Diffusion Models for Medical Anomaly Detection

2022/03/08 by Julia Wolleb, Wolleb, Julia, Florentin Bieder +5 · 48 citations
Computer Science · Engineering · Medicine · #Anomaly Detection Techniques and Applications #Anomaly detection #Artificial intelligence #Autoencoder #COVID-19 diagnosis using AI #Classifier (UML) #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Deep learning #FOS: Computer and information sciences #FOS: Electrical engineering #Generative grammar #Image and Video Processing (eess.IV) #Image denoising #Machine Learning in Healthcare #Machine learning #Noise reduction #Pattern recognition (psychology) #Translation (biology) #cs.CV #eess.IV #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2203.04306

published in arXiv (Cornell University) (Cornell University)

openalex publication_date 2022/03/08 · arxiv created 2022/10/05 · arxiv updated 2022/10/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/06

Abstract

In medical applications, weakly supervised anomaly detection methods are of great interest, as only image-level annotations are required for training. Current anomaly detection methods mainly rely on generative adversarial networks or autoencoder models. Those models are often complicated to train or have difficulties to preserve fine details in the image. We present a novel weakly supervised anomaly detection method based on denoising diffusion implicit models. We combine the deterministic iterative noising and denoising scheme with classifier guidance for image-to-image translation between diseased and healthy subjects. Our method generates very detailed anomaly maps without the need for a complex training procedure. We evaluate our method on the BRATS2020 dataset for brain tumor detection and the CheXpert dataset for detecting pleural effusions.

Cited by

• Group Equivariant Diffusion for Anomaly Detection in Computational Cytology
• Pancakes: Consistent Multi-Protocol Image Segmentation Across Biomedical Domains
• Hide-and-Seek Attribution: Weakly Supervised Segmentation of Vertebral Metastases in CT
• Towards Irreversible Machine Unlearning for Diffusion Models
• ART-ASyn: Anatomy-aware Realistic Texture-based Anomaly Synthesis Framework for Chest X-Rays
• Zero-Training Task-Specific Model Synthesis for Few-Shot Medical Image Classification
• BrainNormalizer: Anatomy-Informed Pseudo-Healthy Brain Reconstruction from Tumor MRI via Edge-Guided ControlNet
• WDT-MD: Wavelet Diffusion Transformers for Microaneurysm Detection in Fundus Images
• VLMDiff: Leveraging Vision-Language Models for Multi-Class Anomaly Detection with Diffusion
• Deep Generative Models for Enhanced Vitreous OCT Imaging
• CBDiff:Conditional Bernoulli Diffusion Models for Image Forgery Localization
• Deep generative priors for 3D brain analysis
• Integrating Anatomical Priors into a Causal Diffusion Model
• Contrastive Anatomy-Contrast Disentanglement: A Domain-General MRI Harmonization Method
• AURAD: Anatomy-Pathology Unified Radiology Synthesis with Progressive Representations
• From Transthoracic to Transesophageal: Cross-Modality Generation using LoRA Diffusion
• MPOCryptoML: Multi-Pattern based Off-Chain Crypto Money Laundering Detection
• Vision Generalist Model: A Survey
• CADD: Context aware disease deviations via restoration of brain images using normative conditional diffusion models
• Diffusion-Scheduled Denoising Autoencoders for Anomaly Detection in Tabular Data
• Out-of-Distribution Detection in Medical Imaging via Diffusion Trajectories
• Zero-Shot Image Anomaly Detection Using Generative Foundation Models
• A Comprehensive Review of Diffusion Models in Smart Agriculture: Progress, Applications, and Challenges
• An h-space Based Adversarial Attack for Protection Against Few-shot Personalization
• Unsupervised anomaly detection using Bayesian flow networks: application to brain FDG PET in the context of Alzheimer's disease
• A Simple Analysis of Discretization Error in Diffusion Models
• Human-Guided Shade Artifact Suppression in CBCT-to-MDCT Translation via Schrödinger Bridge with Conditional Diffusion
• MAMBO: High-Resolution Generative Approach for Mammography Images
• Diffusion-Based Electrocardiography Noise Quantification via Anomaly Detection
• Enhancing Glass Defect Detection with Diffusion Models: Addressing Imbalanced Datasets in Manufacturing Quality Control
• Pseudo-Labeling Driven Refinement of Benchmark Object Detection Datasets via Analysis of Learning Patterns
• MR2US-Pro: Prostate MR to Ultrasound Image Translation and Registration Based on Diffusion Models
• ImmunoDiff: A Diffusion Model for Immunotherapy Response Prediction in Lung Cancer
• Advancing Generalizable Tumor Segmentation with Anomaly-Aware Open-Vocabulary Attention Maps and Frozen Foundation Diffusion Models
• Anomalies by Synthesis: Anomaly Detection using Generative Diffusion Models for Off-Road Navigation
• Detect, Classify, Act: Categorizing Industrial Anomalies with Multi-Modal Large Language Models
• Harnessing EHRs for Diffusion-based Anomaly Detection on Chest X-rays
• NOVA: A Benchmark for Anomaly Localization and Clinical Reasoning in Brain MRI
• Reconstruction-Shift Discrimination via Mask-Guided Latent Diffusion for Medical Anomaly Detection
• Recent Advances in Diffusion Models for Hyperspectral Image Processing and Analysis: A Review
• Beyond Static Anchors: Bounded Prototype Conditioning for Language-Free Medical Anomaly Detection
• Research on Anomaly Detection Methods Based on Diffusion Models
• Anomaly-Driven Approach for Enhanced Prostate Cancer Segmentation
• IterMask3D: Unsupervised Anomaly Detection and Segmentation with Test-Time Iterative Mask Refinement in 3D Brain MR
• BrainMRDiff: A Diffusion Model for Anatomically Consistent Brain MRI Synthesis
• Causal Disentanglement for Robust Long-tail Medical Image Generation
• MathPhys-Guided Coarse-to-Fine Anomaly Synthesis with SQE-Driven Bi-Level Optimization for Anomaly Detection
• SD-ReID: View-aware Stable Diffusion for Aerial-Ground Person Re-Identification

Related

• Denoising Diffusion Models for Anomaly Localization in Medical Images
• Adversarial Denoising Diffusion Model for Unsupervised Anomaly Detection
• AnoDODE: Anomaly Detection with Diffusion ODE
• The role of noise in denoising models for anomaly detection in medical images
• MAD-AD: Masked Diffusion for Unsupervised Brain Anomaly Detection