# Enhancing Reconstruction-Based Out-of-Distribution Detection in Brain MRI with Model and Metric Ensembles

arXiv: https://arxiv.org/abs/2412.17586 · HTML: https://mlsanity.com/paper/2412.17586/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 65 references that are in the map.
- First posted on arXiv 23 Dec 2024.

## Builds on (most cited first, 30 of 38)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](https://mlsanity.com/paper/1711.11585/) (2017)
- [Generalized Out-of-Distribution Detection: A Survey](https://mlsanity.com/paper/2110.11334/) (2021)
- [Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection](https://mlsanity.com/paper/1904.02639/) (2019)
- [GANomaly: Semi-Supervised Anomaly Detection via Adversarial Training](https://mlsanity.com/paper/1805.06725/) (2018)
- [Brain Imaging Generation with Latent Diffusion Models](https://mlsanity.com/paper/2209.07162/) (2022)
- [Diffusion Models for Medical Anomaly Detection](https://mlsanity.com/paper/2203.04306/) (2022)
- [TorchIO: A Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning](https://mlsanity.com/paper/2003.04696/) (2020)
- [Autoencoders for Unsupervised Anomaly Segmentation in Brain MR Images: A Comparative Study](https://mlsanity.com/paper/2004.03271/) (2020)
- [Fast Unsupervised Brain Anomaly Detection and Segmentation with Diffusion Models](https://mlsanity.com/paper/2206.03461/) (2022)
- [Unsupervised Anomaly Localization using Variational Auto-Encoders](https://mlsanity.com/paper/1907.02796/) (2019)
- [Generative AI for Medical Imaging: extending the MONAI Framework](https://mlsanity.com/paper/2307.15208/) (2023)
- [Unsupervised Lesion Detection via Image Restoration with a Normative Prior](https://mlsanity.com/paper/2005.00031/) (2020)
- [What is Healthy? Generative Counterfactual Diffusion for Lesion Localization](https://mlsanity.com/paper/2207.12268/) (2022)
- [Mask, Stitch, and Re-Sample: Enhancing Robustness and Generalizability in Anomaly Detection through Automatic Diffusion Models](https://mlsanity.com/paper/2305.19643/) (2023)
- [Patched Diffusion Models for Unsupervised Anomaly Detection in Brain MRI](https://mlsanity.com/paper/2303.03758/) (2023)
- [Detecting Outliers with Poisson Image Interpolation](https://mlsanity.com/paper/2107.02622/) (2021)
- [Diffusion Models with Implicit Guidance for Medical Anomaly Detection](https://mlsanity.com/paper/2403.08464/) (2024)
- [Unsupervised Anomaly Detection in Medical Images Using Masked Diffusion Model](https://mlsanity.com/paper/2305.19867/) (2023)
- [Unsupervised Anomaly Localization with Structural Feature-Autoencoders](https://mlsanity.com/paper/2208.10992/) (2022)
- [The role of noise in denoising models for anomaly detection in medical images](https://mlsanity.com/paper/2301.08330/) (2023)
- [Rethinking Autoencoders for Medical Anomaly Detection from A Theoretical Perspective](https://mlsanity.com/paper/2403.09303/) (2024)
- [Scale-Space Autoencoders for Unsupervised Anomaly Segmentation in Brain MRI](https://mlsanity.com/paper/2006.12852/) (2020)
- [Unsupervised 3D out-of-distribution detection with latent diffusion models](https://mlsanity.com/paper/2307.03777/) (2023)
- [Transformer-based out-of-distribution detection for clinically safe segmentation](https://mlsanity.com/paper/2205.10650/) (2022)
- [Unsupervised Anomaly Detection in Medical Images with a Memory-augmented Multi-level Cross-attentional Masked Autoencoder](https://mlsanity.com/paper/2203.11725/) (2022)
- [Many tasks make light work: Learning to localise medical anomalies from multiple synthetic tasks](https://mlsanity.com/paper/2307.00899/) (2023)
- [Ensembled Cold-Diffusion Restorations for Unsupervised Anomaly Detection](https://mlsanity.com/paper/2407.06635/) (2024)

## Built on by (most cited first, 4 of 4)

- [Bounding Distributional Shifts in World Modeling through Novelty Detection](https://mlsanity.com/paper/2508.06096/) (2025)
- [Unsupervised Deep Generative Models for Anomaly Detection in Neuroimaging: A Systematic Scoping Review](https://mlsanity.com/paper/2510.14462/) (2025)
- [Mitigating the reconstruction-detection trade-off in VAE-based unsupervised anomaly detection](https://mlsanity.com/paper/2605.02918/) (2026)
- [Evaluating the Safety of Deep Learning-Based Brain MRI Reconstruction](https://mlsanity.com/paper/2608.28714/) (2026)

## Abstract (arXiv)

Out-of-distribution (OOD) detection is crucial for safely deploying automated medical image analysis systems, as abnormal patterns in images could hamper their performance. However, OOD detection in medical imaging remains an open challenge, and we address three gaps: the underexplored potential of a simple OOD detection model, the lack of optimization of deep learning strategies specifically for OOD detection, and the selection of appropriate reconstruction metrics. In this study, we investigated the effectiveness of a reconstruction-based autoencoder for unsupervised detection of synthetic artifacts in brain MRI. We evaluated the general reconstruction capability of the model, analyzed the impact of the selected training epoch and reconstruction metrics, assessed the potential of model and/or metric ensembles, and tested the model on a dataset containing a diverse range of artifacts. Among the metrics assessed, the contrast component of SSIM and LPIPS consistently outperformed others in detecting homogeneous circular anomalies. By combining two well-converged models and using LPIPS and contrast as reconstruction metrics, we achieved a pixel-level area under the Precision-Recall curve of 0.66. Furthermore, with the more realistic OOD dataset, we observed that the detection performance varied between artifact types; local artifacts were more difficult to detect, while global artifacts showed better detection results. These findings underscore the importance of carefully selecting metrics and model configurations, and highlight the need for tailored approaches, as standard deep learning approaches do not always align with the unique needs of OOD detection.