Affordable Access

Access to the full text

Progressive GANomaly: anomaly detection with progressively growing GANs

Authors
  • Madzia-Madzou, Djennifer K.
  • Kuijf, Hugo J.
Type
Published Article
Publisher
SPIE
Volume
12032
Pages
120321–120321
Identifiers
DOI: 10.1117/12.2611105
Source
SPIE
License
Yellow

Abstract

In medical imaging, obtaining large amounts of labeled data is often a hurdle, because annotations and pathologies are scarce. Anomaly detection is a method that is capable of detecting unseen abnormal data while only being trained on normal (unannotated) data. Several algorithms based on generative adversarial networks (GANs) exist to perform this task, yet certain limitations are in place because of the instability of GANs. This paper proposes a new method by combining an existing method, GANomaly, with progressively growing GANs. The latter is known to be more stable, considering its ability to generate high resolution images. The method is tested using Fashion MNIST, Medical Out-of-Distribution Analysis Challenge (MOOD), and in-house brain MRI; using patches of size 16x16 and 32x32. Progressive GANomaly outperforms a one-class SVM or regular GANomaly on Fashion MNIST. Artificial anomalies are created in MOOD images with varying intensities and diameters. Progressive GANomaly detected the most anomalies with varying intensity and size. Additionally, the intermittent reconstructions are proven to be better from progressive GANomaly. On the in-house brain MRI dataset, regular GANomaly outperformed the other methods.

Report this publication

Statistics

Seen <100 times