# Brain subtle anomaly detection based on auto-encoders latent space analysis : application to de novo parkinson patients

arXiv: https://arxiv.org/abs/2302.13593 · HTML: https://mlsanity.com/paper/2302.13593/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 21 references that are in the map.
- First posted on arXiv 27 Feb 2023.

## Builds on (most cited first, 6 of 6)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [A Closer Look at Spatiotemporal Convolutions for Action Recognition](https://mlsanity.com/paper/1711.11248/) (2017)
- [Autoencoders for Unsupervised Anomaly Segmentation in Brain MR Images: A Comparative Study](https://mlsanity.com/paper/2004.03271/) (2020)
- [Convolutional Networks with Dense Connectivity](https://mlsanity.com/paper/2001.02394/) (2020)
- [Patch vs. Global Image-Based Unsupervised Anomaly Detection in MR Brain Scans of Early Parkinsonian Patients](https://mlsanity.com/paper/2110.12707/) (2021)
- [The Scalable Brain Atlas: instant web-based access to public brain atlases and related content](https://mlsanity.com/paper/1312.6310/) (2013)

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

- [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)
- [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)
- [OCSVM-Guided Representation Learning for Unsupervised Anomaly Detection](https://mlsanity.com/paper/2507.21164/) (2025)
- [Towards frugal unsupervised detection of subtle abnormalities in medical imaging](https://mlsanity.com/paper/2309.02458/) (2023)

## Abstract (arXiv)

Neural network-based anomaly detection remains challenging in clinical applications with little or no supervised information and subtle anomalies such as hardly visible brain lesions. Among unsupervised methods, patch-based auto-encoders with their efficient representation power provided by their latent space, have shown good results for visible lesion detection. However, the commonly used reconstruction error criterion may limit their performance when facing less obvious lesions. In this work, we design two alternative detection criteria. They are derived from multivariate analysis and can more directly capture information from latent space representations. Their performance compares favorably with two additional supervised learning methods, on a difficult de novo Parkinson Disease (PD) classification task.