Fast Unsupervised Brain Anomaly Detection and Segmentation with Diffusion Models

Pinaya, Walter Hugo Lopez; Graham, Mark S.; Gray, Robert; Costa, Pedro F. da; Tudosiu, Petru-Daniel; Wright, Paul; Mah, Yee H.; MacKinnon, Andrew D.; Teo, James; Jäger, R; Werring, David J.; Rees, Geraint; Nachev, Parashkev; Ourselin, Sébastien; Cardoso, M. Jorge

doi:10.1007/978-3-031-16452-1_67

Cited by 32 publications

(5 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More recently, following the success of diffusion models for image generation, DDPMs have also been used for anomaly detection tasks in medical imaging (Wolleb et al, 2022;Pinaya et al, 2022a;Bercea et al, 2023a).…”

Section: Related Workmentioning

confidence: 99%

Evaluation of pseudo-healthy image reconstruction for anomaly detection with deep generative models: Application to brain FDG PET

Hassanaly,

Brianceau,

Solal

et al. 2024

Melba

View full text Add to dashboard Cite

Over the past years, pseudo-healthy reconstruction for unsupervised anomaly detection has gained in popularity. This approach has the great advantage of not requiring tedious pixel-wise data annotation and offers possibility to generalize to any kind of anomalies, including that corresponding to rare diseases. By training a deep generative model with only images from healthy subjects, the model will learn to reconstruct pseudo-healthy images. This pseudo-healthy reconstruction is then compared to the input to detect and localize anomalies. The evaluation of such methods often relies on a ground truth lesion mask that is available for test data, which may not exist depending on the application.<br>We propose an evaluation procedure based on the simulation of realistic abnormal images to validate pseudo-healthy reconstruction methods when no ground truth is available. This allows us to extensively test generative models on different kinds of anomalies and measuring their performance using the pair of normal and abnormal images corresponding to the same subject. It can be used as a preliminary automatic step to validate the capacity of a generative model to reconstruct pseudo-healthy images, before a more advanced validation step that would require clinician’s expertise. We apply this framework to the reconstruction of 3D brain FDG PET using a convolutional variational autoencoder with the aim to detect as early as possible the neurodegeneration markers that are specific to dementia such as Alzheimer’s disease.

show abstract

Section: Related Workmentioning

confidence: 99%

Evaluation of pseudo-healthy image reconstruction for anomaly detection with deep generative models: Application to brain FDG PET

Hassanaly,

Brianceau,

Solal

et al. 2024

Melba

View full text Add to dashboard Cite

show abstract

“…Recently, a wide range of diffusion-based perception applications has emerged, such as image generation [15,21,35,47], image segmentation [4,7,18,23], object detection [8], etc. A few previous works have tentatively explored the application of diffusion in medical anomaly detection [32,53], such as AnoDDPM [21], but its inference speed is slow and the anomalous false positive rate is high, which is nowhere near the requirements for practical deployment. To the best of our knowledge, we are the first to propose a diffusion-based pipeline with gratifying anomaly detection and localization performance as well as fast inference speed.…”

Section: Related Workmentioning

confidence: 99%

DiffusionAD: Denoising Diffusion for Anomaly Detection

Zhang¹,

Wang²,

Wu³

et al. 2023

Preprint

View full text Add to dashboard Cite

Anomaly detection is widely applied due to its remarkable effectiveness and efficiency in meeting the needs of realworld industrial manufacturing. We introduce a new pipeline, DiffusionAD, to anomaly detection. We frame anomaly detection as a "noise-to-norm" paradigm, in which anomalies are identified as inconsistencies between a query image and its flawless approximation. Our pipeline achieves this by restoring the anomalous regions from the noisy corrupted query image while keeping the normal regions unchanged. DiffusionAD includes a denoising sub-network and a segmentation sub-network, which work together to provide intuitive anomaly detection and localization in an end-to-end manner, without the need for complicated post-processing steps. Remarkably, during inference, this framework delivers satisfactory performance with just one diffusion reverse process step, which is tens to hundreds of times faster than general diffusion methods. Extensive evaluations on standard and challenging benchmarks including VisA and DAGM show that DiffusionAD outperforms current state-of-the-art paradigms, demonstrating the effectiveness and generalizability of the proposed pipeline.

show abstract

“…To alleviate this, inpainting approaches have been proposed that use the generator to inpaint erased patches during training (Nguyen et al, 2021). Lately, DDPMs have shown to be a promising approach for the task of UAD in brain MRI as they have scalable and stable training properties while generating sharp images of high quality (Wolleb et al, 2022;Wyatt et al, 2022;Sanchez et al, 2022;Pinaya et al, 2022a). While these approaches aim to estimate the entire brain anatomy at once, patch-based DDPMs have been proposed for image restoration ( Özdenizci and Legenstein, 2023) and image inpainting (Lugmayr et al, 2022) in the domain of generic images.…”

Section: Recent Workmentioning

confidence: 99%

“…Recently, denoising diffusion probabilistic models (DDPM) (Ho et al, 2020) have emerged as a state-of-the-art approach for image generation. As a result, they have also been applied to the problem of unsupervised anomaly detection (UAD) in brain MRI (Wyatt et al, 2022;Pinaya et al, 2022a). DDPMs work by adding noise to an input image, then using a trained model to remove the noise and estimate or reconstruct the original image.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Anomaly Detection in 3D Brain MRI Using Deep Learning with Impured Training Data

Behrendt¹,

Bengs²,

Frederik³

et al. 2022

2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI)

View full text Add to dashboard Cite

The detection of lesions in magnetic resonance imaging (MRI)-scans of human brains remains challenging, timeconsuming and error-prone. Recently, unsupervised anomaly detection (UAD) methods have shown promising results for this task. These methods rely on training data sets that solely contain healthy samples. Compared to supervised approaches, this significantly reduces the need for an extensive amount of labeled training data. However, data labelling remains error-prone. We study how unhealthy samples within the training data affect anomaly detection performance for brain MRI-scans. For our evaluations, we consider three publicly available data sets and use autoencoders (AE) as a well-established baseline method for UAD. We systematically evaluate the effect of impured training data by injecting different quantities of unhealthy samples to our training set of healthy samples from T1-weighted MRI-scans. We evaluate a method to identify falsely labeled samples directly during training based on the reconstruction error of the AE. Our results show that training with impured data decreases the UAD performance notably even with few falsely labeled samples. By performing outlier removal directly during training based on the reconstruction-loss, we demonstrate that falsely labeled data can be detected and removed to mitigate the effect of falsely labeled data. Overall, we highlight the importance of clean data sets for UAD in brain MRI and demonstrate an approach for detecting falsely labeled data directly during training.

show abstract

Fast Unsupervised Brain Anomaly Detection and Segmentation with Diffusion Models

Cited by 32 publications

References 17 publications

Evaluation of pseudo-healthy image reconstruction for anomaly detection with deep generative models: Application to brain FDG PET

Evaluation of pseudo-healthy image reconstruction for anomaly detection with deep generative models: Application to brain FDG PET

DiffusionAD: Denoising Diffusion for Anomaly Detection

Unsupervised Anomaly Detection in 3D Brain MRI Using Deep Learning with Impured Training Data

Contact Info

Product

Resources

About