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

arXiv: https://arxiv.org/abs/2301.08330 · HTML: https://mlsanity.com/paper/2301.08330/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models.
- Builds on 25 of its 52 references that are in the map.
- First posted on arXiv 19 Jan 2023.

## Placed in

- Diffusion models / [Medical imaging and segmentation](https://mlsanity.com/diffusion/medical-imaging-and-segmentation/)

## Builds on (most cited first, 25 of 25)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Group Normalization](https://mlsanity.com/paper/1803.08494/) (2018)
- [RePaint: Inpainting using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2201.09865/) (2022)
- [On the Convergence of Adam and Beyond](https://mlsanity.com/paper/1904.09237/) (2019)
- [Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge](https://mlsanity.com/paper/1811.02629/) (2018)
- [Autoencoders for Unsupervised Anomaly Segmentation in Brain MR Images: A Comparative Study](https://mlsanity.com/paper/2004.03271/) (2020)
- [Deep Autoencoding Models for Unsupervised Anomaly Segmentation in Brain MR Images](https://mlsanity.com/paper/1804.04488/) (2018)
- [Soft Diffusion: Score Matching for General Corruptions](https://mlsanity.com/paper/2209.05442/) (2022)
- [Fast Unsupervised Brain Anomaly Detection and Segmentation with Diffusion Models](https://mlsanity.com/paper/2206.03461/) (2022)
- [Unsupervised Detection of Lesions in Brain MRI using constrained adversarial auto-encoders](https://mlsanity.com/paper/1806.04972/) (2018)
- [Unsupervised Anomaly Localization using Variational Auto-Encoders](https://mlsanity.com/paper/1907.02796/) (2019)
- [Unsupervised Lesion Detection via Image Restoration with a Normative Prior](https://mlsanity.com/paper/2005.00031/) (2020)
- [Context-encoding Variational Autoencoder for Unsupervised Anomaly Detection](https://mlsanity.com/paper/1812.05941/) (2018)
- [What is Healthy? Generative Counterfactual Diffusion for Lesion Localization](https://mlsanity.com/paper/2207.12268/) (2022)
- [Detecting Outliers with Foreign Patch Interpolation](https://mlsanity.com/paper/2011.04197/) (2020)
- [Improved anomaly detection by training an autoencoder with skip connections on images corrupted with Stain-shaped noise](https://mlsanity.com/paper/2008.12977/) (2020)
- [Challenging Current Semi-Supervised Anomaly Segmentation Methods for Brain MRI](https://mlsanity.com/paper/2109.06023/) (2021)
- [Scale-Space Autoencoders for Unsupervised Anomaly Segmentation in Brain MRI](https://mlsanity.com/paper/2006.12852/) (2020)
- [Unsupervised brain lesion segmentation from MRI using a convolutional autoencoder](https://mlsanity.com/paper/1811.09655/) (2018)
- [Semi-supervised Learning using Denoising Autoencoders for Brain Lesion Detection and Segmentation](https://mlsanity.com/paper/1611.08664/) (2016)
- [Paying Per-label Attention for Multi-label Extraction from Radiology Reports](https://mlsanity.com/paper/2007.16152/) (2020)

## Built on by (most cited first, 23 of 23)

- [Exploring Plain ViT Reconstruction for Multi-class Unsupervised Anomaly Detection](https://mlsanity.com/paper/2312.07495/) (2023)
- [MedIAnomaly: A comparative study of anomaly detection in medical images](https://mlsanity.com/paper/2404.04518/) (2024)
- [Many tasks make light work: Learning to localise medical anomalies from multiple synthetic tasks](https://mlsanity.com/paper/2307.00899/) (2023)
- [Replication in Visual Diffusion Models: A Survey and Outlook](https://mlsanity.com/paper/2408.00001/) (2024)
- [A Survey of Emerging Applications of Diffusion Probabilistic Models in MRI](https://mlsanity.com/paper/2311.11383/) (2023)
- [Binary Noise for Binary Tasks: Masked Bernoulli Diffusion for Unsupervised Anomaly Detection](https://mlsanity.com/paper/2403.11667/) (2024)
- [Unsupervised Anomaly Detection using Aggregated Normative Diffusion](https://mlsanity.com/paper/2312.01904/) (2023)
- [Enhancing Reconstruction-Based Out-of-Distribution Detection in Brain MRI with Model and Metric Ensembles](https://mlsanity.com/paper/2412.17586/) (2024)
- [Diffusion-Scheduled Denoising Autoencoders for Anomaly Detection in Tabular Data](https://mlsanity.com/paper/2508.00758/) (2025)
- [Causal Ordering for Structure Learning from Time Series](https://mlsanity.com/paper/2510.24639/) (2025)
- [Unsupervised Detection of Fetal Brain Anomalies using Denoising Diffusion Models](https://mlsanity.com/paper/2408.03654/) (2024)
- [Efficient Slice Anomaly Detection Network for 3D Brain MRI Volume](https://mlsanity.com/paper/2408.15958/) (2024)
- [Diff-CXR: Report-to-CXR generation through a disease-knowledge enhanced diffusion model](https://mlsanity.com/paper/2410.20165/) (2024)
- [OCSVM-Guided Representation Learning for Unsupervised Anomaly Detection](https://mlsanity.com/paper/2507.21164/) (2025)
- [Unsupervised Deep Generative Models for Anomaly Detection in Neuroimaging: A Systematic Scoping Review](https://mlsanity.com/paper/2510.14462/) (2025)
- [Tau Anomaly Detection in PET Imaging via Bilateral-Guided Deterministic Diffusion Model](https://mlsanity.com/paper/2405.13199/) (2024)
- [Localizing Anomalies via Multiscale Score Matching Analysis](https://mlsanity.com/paper/2407.00148/) (2024)
- [U2AD: Uncertainty-based Unsupervised Anomaly Detection Framework for Detecting T2 Hyperintensity in MRI Spinal Cord](https://mlsanity.com/paper/2503.13400/) (2025)
- [Deep Learning Architectures for Medical Image Denoising: A Comparative Study of CNN-DAE, CADTra, and DCMIEDNet](https://mlsanity.com/paper/2508.17223/) (2025)
- [Unsupervised Anomaly Detection in Brain MRI via Disentangled Anatomy Learning](https://mlsanity.com/paper/2512.21924/) (2025)
- [MTL-MAD: Multi-Task Learners are Effective Medical Anomaly Detectors](https://mlsanity.com/paper/2605.05891/) (2026)
- [Noise-Aware Visual Representation Learning for Medical Visual Question Answering](https://mlsanity.com/paper/2606.05535/) (2026)
- [MIRTO: a registration-gated, multiverse-tested evaluation protocol for unsupervised anomaly segmentation in brain MRI](https://mlsanity.com/paper/2610.02136/) (2026)

## Abstract (arXiv)

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.