分解与耦合显著性图用于超声图像中的病灶分割
Decomposing and Coupling Saliency Map for Lesion Segmentation in Ultrasound Images
AI总结：
本文提出DC-Net，通过分解-耦合子网解耦并融合前景背景显著性图，结合三种融合策略与谐波损失函数，有效解决超声图像病灶分割难题，性能显著优于现有方法。
摘要：
超声图像的复杂场景，即相邻组织（即背景）与病灶区域（即前景）具有相似的强度，甚至比病灶区域包含更丰富的纹理模式，为准确的病灶分割带来了独特的挑战。本文提出了一种分解-耦合网络（decomposition-coupling network），称为DC-Net，以（前景-背景）显著性图解耦-融合的方式应对这一挑战。DC-Net由分解子网和耦合子网组成，前者初步将原始图像解耦为前景和背景显著性图，后者在显著性先验融合的辅助下进行准确分割。耦合子网涉及三个方面的融合策略，包括：1）区域特征聚合（通过编码器中的可微上下文池化算子）以在降维过程中自适应地保留局部上下文细节，同时具有较大的感受野；2）关系感知表示融合（通过解码器中的互相关融合模块）以在分辨率恢复期间高效融合低级视觉特征和高级语义特征；3）依赖感知先验合并（通过耦合器）利用从背景表示中导出的互补信息来增强前景显著性表示。此外，引入了谐波损失函数，以鼓励网络将更多注意力集中在低置信度和困难样本上。所提出的方法在两个超声病灶分割任务上进行了评估，结果表明其性能比现有最先进的方法有显著提升。
英文摘要：
Complex scenario of ultrasound image, in which adjacent tissues (i.e., background) share similar intensity with and even contain richer texture patterns than lesion region (i.e., foreground), brings a unique challenge for accurate lesion segmentation. This work presents a decomposition-coupling network, called DC-Net, to deal with this challenge in a (foreground-background) saliency map disentanglement-fusion manner. The DC-Net consists of decomposition and coupling subnets, and the former preliminarily disentangles original image into foreground and background saliency maps, followed by the latter for accurate segmentation under the assistance of saliency prior fusion. The coupling subnet involves three aspects of fusion strategies, including: 1) regional feature aggregation (via differentiable context pooling operator in the encoder) to adaptively preserve local contextual details with the larger receptive field during dimension reduction; 2) relation-aware representation fusion (via cross-correlation fusion module in the decoder) to efficiently fuse low-level visual characteristics and high-level semantic features during resolution restoration; 3) dependency-aware prior incorporation (via coupler) to reinforce foreground-salient representation with the complementary information derived from background representation. Furthermore, a harmonic loss function is introduced to encourage the network to focus more attention on low-confidence and hard samples. The proposed method is evaluated on two ultrasound lesion segmentation tasks, which demonstrates the remarkable performance improvement over existing state-of-the-art methods.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
