AI 中文总结
研究旨在解决非增强CT中脑卒病变分割难题。提出FSB-Net，利用频域分析，含小波边界检测头、频率-空间交叉注意力模块和频谱边界损失。在公共数据集上评估，性能优于多种方法，达当前最佳。
AI 中文摘要
在非增强计算机断层扫描（NCCT）中准确分割脑卒病变对于快速临床决策至关重要，但由于病变与正常脑组织之间的对比度低、缺血性和出血性亚型的病变形态异质性以及部分容积效应导致的边界模糊，分割仍然很困难。当前的深度学习方法主要优化区域级重叠，但缺乏明确的边界建模，导致描绘不准确，影响体积评估和治疗计划。我们提出了FSB-Net，一种频率-空间边界网络，利用频域分析进行边界感知的脑卒病变分割。FSB-Net引入了三个组件：小波边界检测头（WBDH），它将离散小波变换应用于多尺度编码器特征，提取高频子带作为边界表示；频率-空间交叉注意力模块（FSCAM），它在小波边界特征和空间解码器特征之间进行双向注意力，以选择性地增强边界；以及频谱边界损失，它惩罚傅里叶域中的高频差异，以优化边界清晰度。基于PVTv2-B2编码器构建，FSB-Net在包含缺血性和出血性病例的公共脑卒CT数据集上进行了评估。实验结果表明，FSB-Net在所有指标上均优于U-Net、UNet++、MANet和DeepLabV3+，在平均Dice、平均IoU和HD95方面达到了当前的最佳性能。
英文摘要
Accurate segmentation of brain stroke lesions in non-contrast computed tomography (NCCT) scans is critical for rapid clinical decision-making, yet remains difficult due to the low contrast between lesion and normal brain tissue, heterogeneous lesion morphology across ischemic and hemorrhagic subtypes, and ambiguous boundaries caused by partial volume effects. Current deep learning approaches primarily optimize region-level overlap but lack explicit boundary modeling, leading to imprecise delineation that can affect volumetric assessment and treatment planning. We propose FSB-Net, a frequency-spatial boundary network that leverages frequency-domain analysis for boundary-aware stroke lesion segmentation. FSB-Net introduces three components: (i) a Wavelet Boundary Detection Head (WBDH) that applies the discrete wavelet transform to multi-scale encoder features, extracting high-frequency sub-bands as boundary representations; (ii) a Frequency-Spatial Cross-Attention Module (FSCAM) that performs bidirectional attention between wavelet boundary features and spatial decoder features for selective boundary enhancement; and (iii) a Spectral Boundary Loss that penalizes high-frequency discrepancies in the Fourier domain to optimize boundary sharpness. Built on a PVTv2-B2 encoder, FSB-Net is evaluated on a public Brain Stroke CT dataset containing both ischemic and hemorrhagic cases. Experimental results show that FSB-Net outperforms U-Net, UNet++, MANet, and DeepLabV3+ across all metrics, achieving state-of-the-art performance in mean Dice, mean IoU, and HD95.
