# Patch vs. Global Image-Based Unsupervised Anomaly Detection in MR Brain Scans of Early Parkinsonian Patients

arXiv: https://arxiv.org/abs/2110.12707 · HTML: https://mlsanity.com/paper/2110.12707/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Oct 2021.

## Built on by (most cited first, 5 of 5)

- [On the Pitfalls of Using the Residual Error as Anomaly Score](https://mlsanity.com/paper/2202.03826/) (2022)
- [Brain subtle anomaly detection based on auto-encoders latent space analysis : application to de novo parkinson patients](https://mlsanity.com/paper/2302.13593/) (2023)
- [GAN-based synthetic FDG PET images from T1 brain MRI can serve to improve performance of deep unsupervised anomaly detection models](https://mlsanity.com/paper/2505.07364/) (2025)
- [Unsupervised Deep Generative Models for Anomaly Detection in Neuroimaging: A Systematic Scoping Review](https://mlsanity.com/paper/2510.14462/) (2025)
- [Towards frugal unsupervised detection of subtle abnormalities in medical imaging](https://mlsanity.com/paper/2309.02458/) (2023)

## Abstract (arXiv)

Although neural networks have proven very successful in a number of medical image analysis applications, their use remains difficult when targeting subtle tasks such as the identification of barely visible brain lesions, especially given the lack of annotated datasets. Good candidate approaches are patch-based unsupervised pipelines which have both the advantage to increase the number of input data and to capture local and fine anomaly patterns distributed in the image, while potential inconveniences are the loss of global structural information. We illustrate this trade-off on Parkinson's disease (PD) anomaly detection comparing the performance of two anomaly detection models based on a spatial auto-encoder (AE) and an adaptation of a patch-fed siamese auto-encoder (SAE). On average, the SAE model performs better, showing that patches may indeed be advantageous.