Skip to main content

Vector-Quantized Latent Flows for Medical Image Synthesis And Out-of-Distribution Detection

Firas Khader

DOI
10.17023/zssz-ta38
  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00
    Length: 00:02:16
19 Apr 2023

We present an innovative method that allows for simultaneous out-of-distribution detection and image generation by encoding images in the latent space of a vector-quantized autoencoder and using normalizing flow models. The technique is demonstrated on a medical dataset of knee radiographs and can be used to relieve clinical radiologists of tedious tasks of quality control while simultaneously guiding radiologic technologists to improved and standardized image quality during image acquisition.

Tags:
ISBI
IEEE International Symposium on Biomedical Imaging
IEEE ISBI 2023

More Like This

Hybrid Spiking Neural Networks Fine-Tuning for Hippocampus Segmentation
21 Apr 2023

Hybrid Spiking Neural Networks Fine-Tuning for Hippocampus Segmentation

  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00
Uncertainty Assessment In Whole-Body Low Dose Pet Reconstruction Using Non-Parametric Bayesian Deep Learning Approach
21 Apr 2023

Uncertainty Assessment In Whole-Body Low Dose Pet Reconstruction Using Non-Parametric Bayesian Deep Learning Approach

  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00
Weakly Supervised Learning of Piecewise Rigid Transformation for Orthognathic Surgical Reconstruction of Dentofacial Deformity
21 Apr 2023

Weakly Supervised Learning of Piecewise Rigid Transformation for Orthognathic Surgical Reconstruction of Dentofacial Deformity

  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00