Nguyen Thi-Nhu-Quynh, Ho Quang-Huy, Nguyen Van Quang, Pham Van-Truong, Tran Thi-Thao
Department of Automation Engineering, School of Electrical and Electronic Engineering, Hanoi University of Science and Technology, Vietnam.
Biomed Phys Eng Express. 2025 Jun 9;11(4). doi: 10.1088/2057-1976/adde66.
Medical image segmentation is becoming a growing crucial step in assisting with disease detection and diagnosis. However, medical images often exhibit complex structures and textures, resulting in the need for highly complex methods. Particularly, when Deep Learning methods are utilized, they often require large-scale pretraining, leading to significant memory demands and increased computational costs. The well-known Convolutional Neural Networks (CNNs) have become the backbone of medical image segmentation tasks thanks to their effective feature extraction abilities. However, they often struggle to capture global context due to the limited sizes of their kernels. To address this, various Transformer-based models have been introduced to learn long-range dependencies through self-attention mechanisms. However, these architectures typically incur relatively high computational complexity.To address the aforementioned challenges, we propose a lightweight and computationally efficient model named ADC-MambaNet, which combines the conventional Depthwise Convolutional layers with the Mamba algorithm that can address the computational complexity of Transformers. In the proposed model, a new feature extractor named Harmonious Mamba-Convolution (HMC) block, and the Multi-Dimensional Priority Attention (MDPA) block have been designed. These blocks enhance the feature extraction process, thereby improving the overall performance of the model. In particular, the mechanisms enable the model to effectively capture local and global patterns from the feature maps while keeping the computational costs low. A novel loss function called the Balanced Normalized Cross Entropy is also introduced, bringing promising performance compared to other losses.Evaluations on five public medical image datasets: ISIC 2018 Lesion Segmentation, PH2, Data Science Bowl 2018, GlaS, and Lung x-ray demonstrate that ADC-MambaNet achieves higher evaluation scores while maintaining a compact parameters and low computational complexity.ADC-MambaNet offers a promising solution for accurate and efficient medical image segmentation, especially in resource-limited or edge-computing environments. Implementation code will be publicly accessible at:https://github.com/nqnguyen812/mambaseg-model.
医学图像分割正日益成为辅助疾病检测和诊断的关键步骤。然而，医学图像往往呈现出复杂的结构和纹理，这就需要高度复杂的方法。特别是在使用深度学习方法时，它们通常需要大规模的预训练，从而导致巨大的内存需求和计算成本的增加。著名的卷积神经网络（CNN）由于其有效的特征提取能力，已成为医学图像分割任务的支柱。然而，由于其内核尺寸有限，它们往往难以捕捉全局上下文。为了解决这个问题，人们引入了各种基于Transformer的模型，通过自注意力机制来学习长距离依赖关系。然而，这些架构通常会带来相对较高的计算复杂度。为了应对上述挑战，我们提出了一种名为ADC-MambaNet的轻量级且计算高效的模型，它将传统的深度卷积层与能够解决Transformer计算复杂度的Mamba算法相结合。在所提出的模型中，设计了一种名为和谐Mamba卷积（HMC）块的新特征提取器和多维优先级注意力（MDPA）块。这些块增强了特征提取过程，从而提高了模型的整体性能。特别是，这些机制使模型能够在保持计算成本较低的同时，有效地从特征图中捕捉局部和全局模式。还引入了一种名为平衡归一化交叉熵的新型损失函数，与其他损失相比，它具有良好的性能。对五个公共医学图像数据集（ISIC 2018病变分割、PH2、2018年数据科学碗、GlaS和肺部X光）的评估表明，ADC-MambaNet在保持紧凑参数和低计算复杂度的同时，实现了更高的评估分数。ADC-MambaNet为准确高效的医学图像分割提供了一个有前景的解决方案，特别是在资源有限或边缘计算环境中。实现代码将在以下网址公开获取：https://github.com/nqnguyen812/mambaseg-model。
