mlsanityData to 14 Oct 2026

Meningioma segmentation in T1-weighted MRI leveraging global context and attention mechanisms

arXiv 2101.07715 ↗First posted 19 Jan 2021eess.IV cs.CV cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

Meningiomas are the most common type of primary brain tumor, accounting for approximately 30% of all brain tumors. A substantial number of these tumors are never surgically removed but rather monitored over time. Automatic and precise meningioma segmentation is therefore beneficial to enable reliable growth estimation and patient-specific treatment planning. In this study, we propose the inclusion of attention mechanisms over a U-Net architecture: (i) Attention-gated U-Net (AGUNet) and (ii) Dual Attention U-Net (DAUNet), using a 3D MRI volume as input. Attention has the potential to leverage the global context and identify features' relationships across the entire volume. To limit spatial resolution degradation and loss of detail inherent to encoder-decoder architectures, we studied the impact of multi-scale input and deep supervision components. The proposed architectures are trainable end-to-end and each concept can be seamlessly disabled for ablation studies. The validation studies were performed using a 5-fold cross validation over 600 T1-weighted MRI volumes from St. Olavs University Hospital, Trondheim, Norway. For the best performing architecture, an average Dice score of 81.6% was reached for an F1-score of 95.6%. With an almost perfect precision of 98%, meningiomas smaller than 3ml were occasionally missed hence reaching an overall recall of 93%. Leveraging global context from a 3D MRI volume provided the best performances, even if the native volume resolution could not be processed directly. Overall, near-perfect detection was achieved for meningiomas larger than 3ml which is relevant for clinical use. In the future, the use of multi-scale designs and refinement networks should be further investigated to improve the performance. A larger number of cases with meningiomas below 3ml might also be needed to improve the performance for the smallest tumors.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 32 of its 65 references that are in the map. First posted on arXiv 19 Jan 2021.

Builds on

32 of 65 references.

References · 32

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  4. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  5. 2016Pyramid Scene Parsing Networkcited by 2,479
  6. 2017Non-local Neural Networkscited by 2,293
  7. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,487
  8. 2018Attention U-Net: Learning Where to Look for the Pancreascited by 1,435
  9. 2018Dual Attention Network for Scene Segmentationcited by 1,003
  10. 2016RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentationcited by 465
  11. 2014Deeply-Supervised Netscited by 367
  12. 20183D MRI brain tumor segmentation using autoencoder regularizationcited by 328
20 more
  1. 2017A Structured Self-attentive Sentence Embeddingcited by 318
  2. 2018nnU-Net: Self-adapting Framework for U-Net-Based Medical Image Segmentationcited by 291
  3. 2018Attention Gated Networks: Learning to Leverage Salient Regions in Medical Imagescited by 272
  4. 2016Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentationcited by 263
  5. 2017Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Networkcited by 208
  6. 2018A Novel Focal Tversky loss function with improved Attention U-Net for lesion segmentationcited by 172
  7. 2015Brain Tumor Segmentation with Deep Neural Networkscited by 137
  8. 2018BACH: Grand Challenge on Breast Cancer Histology Imagescited by 131
  9. 2018Revisiting Small Batch Training for Deep Neural Networkscited by 102
  10. 2019Multi-scale self-guided attention for medical image segmentationcited by 84
  11. 2018Learn To Pay Attentioncited by 83
  12. 2015Efficient piecewise training of deep structured models for semantic segmentationcited by 71
  13. 2018No New-Netcited by 61
  14. 2017Evaluate the Malignancy of Pulmonary Nodules Using the 3D Deep Leaky Noisy-or Networkcited by 53
  15. 2017A deep learning model integrating FCNNs and CRFs for brain tumor segmentationcited by 35
  16. 2018Brain Tumor Segmentation using an Ensemble of 3D U-Nets and Overall Survival Prediction using Radiomic Featurescited by 33
  17. 2020Automatic lung segmentation in routine imaging is primarily a data diversity problem, not a methodology problemcited by 9
  18. 2017Automated cardiovascular magnetic resonance image analysis with fully convolutional networkscited by 2
  19. 2020Fast meningioma segmentation in T1-weighted MRI volumes using a lightweight 3D deep learning architecturecited by 2
  20. 2020Hybrid Multiple Attention Network for Semantic Segmentation in Aerial Imagescited by 1

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 1; 2023: 6.

9 papers.

  1. 2021Mediastinal lymph nodes segmentation using 3D convolutional neural network ensembles and anatomical priors guidingcited by 18
  2. 2023AeroPath: An airway segmentation benchmark dataset with challenging pathologycited by 10
  3. 2022Preoperative brain tumor imaging: models and software for segmentation and standardized reportingcited by 9
  4. 2023Segmentation of glioblastomas in early post-operative multi-modal MRI with deep neural networkscited by 3
  5. 2023Raidionics: an open software for pre- and postoperative central nervous system tumor segmentation and standardized reportingcited by 3
  6. 2023M-VAAL: Multimodal Variational Adversarial Active Learning for Downstream Medical Image Analysis Taskscited by 2
  7. 2021Hybrid guiding: A multi-resolution refinement approach for semantic segmentation of gigapixel histopathological imagescited by 1
  8. 2023Localise to segment: crop to improve organ at risk segmentation accuracycited by 0
  9. 2023Interpolation-Split: a data-centric deep learning approach with big interpolated data to boost airway segmentation performancecited by 0