English

CVAD: A generic medical anomaly detector based on Cascade VAE

Image and Video Processing 2022-01-28 v2 Computer Vision and Pattern Recognition

Abstract

Detecting out-of-distribution (OOD) samples in medical imaging plays an important role for downstream medical diagnosis. However, existing OOD detectors are demonstrated on natural images composed of inter-classes and have difficulty generalizing to medical images. The key issue is the granularity of OOD data in the medical domain, where intra-class OOD samples are predominant. We focus on the generalizability of OOD detection for medical images and propose a self-supervised Cascade Variational autoencoder-based Anomaly Detector (CVAD). We use a variational autoencoders' cascade architecture, which combines latent representation at multiple scales, before being fed to a discriminator to distinguish the OOD data from the in-distribution (ID) data. Finally, both the reconstruction error and the OOD probability predicted by the binary discriminator are used to determine the anomalies. We compare the performance with the state-of-the-art deep learning models to demonstrate our model's efficacy on various open-access medical imaging datasets for both intra- and inter-class OOD. Further extensive results on datasets including common natural datasets show our model's effectiveness and generalizability. The code is available at https://github.com/XiaoyuanGuo/CVAD.

Keywords

Cite

@article{arxiv.2110.15811,
  title  = {CVAD: A generic medical anomaly detector based on Cascade VAE},
  author = {Xiaoyuan Guo and Judy Wawira Gichoya and Saptarshi Purkayastha and Imon Banerjee},
  journal= {arXiv preprint arXiv:2110.15811},
  year   = {2022}
}

Comments

6 pages, 4 figures, 4 tables

R2 v1 2026-06-24T07:17:52.409Z