#5971. Three-dimensional deep learning with spatial erasing for unsupervised anomaly segmentation in brain MRI

August 2026publication date
Proposal available till 07-06-2025
4 total number of authors per manuscript0 $

The title of the journal is available only for the authors who have already paid for
Journal’s subject area:
Surgery;
Computer Graphics and Computer-Aided Design;
Radiology, Nuclear Medicine and Imaging;
Health Informatics;
Computer Science Applications;
Computer Vision and Pattern Recognition;
Biomedical Engineering;
Places in the authors’ list:
place 1place 2place 3place 4
FreeFreeFreeFree
2350 $1200 $1050 $900 $
Contract №5971.1 Contract №5971.2 Contract №5971.3 Contract №5971.4
1 place - free (for sale)
2 place - free (for sale)
3 place - free (for sale)
4 place - free (for sale)

Abstract:
Purpose: Brain Magnetic Resonance Images (MRIs) are essential for the diagnosis of neurological diseases. Recently, deep learning methods for unsupervised anomaly detection (UAD) have been proposed for the analysis of brain MRI. These methods rely on healthy brain MRIs and eliminate the requirement of pixel-wise annotated data compared to supervised deep learning. While a wide range of methods for UAD have been proposed, these methods are mostly 2D and only learn from MRI slices, disregarding that brain lesions are inherently 3D and the spatial context of MRI volumes remains unexploited. Methods: We investigate whether using increased spatial context by using MRI volumes combined with spatial erasing leads to improved unsupervised anomaly segmentation performance compared to learning from slices. We evaluate and compare 2D variational autoencoder (VAE) to their 3D counterpart, propose 3D input erasing, and systemically study the impact of the data set size on the performance.
Keywords:
3D autoencoder; Anomaly; Brain MRI; Segmentation; Unsupervised

Contacts :
0