mlsanityData to 7 Oct 2026

Transformer based Models for Unsupervised Anomaly Segmentation in Brain MR Images

arXiv 2207.02059 ↗First posted 5 Jul 2022eess.IV cs.CV q-bio.NCcited by 7

Not on the map. Why?

Abstract (arXiv)

The quality of patient care associated with diagnostic radiology is proportionate to a physician workload. Segmentation is a fundamental limiting precursor to both diagnostic and therapeutic procedures. Advances in machine learning (ML) aim to increase diagnostic efficiency by replacing a single application with generalized algorithms. The goal of unsupervised anomaly detection (UAD) is to identify potential anomalous regions unseen during training, where convolutional neural network (CNN) based autoencoders (AEs) and variational autoencoders (VAEs) are considered a de facto approach for reconstruction based-anomaly segmentation. The restricted receptive field in CNNs limits the CNN to model the global context. Hence, if the anomalous regions cover large parts of the image, the CNN-based AEs are not capable of bringing a semantic understanding of the image. Meanwhile, vision transformers (ViTs) have emerged as a competitive alternative to CNNs. It relies on the self-attention mechanism that can relate image patches to each other. We investigate in this paper Transformer capabilities in building AEs for the reconstruction-based UAD task to reconstruct a coherent and more realistic image. We focus on anomaly segmentation for brain magnetic resonance imaging (MRI) and present five Transformer-based models while enabling segmentation performance comparable to or superior to state-of-the-art (SOTA) models. The source code is made publicly available on GitHub: https://github.com/ahmedgh970/Transformers_Unsupervised_Anomaly_Segmentation.git.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 33 of its 48 references that are in the map. First posted on arXiv 5 Jul 2022.

Builds on

33 of 48 references.

References · 33

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  3. 2020End-to-End Object Detection with Transformerscited by 7,384
  4. 2017Neural Discrete Representation Learningcited by 4,650
  5. 2017Non-local Neural Networkscited by 2,290
  6. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  7. 2021Vision Transformers for Dense Predictioncited by 1,789
  8. 2019Generating Long Sequences with Sparse Transformerscited by 1,523
  9. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,368
  10. 2021Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentationcited by 1,218
  11. 2021UNETR: Transformers for 3D Medical Image Segmentationcited by 954
  12. 2016Pixel Recurrent Neural Networkscited by 814
21 more
  1. 2018Image Transformercited by 770
  2. 2021Twins: Revisiting the Design of Spatial Attention in Vision Transformerscited by 565
  3. 2021Medical Transformer: Gated Axial-Attention for Medical Image Segmentationcited by 319
  4. 2018Attention Gated Networks: Learning to Leverage Salient Regions in Medical Imagescited by 271
  5. 2021TransFuse: Fusing Transformers and CNNs for Medical Image Segmentationcited by 258
  6. 2021CoTr: Efficiently Bridging CNN and Transformer for 3D Medical Image Segmentationcited by 227
  7. 2021Co-Scale Conv-Attentional Image Transformerscited by 224
  8. 2020U-Net and its variants for medical image segmentation: theory and applicationscited by 169
  9. 2018Deep Autoencoding Models for Unsupervised Anomaly Segmentation in Brain MR Imagescited by 146
  10. 2020Autoencoders for Unsupervised Anomaly Segmentation in Brain MR Images: A Comparative Studycited by 146
  11. 2021LambdaNetworks: Modeling Long-Range Interactions Without Attentioncited by 107
  12. 2018Unsupervised Detection of Lesions in Brain MRI using constrained adversarial auto-encoderscited by 83
  13. 2019Unsupervised Anomaly Localization using Variational Auto-Encoderscited by 73
  14. 2020MADGAN: unsupervised Medical Anomaly Detection GAN using multiple adjacent brain MRI slice reconstructioncited by 50
  15. 2021AFTer-UNet: Axial Fusion Transformer UNet for Medical Image Segmentationcited by 48
  16. 2021Constrained Contrastive Distribution Learning for Unsupervised Anomaly Detection and Localisation in Medical Imagescited by 45
  17. 2018RA-UNet: A hybrid deep attention-aware network to extract liver and tumor in CT scanscited by 41
  18. 2021Unsupervised Brain Anomaly Detection and Segmentation with Transformerscited by 34
  19. 2020Scale-Space Autoencoders for Unsupervised Anomaly Segmentation in Brain MRIcited by 22
  20. 2018Unsupervised brain lesion segmentation from MRI using a convolutional autoencodercited by 17
  21. 2020Multiple Sclerosis Lesion Segmentation -- A Survey of Supervised CNN-Based Methodscited by 3

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 1; 2025: 3.

7 papers.

  1. 2023Unsupervised Pathology Detection: A Deep Dive Into the State of the Artcited by 24
  2. 2024AutoRG-Brain: Grounded Report Generation for Brain MRIcited by 23
  3. 2023Cheap Lunch for Medical Image Segmentation by Fine-tuning SAM on Few Exemplarscited by 21
  4. 2023Unsupervised Brain Tumor Segmentation with Image-based Promptscited by 1
  5. 2025Quantitative Benchmarking of Anomaly Detection Methods in Digital Pathologycited by 1
  6. 2025Unsupervised Deep Generative Models for Anomaly Detection in Neuroimaging: A Systematic Scoping Reviewcited by 1
  7. 2025Latent Anomaly Detection: Masked VQ-GAN for Unsupervised Segmentation in Medical CBCTcited by 0