超声图像中的乳腺肿瘤分割是定量分析的基础，在乳腺癌的诊断和治疗中发挥着至关重要的作用。最近，现有的方法主要集中在空间域实现，而很少关注频域。在本文中，我们提出了一种多频率和多尺度交互式 CNN-Transformer 混合网络（MFMSNet）。具体来说，我们利用 Octave 卷积代替传统卷积来有效分离高频和低频分量，同时降低计算复杂度。引入多频变压器块（MF-Trans）可以实现高频和低频信息之间的高效交互，从而捕获远程依赖性。此外，我们采用多尺度交互式融合模块（MSIF）来合并不同尺寸的高频特征图，通过整合局部上下文信息来增强对肿瘤边缘的强调。实验结果证明，我们的 MFMSNet 在两个公开的乳腺超声数据集和一个甲状腺超声数据集上优于七种最先进的方法。在MFMSNet的评估中，在BUSI、BUI和DDTI数据集上进行了测试，各自的测试集中包含130张图像（BUSI）、47张图像（BUI）和128张图像（DDTI）。采用五重交叉验证方法，获得的骰子系数如下：83.42％（BUSI）、90.79％（BUI）和79.96％（DDTI）。该代码可在 https://github.com/wrc990616/MFMSNet 上获取。版权所有 © 2024 Elsevier Ltd。保留所有权利。

Breast tumor segmentation in ultrasound images is fundamental for quantitative analysis and plays a crucial role in the diagnosis and treatment of breast cancer. Recently, existing methods have mainly focused on spatial domain implementations, with less attention to the frequency domain. In this paper, we propose a Multi-frequency and Multi-scale Interactive CNN-Transformer Hybrid Network (MFMSNet). Specifically, we utilize Octave convolutions instead of conventional convolutions to effectively separate high-frequency and low-frequency components while reducing computational complexity. Introducing the Multi-frequency Transformer block (MF-Trans) enables efficient interaction between high-frequency and low-frequency information, thereby capturing long-range dependencies. Additionally, we incorporate Multi-scale interactive fusion module (MSIF) to merge high-frequency feature maps of different sizes, enhancing the emphasis on tumor edges by integrating local contextual information. Experimental results demonstrate the superiority of our MFMSNet over seven state-of-the-art methods on two publicly available breast ultrasound datasets and one thyroid ultrasound dataset. In the evaluation of MFMSNet, tests were conducted on the BUSI, BUI, and DDTI datasets, comprising 130 images (BUSI), 47 images (BUI), and 128 images (DDTI) in the respective test sets. Employing a five-fold cross-validation approach, the obtained dice coefficients are as follows: 83.42 % (BUSI), 90.79 % (BUI), and 79.96 % (DDTI). The code is available at https://github.com/wrc990616/MFMSNet.Copyright © 2024 Elsevier Ltd. All rights reserved.