文献速递乳腺US

交互融合全局与局部特征用于乳腺超声图像良恶性分类

Interactively Fusing Global and Local Features for Benign and Malignant Classification of Breast Ultrasound Images.
PubMed 文献 · Ultrasound Med Biol · 2024-12-20

本研究提出CTMF-Net深度学习网络,通过CNN分支与Transformer分支的多阶段特征交互融合进行乳腺超声图像良恶性分类。在SYSU和UDIAT数据集内部验证准确率分别为90.14±0.58%和92.04±4.90%,优于其他先进网络(p<0.05);在BUSI外部验证中,基于SYSU训练时AUC为0.8704,较次优方法提高0.0126,基于UDIAT训练时AUC为0.8505,较次优方法提高0.0130。

要点

  • CTMF-Net在SYSU内部验证准确率达90.14±0.58%,优于其他先进网络(p<0.05)。
  • BUSI外部验证中,SYSU训练模型AUC为0.8704,较次优方法提高0.0126。
  • UDIAT训练模型外部验证AUC为0.8505,较次优方法提高0.0130。

核心结论

  • CTMF-Net优于所有现有方法,可有效辅助医生实现更准确的乳腺肿瘤分类性能。

研究设计与样本

  • 研究提出CNN与Transformer多阶段融合网络CTMF-Net,CNN分支以视觉几何组为骨干,Transformer分支以ViT为基础网络,两分支各分四阶段,每阶段末通过特征交互模块融合,CNN分支每阶段后使用卷积块注意力模块增强特征;在SYSU、UDIAT和BUSI三个公开乳腺超声数据集上与多种先进深度学习方法进行大量实验。

诊断标准与关键数值

  • SYSU内部验证准确率90.14±0.58%,UDIAT内部验证准确率92.04±4.90%,均优于其他先进网络(p<0.05)。
  • BUSI外部验证:基于SYSU训练时AUC 0.8704,较次优视觉几何组注意力ViT方法提高0.0126。
  • BUSI外部验证:基于UDIAT训练时AUC 0.8505,较次优全局上下文ViT方法提高0.0130。

临床应用与阅片要点

  • 作者认为CTMF-Net可有效辅助医生实现更准确的乳腺肿瘤分类性能。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

OBJECTIVE: Breast ultrasound (BUS) is used to classify benign and malignant breast tumors, and its automatic classification can reduce subjectivity. However, current convolutional neural networks (CNNs) face challenges in capturing global features, while vision transformer (ViT) networks have limitations in effectively extracting local features. Therefore, this study aimed to develop a deep learning method that enables the interaction and updating of intermediate features between CNN and ViT to achieve high-accuracy BUS image classification.

METHODS: This study introduced the CNN and transformer multi-stage fusion network (CTMF-Net) consisting of two branches: a CNN branch and a transformer branch. The CNN branch employs visual geometry group as its backbone, while the transformer branch utilizes ViT as its base network. Both branches were divided into four stages. At the end of each stage, a proposed feature interaction module facilitated feature interaction and fusion between the two branches. Additionally, the convolutional block attention module was employed to enhance relevant features after each stage of the CNN branch. Extensive experiments were conducted using various state-of-the-art deep-learning classification methods on three public breast ultrasound datasets (SYSU, UDIAT and BUSI).

RESULTS: For the internal validation on SYSU and UDIAT, our proposed method CTMF-Net achieved the highest accuracy of 90.14 ± 0.58% on SYSU and 92.04 ± 4.90% on UDIAT, which showed superior classification performance over other state-of-art networks (p < 0.05). Additionally, for external validation on BUSI, CTMF-Net showed outstanding performance, achieving the highest area under the curve score of 0.8704 when trained on SYSU, marking a 0.0126 improvement over the second-best visual geometry group attention ViT method. Similarly, when applied to UDIAT, CTMF-Net achieved an area under the curve score of 0.8505, surpassing the second-best global context ViT method by 0.0130.

CONCLUSION: Our proposed method, CTMF-Net, outperforms all existing methods and can effectively assist doctors in achieving more accurate classification performance of breast tumors.

来源:Ultrasound Med Biol,查看原文。版权归原作者所有。

引用

  1. Wang W, Zhou J, Zhao J, et al. Interactively Fusing Global and Local Features for Benign and Malignant Classification of Breast Ultrasound Images. Ultrasound Med Biol. 2024. PMID: 39709289. doi:10.1016/j.ultrasmedbio.2024.11.014

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。