IEEE Trans Image Process. 2023;32:4842-4855. doi: 10.1109/TIP.2023.3304518. Epub 2023 Sep 1.
Breast tumor segmentation of ultrasound images provides valuable information of tumors for early detection and diagnosis. Accurate segmentation is challenging due to low image contrast between areas of interest; speckle noises, and large inter-subject variations in tumor shape and size. This paper proposes a novel Multi-scale Dynamic Fusion Network (MDF-Net) for breast ultrasound tumor segmentation. It employs a two-stage end-to-end architecture with a trunk sub-network for multiscale feature selection and a structurally optimized refinement sub-network for mitigating impairments such as noise and inter-subject variation via better feature exploration and fusion. The trunk network is extended from UNet++ with a simplified skip pathway structure to connect the features between adjacent scales. Moreover, deep supervision at all scales, instead of at the finest scale in UNet++, is proposed to extract more discriminative features and mitigate errors from speckle noise via a hybrid loss function. Unlike previous works, the first stage is linked to a loss function of the second stage so that both the preliminary segmentations and refinement subnetworks can be refined together at training. The refinement sub-network utilizes a structurally optimized MDF mechanism to integrate preliminary segmentation information (capturing general tumor shape and size) at coarse scales and explores inter-subject variation information at finer scales. Experimental results from two public datasets show that the proposed method achieves better Dice and other scores over state-of-the-art methods. Qualitative analysis also indicates that our proposed network is more robust to tumor size/shapes, speckle noise and heavy posterior shadows along tumor boundaries. An optional post-processing step is also proposed to facilitate users in mitigating segmentation artifacts. The efficiency of the proposed network is also illustrated on the "Electron Microscopy neural structures segmentation dataset". It outperforms a state-of-the-art algorithm based on UNet-2022 with simpler settings. This indicates the advantages of our MDF-Nets in other challenging image segmentation tasks with small to medium data sizes.
超声图像的乳腺肿瘤分割为早期检测和诊断提供了有价值的肿瘤信息。由于感兴趣区域之间的图像对比度低、斑点噪声以及肿瘤形状和大小的个体间差异较大，因此准确的分割具有挑战性。本文提出了一种用于乳腺超声肿瘤分割的新型多尺度动态融合网络（MDF-Net）。它采用两阶段端到端架构，主干子网用于多尺度特征选择，结构优化的细化子网用于通过更好的特征探索和融合来减轻噪声和个体间差异等干扰。主干网络是在 UNet++的基础上扩展而来的，具有简化的跳过路径结构，用于连接相邻尺度之间的特征。此外，与 UNet++不同，提出了在所有尺度上进行深度监督，而不是在最细尺度上进行监督，通过混合损失函数提取更具鉴别力的特征并减轻斑点噪声的误差。与以前的工作不同，第一阶段与第二阶段的损失函数相关联，以便在训练时可以一起细化初步分割和细化子网。细化子网利用结构优化的 MDF 机制在粗尺度上整合初步分割信息（捕获肿瘤的大致形状和大小），并在更细的尺度上探索个体间的变化信息。来自两个公共数据集的实验结果表明，该方法在 Dice 等分数上优于最先进的方法。定性分析还表明，我们提出的网络对肿瘤大小/形状、斑点噪声和肿瘤边界处较重的后影更具鲁棒性。还提出了一个可选的后处理步骤，以方便用户减轻分割伪影。该网络的效率也在“电子显微镜神经结构分割数据集”上得到了说明。它比基于 UNet-2022 的最先进算法具有更简单的设置，表现出更好的性能。这表明我们的 MDF-Nets 在其他具有中小数据量的具有挑战性的图像分割任务中具有优势。
