# Leveraging 3D Information in Unsupervised Brain MRI Segmentation

arXiv: https://arxiv.org/abs/2101.10674 · HTML: https://mlsanity.com/paper/2101.10674/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 20 references that are in the map.
- First posted on arXiv 26 Jan 2021.

## Builds on (most cited first, 9 of 9)

- [Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishing](https://mlsanity.com/paper/1903.10145/) (2019)
- [Autoencoders for Unsupervised Anomaly Segmentation in Brain MR Images: A Comparative Study](https://mlsanity.com/paper/2004.03271/) (2020)
- [Automated brain extraction of multi-sequence MRI using artificial neural networks](https://mlsanity.com/paper/1901.11341/) (2019)
- [Standardized Assessment of Automatic Segmentation of White Matter Hyperintensities and Results of the WMH Segmentation Challenge](https://mlsanity.com/paper/1904.00682/) (2019)
- [Unsupervised Detection of Lesions in Brain MRI using constrained adversarial auto-encoders](https://mlsanity.com/paper/1806.04972/) (2018)
- [Context-encoding Variational Autoencoder for Unsupervised Anomaly Detection](https://mlsanity.com/paper/1812.05941/) (2018)
- [A Survey on GANs for Anomaly Detection](https://mlsanity.com/paper/1906.11632/) (2019)
- [Improving automated multiple sclerosis lesion segmentation with a cascaded 3D convolutional neural network approach](https://mlsanity.com/paper/1702.04869/) (2017)
- [Glioma Segmentation with Cascaded Unet](https://mlsanity.com/paper/1810.04008/) (2018)

## Built on by (most cited first, 2 of 2)

- [A Two-Stage Generative Model with CycleGAN and Joint Diffusion for MRI-based Brain Tumor Detection](https://mlsanity.com/paper/2311.03074/) (2023)
- [Unsupervised Deep Generative Models for Anomaly Detection in Neuroimaging: A Systematic Scoping Review](https://mlsanity.com/paper/2510.14462/) (2025)

## Abstract (arXiv)

Automatic segmentation of brain abnormalities is challenging, as they vary considerably from one pathology to another. Current methods are supervised and require numerous annotated images for each pathology, a strenuous task. To tackle anatomical variability, Unsupervised Anomaly Detection (UAD) methods are proposed, detecting anomalies as outliers of a healthy model learned using a Variational Autoencoder (VAE). Previous work on UAD adopted a 2D approach, meaning that MRIs are processed as a collection of independent slices. Yet, it does not fully exploit the spatial information contained in MRI. Here, we propose to perform UAD in a 3D fashion and compare 2D and 3D VAEs. As a side contribution, we present a new loss function guarantying a robust training. Learning is performed using a multicentric dataset of healthy brain MRIs, and segmentation performances are estimated on White-Matter Hyperintensities and tumors lesions. Experiments demonstrate the interest of 3D methods which outperform their 2D counterparts.