The role of noise in denoising models for anomaly detection in medical images

TL;DR

This paper investigates how optimizing noise parameters in denoising autoencoders and diffusion models enhances unsupervised anomaly detection in medical images, demonstrating improved performance on brain MRI and CT datasets.

Contribution

It reveals that tuning the spatial resolution and magnitude of training noise significantly improves anomaly detection, and compares the effectiveness of DAEs and diffusion models.

Findings

Optimized noise parameters improve detection accuracy.

DAEs with coarse noise achieve state-of-the-art results.

Diffusion models show promise but need further development.

Abstract

Pathological brain lesions exhibit diverse appearance in brain images, in terms of intensity, texture, shape, size, and location. Comprehensive sets of data and annotations are difficult to acquire. Therefore, unsupervised anomaly detection approaches have been proposed using only normal data for training, with the aim of detecting outlier anomalous voxels at test time. Denoising methods, for instance classical denoising autoencoders (DAEs) and more recently emerging diffusion models, are a promising approach, however naive application of pixelwise noise leads to poor anomaly detection performance. We show that optimization of the spatial resolution and magnitude of the noise improves the performance of different model training regimes, with similar noise parameter adjustments giving good performance for both DAEs and diffusion models. Visual inspection of the reconstructions suggests that the training noise influences the trade-off between the extent of the detail that is reconstructed and the extent of erasure of anomalies, both of which contribute to better anomaly detection performance. We validate our findings on two real-world datasets (tumor detection in brain MRI and hemorrhage/ischemia/tumor detection in brain CT), showing good detection on diverse anomaly appearances. Overall, we find that a DAE trained with coarse noise is a fast and simple method that gives state-of-the-art accuracy. Diffusion models applied to anomaly detection are as yet in their infancy and provide a promising avenue for further research.