发表机构
Chalmers University of Technology（查尔姆斯理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
BATS是一种边界感知混合分辨率的3D医学图像分割架构，通过稀疏层次结构减少内存占用，在保持接近密集基线精度的同时降低GPU内存消耗，部分数据集上推理速度提升。
AI 中文摘要
许多高性能体分割模型维持密集的多尺度特征图，导致激活内存和推理成本较高。我们提出BATS（Boundary-Aware Token Selection，边界感知令牌选择），这是一种3D医学图像分割架构，在预测的类别边界附近集中高分辨率处理。密集边界预测器确定需要额外分辨率的位置，而先细后粗的上下文级联构建依赖于输入的混合分辨率层次结构。同质区域以粗粒度表示，边界、薄结构和小目标周围保留更精细的令牌。稀疏层次结构经过细化并光栅化为密集分割结果。BATS在每个分辨率级别独立预测边界相关性，防止错误的粗粒度决策抑制细粒度证据。父簇注意力进一步将分层祖先令牌注入局部注意力邻域，无需密集多尺度特征图或跨尺度邻域搜索即可提供跨尺度上下文。我们使用标准化的nnU-Net Revisited协议在五个公开CT和MRI数据集上评估BATS。BATS在对比方法中取得最高的LiTS Dice分数，且在五个数据集上的平均Dice分数与最强的密集基线MedNeXt-L仅相差0.37个百分点。相对于MedNeXt-L，它在KiTS、LiTS和BraTS上减少了53%以上的峰值已分配GPU内存。在保留令牌较少的KiTS和LiTS上，推理速度最高提升30%，但在令牌更密集的BraTS上速度较慢。因此，混合分辨率处理可实现稳定的内存节省，而运行时和精度增益则取决于数据集的边界密度。
英文摘要
Many high-performing volumetric segmentation models maintain dense multi-scale feature maps, leading to high activation memory and inference cost. We present BATS (Boundary-Aware Token Selection), a 3D medical image segmentation architecture that concentrates fine-resolution processing near predicted class boundaries. A dense boundary predictor identifies where additional resolution is needed, while a fine-first context cascade constructs an input-dependent mixed-resolution hierarchy. Homogeneous regions are represented coarsely, with finer tokens retained around boundaries, thin structures, and small targets. The sparse hierarchy is refined and rasterised into a dense segmentation. BATS predicts boundary relevance independently at every resolution level, preventing an erroneous coarse-scale decision from suppressing fine-scale evidence. Parent cluster attention further injects hierarchical ancestor tokens into local attention neighbourhoods, providing cross-scale context without dense multi-scale feature maps or cross-scale neighbour search. We evaluate BATS on five public CT and MRI datasets using the standardised nnU-Net Revisited protocol. BATS achieves the highest LiTS Dice among the compared methods and averages within 0.37 Dice points of the strongest dense baseline, MedNeXt-L, across the five datasets. Relative to MedNeXt-L, it reduces peak allocated GPU memory by more than 53% on KiTS, LiTS, and BraTS. Inference is up to 30% faster on KiTS and LiTS, which retain fewer tokens, but slower on the more token-dense BraTS. Mixed-resolution processing therefore provides consistent memory savings, while runtime and accuracy gains depend on dataset boundary density.
