# Reversing the Abnormal: Pseudo-Healthy Generative Networks for Anomaly Detection

arXiv: https://arxiv.org/abs/2303.08452 · HTML: https://mlsanity.com/paper/2303.08452/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 28 references that are in the map.
- First posted on arXiv 15 Mar 2023.

## Builds on (most cited first, 18 of 18)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Towards Total Recall in Industrial Anomaly Detection](https://mlsanity.com/paper/2106.08265/) (2021)
- [PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization](https://mlsanity.com/paper/2011.08785/) (2020)
- [A Unifying Review of Deep and Shallow Anomaly Detection](https://mlsanity.com/paper/2009.11732/) (2020)
- [Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddings](https://mlsanity.com/paper/1911.02357/) (2019)
- [Multiresolution Knowledge Distillation for Anomaly Detection](https://mlsanity.com/paper/2011.11108/) (2020)
- [Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentation](https://mlsanity.com/paper/1603.05959/) (2016)
- [OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representations](https://mlsanity.com/paper/1903.08550/) (2019)
- [Aggregated Contextual Transformations for High-Resolution Image Inpainting](https://mlsanity.com/paper/2104.01431/) (2021)
- [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)
- [Understanding Anomaly Detection with Deep Invertible Networks through Hierarchies of Distributions and Features](https://mlsanity.com/paper/2006.10848/) (2020)
- [Soft-IntroVAE: Analyzing and Improving the Introspective Variational Autoencoder](https://mlsanity.com/paper/2012.13253/) (2020)
- [On the Pitfalls of Using the Residual Error as Anomaly Score](https://mlsanity.com/paper/2202.03826/) (2022)

## Built on by (most cited first, 18 of 18)

- [Mask, Stitch, and Re-Sample: Enhancing Robustness and Generalizability in Anomaly Detection through Automatic Diffusion Models](https://mlsanity.com/paper/2305.19643/) (2023)
- [Diffusion Models for Counterfactual Generation and Anomaly Detection in Brain Images](https://mlsanity.com/paper/2308.02062/) (2023)
- [Guided Reconstruction with Conditioned Diffusion Models for Unsupervised Anomaly Detection in Brain MRIs](https://mlsanity.com/paper/2312.04215/) (2023)
- [Evaluation of pseudo-healthy image reconstruction for anomaly detection with deep generative models: Application to brain FDG PET](https://mlsanity.com/paper/2401.16363/) (2024)
- [Leveraging the Mahalanobis Distance to enhance Unsupervised Brain MRI Anomaly Detection](https://mlsanity.com/paper/2407.12474/) (2024)
- [DISYRE: Diffusion-Inspired SYnthetic REstoration for Unsupervised Anomaly Detection](https://mlsanity.com/paper/2311.15453/) (2023)
- [Unsupervised Anomaly Detection using Aggregated Normative Diffusion](https://mlsanity.com/paper/2312.01904/) (2023)
- [Language Models Meet Anomaly Detection for Better Interpretability and Generalizability](https://mlsanity.com/paper/2404.07622/) (2024)
- [Applications of interpretable deep learning in neuroimaging: a comprehensive review](https://mlsanity.com/paper/2406.17792/) (2024)
- [Denoising Diffusion Models for Anomaly Localization in Medical Images](https://mlsanity.com/paper/2410.23834/) (2024)
- [Weakly Supervised Anomaly Detection for Chest X-Ray Image](https://mlsanity.com/paper/2311.09642/) (2023)
- [Spatial-aware Attention Generative Adversarial Network for Semi-supervised Anomaly Detection in Medical Image](https://mlsanity.com/paper/2405.12872/) (2024)
- [Towards the Discovery of Down Syndrome Brain Biomarkers Using Generative Models](https://mlsanity.com/paper/2409.13437/) (2024)
- [Selective Test-Time Adaptation for Unsupervised Anomaly Detection using Neural Implicit Representations](https://mlsanity.com/paper/2410.03306/) (2024)
- [Patch2Loc: Learning to Localize Patches for Unsupervised Brain Lesion Detection](https://mlsanity.com/paper/2506.22504/) (2025)
- [Investigating the Role of Bilateral Symmetry for Inpainting Brain MRI](https://mlsanity.com/paper/2504.10039/) (2025)
- [Deep Learning Approaches for Medical Imaging Under Varying Degrees of Label Availability: A Comprehensive Survey](https://mlsanity.com/paper/2504.11588/) (2025)
- [Unsupervised Anomaly Detection in Brain MRI via Disentangled Anatomy Learning](https://mlsanity.com/paper/2512.21924/) (2025)

## Abstract (arXiv)

Early and accurate disease detection is crucial for patient management and successful treatment outcomes. However, the automatic identification of anomalies in medical images can be challenging. Conventional methods rely on large labeled datasets which are difficult to obtain. To overcome these limitations, we introduce a novel unsupervised approach, called PHANES (Pseudo Healthy generative networks for ANomaly Segmentation). Our method has the capability of reversing anomalies, i.e., preserving healthy tissue and replacing anomalous regions with pseudo-healthy (PH) reconstructions. Unlike recent diffusion models, our method does not rely on a learned noise distribution nor does it introduce random alterations to the entire image. Instead, we use latent generative networks to create masks around possible anomalies, which are refined using inpainting generative networks. We demonstrate the effectiveness of PHANES in detecting stroke lesions in T1w brain MRI datasets and show significant improvements over state-of-the-art (SOTA) methods. We believe that our proposed framework will open new avenues for interpretable, fast, and accurate anomaly segmentation with the potential to support various clinical-oriented downstream tasks.