提出双语义感知网络，提升超声视频分割抗噪能力
Dual Semantic-Aware Network for Noise Suppressed Ultrasound Video Segmentation
- 通过帧间语义关联与局部全局特征融合，增强噪声下分割鲁棒性
- 在4个数据集上超越现有方法，平均Dice达0.872，且推理速度更快
- 适合医学图像分割场景，尤其适用于低质量超声视频处理
超声成像因其简便无创被广泛应用，但其固有特性常引入大量噪声，给超声视频序列中病灶或器官的自动分割带来挑战。为此，本文提出双语义感知网络（DSANet），通过建立局部与全局特征间的相互语义感知，提升模型对噪声的鲁棒性。具体地，设计相邻帧语义感知模块（AFSA），构建通道级相似矩阵，在不依赖像素级关系的前提下实现帧间特征融合，有效抑制随机噪声。同时提出局部-全局语义感知模块（LGSA），将独立于每帧的空间细节特征（局部）与融合邻近帧时序上下文的条件全局特征进行重组与融合，形成多层级语义表示，显著增强抗干扰能力。在四个基准数据集上的广泛评估表明，DSANet在分割精度上显著优于当前最优方法，平均Dice系数达0.872；由于避免了像素级特征依赖，推理帧率（FPS）远高于主流视频方法，甚至超过部分图像基模型。代码已开源。
原文摘要 · Abstract (English)
Ultrasound imaging is a prevalent diagnostic tool known for its simplicity and non-invasiveness. However, its inherent characteristics often introduce substantial noise, posing considerable challenges for automated lesion or organ segmentation in ultrasound video sequences. To address these limitations, we propose the Dual Semantic-Aware Network (DSANet), a novel framework designed to enhance noise robustness in ultrasound video segmentation by fostering mutual semantic awareness between local and global features. Specifically, we introduce an Adjacent-Frame Semantic-Aware (AFSA) module, which constructs a channel-wise similarity matrix to guide feature fusion across adjacent frames, effectively mitigating the impact of random noise without relying on pixel-level relationships. Additionally, we propose a Local-and-Global Semantic-Aware (LGSA) module that reorganizes and fuses temporal unconditional local features, which capture spatial details independently at each frame, with conditional global features that incorporate temporal context from adjacent frames. This integration facilitates multi-level semantic representation, significantly improving the model's resilience to noise interference. Extensive evaluations on four benchmark datasets demonstrate that DSANet substantially outperforms state-of-the-art methods in segmentation accuracy. Moreover, since our model avoids pixel-level feature dependencies, it achieves significantly higher inference FPS than video-based methods, and even surpasses some image-based models. Code can be found in \href{https://github.com/ZhouL2001/DSANet}{DSANet}
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。