Dong Tian-Feng, Zhou Chang-Jiang, Huang Zhen-Yi, Zhao Hao, Wang Xue-Long, Yan Shi-Ju
School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai, China.
Department of Ultrasound, Jinan City People's Hospital, People's Hospital Affiliated to Shandong First Medical University, Jinan, Shandong, China.
Comput Assist Surg (Abingdon). 2025 Dec;30(1):2523266. doi: 10.1080/24699322.2025.2523266. Epub 2025 Jun 28.
Breast and thyroid cancers are among the most prevalent and fastest growing malignancies worldwide with ultrasound imaging serving as the primary modality for screening and surgical navigation of these lesions. Accurate and real-time lesion segmentation in ultrasound images is crucial for guiding precise needle placement during biopsies and surgeries. To address this clinical need, we propose , a deep learning model for automatic segmentation of breast tumors and thyroid nodules in ultrasound images. MLP-UNet adopts an encoder-decoder architecture with a U-shaped structure and integrates a MLP-based module(MAP) module within the encoder stage. Attention module is a lightweight employed during the skip connections to enhance feature representation. Using only using 33.75 M parameters, MLP-UNet achieves state-of-the-art segmentation performance. On the BUSI, it attains Dice, IoU, and Recall of 80.61%, 67.93%, and 80.48%, respectively. And on the DDTI, it attains Dice, IoU, and Recall of 81.67% for Dice, 71.72%. These results outperform several classical and state-of-the-art segmentation networks while maintaining low computational complexity, highlighting its significant potential for clinical application in ultrasound-guided surgical navigation systems.
乳腺癌和甲状腺癌是全球最常见且增长最快的恶性肿瘤之一，超声成像作为这些病变筛查和手术导航的主要方式。超声图像中准确且实时的病变分割对于在活检和手术期间指导精确的针穿刺至关重要。为满足这一临床需求，我们提出了一种用于超声图像中乳腺肿瘤和甲状腺结节自动分割的深度学习模型。MLP-UNet采用具有U形结构的编码器-解码器架构，并在编码器阶段集成了基于MLP的模块（MAP模块）。注意力模块是在跳跃连接期间使用的轻量级模块，以增强特征表示。MLP-UNet仅使用3375万个参数，就实现了领先的分割性能。在BUSI数据集上，它的Dice系数、交并比和召回率分别达到80.61%、67.93%和80.48%。在DDTI数据集上，其Dice系数达到81.67%，交并比达到71.72%。这些结果优于几个经典的和领先的分割网络，同时保持了低计算复杂度，突出了其在超声引导手术导航系统中临床应用的巨大潜力。
