Progressive GANomaly: Anomaly detection with progressively growing GANs

TL;DR

This paper introduces Progressive GANomaly, a novel anomaly detection method combining GANomaly with progressively growing GANs, demonstrating improved stability and performance on various datasets, especially in detecting anomalies in medical images.

Contribution

It presents a new anomaly detection approach that integrates progressively growing GANs with GANomaly, enhancing stability and detection accuracy in medical imaging applications.

Findings

Progressive GANomaly outperforms GANomaly on Fashion MNIST.

It detects anomalies of varying size and intensity effectively.

Intermittent reconstructions are improved with the proposed method.

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 sizes 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.