mlsanityData to 14 Oct 2026

Hard Spatial Gating for Precision-Driven Brain Metastasis Segmentation: Addressing the Over-Segmentation Paradox in Deep Attention Networks

arXiv 2511.22606 ↗First posted 27 Nov 2025eess.IV cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Brain metastasis segmentation in MRI remains a formidable challenge due to diminutive lesion sizes (5-15 mm) and extreme class imbalance (less than 2% tumor volume). While soft-attention CNNs are widely used, we identify a critical failure mode termed the "over-segmentation paradox," where models achieve high sensitivity (recall > 0.88) but suffer from catastrophic precision collapse (precision < 0.23) and boundary errors exceeding 150 mm. This imprecision poses significant risks for stereotactic radiosurgery planning. To address this, we introduce the Spatial Gating Network (SG-Net), a precision-first architecture employing hard spatial gating mechanisms. Unlike traditional soft attention, SG-Net enforces strict feature selection to aggressively suppress background artifacts while preserving tumor features. Validated on the Brain-Mets-Lung-MRI dataset (n=92), SG-Net achieves a Dice Similarity Coefficient of 0.5578 +/- 0.0243 (95% CI: 0.45-0.67), statistically outperforming Attention U-Net (p < 0.001) and ResU-Net (p < 0.001). Most critically, SG-Net demonstrates a threefold improvement in boundary precision, achieving a 95% Hausdorff Distance of 56.13 mm compared to 157.52 mm for Attention U-Net, while maintaining robust recall (0.79) and superior precision (0.52 vs. 0.20). Furthermore, SG-Net requires only 0.67M parameters (8.8x fewer than Attention U-Net), facilitating deployment in resource-constrained environments. These findings establish hard spatial gating as a robust solution for precision-driven lesion detection, directly enhancing radiosurgery accuracy.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 42 of its 74 references that are in the map. First posted on arXiv 27 Nov 2025.

Builds on

42 of 74 references.

References · 42

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  6. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  7. 2017Squeeze-and-Excitation Networkscited by 4,789
  8. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  9. 2018CBAM: Convolutional Block Attention Modulecited by 2,477
  10. 2017Non-local Neural Networkscited by 2,293
  11. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,292
  12. 2021TransUNet: Transformers Make Strong Encoders for Medical Image Segmentationcited by 1,558
30 more
  1. 2018Attention U-Net: Learning Where to Look for the Pancreascited by 1,435
  2. 2021Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentationcited by 1,222
  3. 2017A Survey on Deep Learning in Medical Image Analysiscited by 1,186
  4. 2018Dual Attention Network for Scene Segmentationcited by 1,003
  5. 2014Striving for Simplicity: The All Convolutional Netcited by 990
  6. 2021UNETR: Transformers for 3D Medical Image Segmentationcited by 959
  7. 2018Self-Attention Generative Adversarial Networkscited by 809
  8. 2017Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentationscited by 620
  9. 2019ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networkscited by 575
  10. 2021The RSNA-ASNR-MICCAI BraTS 2021 Benchmark on Brain Tumor Segmentation and Radiogenomic Classificationcited by 518
  11. 2018Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challengecited by 511
  12. 2022MONAI: An open-source framework for deep learning in healthcarecited by 448
  13. 2019Selective Kernel Networkscited by 403
  14. 2017Deep Learning for Medical Image Analysiscited by 401
  15. 2019A large annotated medical image dataset for the development and evaluation of segmentation algorithmscited by 373
  16. 2017Road Extraction by Deep Residual U-Netcited by 333
  17. 2019GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyondcited by 331
  18. 2019Med3D: Transfer Learning for 3D Medical Image Analysiscited by 288
  19. 2018Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networkscited by 280
  20. 2018Attention Gated Networks: Learning to Leverage Salient Regions in Medical Imagescited by 272
  21. 2021TransBTS: Multimodal Brain Tumor Segmentation Using Transformercited by 265
  22. 2016Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentationcited by 263
  23. 2019ResUNet-a: a deep learning framework for semantic segmentation of remotely sensed datacited by 261
  24. 2021TransFuse: Fusing Transformers and CNNs for Medical Image Segmentationcited by 258
  25. 2021Coordinate Attention for Efficient Mobile Network Designcited by 241
  26. 2017Tversky loss function for image segmentation using 3D fully convolutional deep networkscited by 228
  27. 2018A Novel Focal Tversky loss function with improved Attention U-Net for lesion segmentationcited by 172
  28. 2016Unsupervised domain adaptation in brain lesion segmentation with adversarial networkscited by 125
  29. 2019Reducing the Hausdorff Distance in Medical Image Segmentation with Convolutional Neural Networkscited by 116
  30. 2019Spatial Group-wise Enhance: Improving Semantic Feature Learning in Convolutional Networkscited by 33

Built on by

Not cited yet.