Wang Xian, Zeng Wenzhi, Xu Junzeng, Zhang Senhao, Gu Yuexing, Li Benhui, Wang Xueyang
Attending Physician of Health Management Institute, The Second Medical Center and National Clinical Research Center for Geriatric Diseases, Chinese PLA General Hospital, Beijing, China.
Group of Agricultural High-Efficiency Water Management and Artificial Intelligence, College of Agricultural Science and Engineering, Hohai University, Nanjing, Jiangsu, China.
Front Oncol. 2025 May 13;15:1563959. doi: 10.3389/fonc.2025.1563959. eCollection 2025.
This paper introduces a novel lightweight MM-3DUNet (Multi-task Mobile 3D UNet) network designed for efficient and accurate segmentation of breast cancer tumors masses from MRI images, which leverages depth-wise separable convolutions, channel expansion units, and auxiliary classification tasks to enhance feature representation and computational efficiency.
We propose a 3D depth-wise separable convolution, and construct channel expansional convolution (CEC) unit and inverted residual block (IRB) to reduce the parameter count and computational load, making the network more suitable for use in resource-constrained environments. In addition, an auxiliary classification task (ACT) is introduced in the proposed architecture to provide additional supervisory signals for the main task of segmentation. The network architecture features a contracting path for downsampling and an expanding path for precise localization, enhanced by skip connections that integrate multi-level semantic information.
The network was evaluated using a dataset of Dynamic Contrast Enhanced MRI (DCE-MRI) breast cancer images, and the results show that compared to the classical 3DU-Net, MM-3DUNet could significantly reduce model parameters by 63.16% and computational demands by 80.90%, while increasing segmentation accuracy by 1.30% in IoU (Intersection over Union).
MM-3DUNet offers a substantial reduction in computational requirements of breast cancer mass segmentation network. This network not only enhances diagnostic precision but also supports deployment in diverse clinical settings, potentially improving early detection and treatment outcomes for breast cancer patients.
本文介绍了一种新型的轻量级MM - 3DUNet（多任务移动3D U-Net）网络，该网络旨在从MRI图像中高效、准确地分割乳腺癌肿瘤肿块，它利用深度可分离卷积、通道扩展单元和辅助分类任务来增强特征表示和计算效率。
我们提出了一种3D深度可分离卷积，并构建通道扩展卷积（CEC）单元和倒置残差块（IRB）以减少参数数量和计算量，使网络更适合在资源受限的环境中使用。此外，在所提出的架构中引入了辅助分类任务（ACT），以为分割的主要任务提供额外的监督信号。该网络架构具有用于下采样的收缩路径和用于精确定位的扩展路径，并通过集成多级语义信息的跳跃连接得到增强。
使用动态对比增强MRI（DCE - MRI）乳腺癌图像数据集对该网络进行了评估，结果表明，与经典的3D U-Net相比，MM - 3DUNet可以显著减少63.16%的模型参数和80.90%的计算需求，同时在交并比（IoU）方面将分割准确率提高1.30%。
MM - 3DUNet大幅降低了乳腺癌肿块分割网络的计算需求。该网络不仅提高了诊断精度，还支持在各种临床环境中部署，有可能改善乳腺癌患者的早期检测和治疗效果。
