Vector-Quantized Latent Flows for Medical Image Synthesis and Out-Of-Distribution Detection

IEEE International Symposium on Biomedical Imaging (ISBI), vol. 32, pp. 1–5

Abstract

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.

Authors 8

1. Firas Khader Aachen Department of Diagnostic and Interventional Radiology

   Universitätsklinikum Aachen

   Affiliation as printed

   University Hospital Aachen,Department of Diagnostic and Interventional Radiology,Aachen,Germany

   Department of Diagnostic and Interventional Radiology, University Hospital Aachen, Aachen, Germany

2. Gustav Anton Müller‐Franzes Aachen Department of Diagnostic and Interventional Radiology

   Universitätsklinikum Aachen

   Affiliation as printed

   University Hospital Aachen,Department of Diagnostic and Interventional Radiology,Aachen,Germany

   Department of Diagnostic and Interventional Radiology, University Hospital Aachen, Aachen, Germany

3. Soroosh Tayebi Arasteh Aachen Department of Diagnostic and Interventional Radiology

   Universitätsklinikum Aachen

   Affiliation as printed

   University Hospital Aachen,Department of Diagnostic and Interventional Radiology,Aachen,Germany

   Department of Diagnostic and Interventional Radiology, University Hospital Aachen, Aachen, Germany

4. Tianyu Han Aachen Physics of Molecular Imaging Systems

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University,Physics of Molecular Imaging Systems, Experimental Molecular Imaging,Aachen,Germany

   Physics of Molecular Imaging Systems, Experimental Molecular Imaging, RWTH Aachen University, Aachen, Germany

5. Jakob Nikolas Kather

   University of Leeds · German Cancer Research Center · University Hospital Heidelberg · National Center for Tumor Diseases · Deutsches Konsortium für Translationale Krebsforschung · Else Kröner Fresenius Center for Digital Health · Technische Universität Dresden

   Affiliation as printed

   University of Leeds,Pathology & Data Analytics, Leeds Institute of Medical Research at St James’s,Leeds,United Kingdom

   Else Kroener Fresenius Center for Digital Health, Medical Faculty Carl Gustav Carus, Technical University Dresden, Dresden, Germany

   German Cancer Consortium (DKTK), German Cancer Research Center (DKFZ), Heidelberg, Germany

   Medical Oncology, National Center for Tumor Diseases (NCT), University Hospital Heidelberg, Heidelberg, Germany

6. Johannes Stegmaier Aachen Institute of Imaging & Computer Vision

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University,Institute of Imaging and Computer Vision,Aachen,Germany

   Institute of Imaging and Computer Vision, RWTH Aachen University, Aachen, Germany

7. Sven Nebelung Aachen Department of Diagnostic and Interventional Radiology

   Universitätsklinikum Aachen

   Affiliation as printed

   University Hospital Aachen,Department of Diagnostic and Interventional Radiology,Aachen,Germany

   Department of Diagnostic and Interventional Radiology, University Hospital Aachen, Aachen, Germany

8. Daniel Truhn Aachen Department of Diagnostic and Interventional Radiology

   Universitätsklinikum Aachen

   Affiliation as printed

   University Hospital Aachen,Department of Diagnostic and Interventional Radiology,Aachen,Germany

   Department of Diagnostic and Interventional Radiology, University Hospital Aachen, Aachen, Germany