提出硬空间门控机制，解决脑转移瘤分割中高灵敏度低精度的难题。
Hard Spatial Gating for Precision-Driven Brain Metastasis Segmentation: Addressing the Over-Segmentation Paradox in Deep Attention Networks
- 采用硬空间门控替代软注意力，严格抑制背景噪声
- 边界精度提升3倍，95%豪斯多夫距离降至56.13毫米
- 参数量仅0.67M，适合资源受限环境部署
脑转移瘤的MRI分割因病灶尺寸小（5-15毫米）和极端类别不平衡（肿瘤体积<2%）而极具挑战。尽管软注意力CNN广泛应用，但存在“过度分割悖论”：模型灵敏度高（召回率>0.88），但精确率惨跌至<0.23，边界误差超150毫米，严重影响立体定向放射外科规划。为此，本文提出空间门控网络（SG-Net），一种以精度为先的架构，采用硬空间门控机制。与传统软注意力不同，SG-Net强制特征选择，强力抑制背景伪影同时保留肿瘤特征。在Brain-Mets-Lung-MRI数据集（n=92）上验证，SG-Net获得Dice相似系数0.5578±0.0243（95%置信区间：0.45-0.67），显著优于Attention U-Net（p<0.001）和ResU-Net（p<0.001）。最关键的是，边界精度提升三倍，95%豪斯多夫距离由Attention U-Net的157.52毫米降至56.13毫米，同时保持良好召回率（0.79）和优越精确率（0.52对比0.20）。此外，SG-Net仅需0.67M参数（比Attention U-Net少8.8倍），便于在资源受限场景部署。这些结果确立了硬空间门控在精准病变检测中的稳健性，直接提升放疗精度。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。