we performed an additional experiment: Figure 1 Reconstruction quality of Medfusion Variational Autoencoder (VAE).

Techniques: Diffusion-based Assay