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

arXiv: https://arxiv.org/abs/2511.22606 · HTML: https://mlsanity.com/paper/2511.22606/

## 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 (most cited first, 30 of 42)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation](https://mlsanity.com/paper/2102.04306/) (2021)
- [Attention U-Net: Learning Where to Look for the Pancreas](https://mlsanity.com/paper/1804.03999/) (2018)
- [Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation](https://mlsanity.com/paper/2105.05537/) (2021)
- [A Survey on Deep Learning in Medical Image Analysis](https://mlsanity.com/paper/1702.05747/) (2017)
- [Dual Attention Network for Scene Segmentation](https://mlsanity.com/paper/1809.02983/) (2018)
- [Striving for Simplicity: The All Convolutional Net](https://mlsanity.com/paper/1412.6806/) (2014)
- [UNETR: Transformers for 3D Medical Image Segmentation](https://mlsanity.com/paper/2103.10504/) (2021)
- [Self-Attention Generative Adversarial Networks](https://mlsanity.com/paper/1805.08318/) (2018)
- [Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations](https://mlsanity.com/paper/1707.03237/) (2017)
- [ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks](https://mlsanity.com/paper/1910.03151/) (2019)
- [The RSNA-ASNR-MICCAI BraTS 2021 Benchmark on Brain Tumor Segmentation and Radiogenomic Classification](https://mlsanity.com/paper/2107.02314/) (2021)
- [Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge](https://mlsanity.com/paper/1811.02629/) (2018)
- [MONAI: An open-source framework for deep learning in healthcare](https://mlsanity.com/paper/2211.02701/) (2022)
- [Selective Kernel Networks](https://mlsanity.com/paper/1903.06586/) (2019)
- [Deep Learning for Medical Image Analysis](https://mlsanity.com/paper/1708.08987/) (2017)
- [A large annotated medical image dataset for the development and evaluation of segmentation algorithms](https://mlsanity.com/paper/1902.09063/) (2019)
- [Road Extraction by Deep Residual U-Net](https://mlsanity.com/paper/1711.10684/) (2017)
- [GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond](https://mlsanity.com/paper/1904.11492/) (2019)
- [Med3D: Transfer Learning for 3D Medical Image Analysis](https://mlsanity.com/paper/1904.00625/) (2019)

## 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.