ESDMR-Net：一种用于医学图像分割的带有扩张-压缩与双多尺度残差连接的轻量级网络
ESDMR-Net: A Lightweight Network With Expand-Squeeze and Dual Multiscale Residual Connections for Medical Image Segmentation
AI总结：
针对现有医学图像分割方法计算成本高的问题，提出带有扩张-压缩模块与双多尺度残差连接的轻量级全卷积网络ESDMR-Net，在参数量大幅降低的同时在7个数据集上取得最优分割效果。
摘要：
分割是包括医学图像分析在内的众多计算机视觉应用中的一项重要任务。近年来，基于复杂卷积神经网络架构的医学图像分割方法复杂度不断提升，这一进展使得这类方法在公认基准数据集上的性能得到了渐进式提升。然而，现有大多数方法计算需求极高，限制了其实际应用。\n本文提出了扩张-压缩双多尺度残差网络（ESDMR-Net），这是一种全卷积网络，特别适用于移动设备等资源受限的计算硬件。ESDMR-Net聚焦于多尺度特征提取，能够学习语义不同的特征之间的上下文依赖关系。ESDMR-Net的架构支持编码器-解码器对内部的双流信息传递。扩张操作（深度可分离卷积）将所有携带多尺度信息的丰富特征提供给压缩操作（瓶颈层），随后由压缩操作提取分割任务所需的必要信息。扩张-压缩（ES）模块帮助网络更多关注占比不足的类别，从而提升分割精度。为增强跨多种分辨率或尺度的信息流动，我们在跳跃连接中集成了双多尺度残差（DMR）模块。这种集成使得解码器能够获取不同抽象层级的特征，最终形成更全面的特征表示。\n我们在来自5种不同应用场景的7个数据集上开展了实验。我们的模型尽管可训练参数量大幅减少（减少了2个甚至3个数量级），仍取得了最优结果。
英文摘要：
Segmentation is an important task in a wide range of computer vision applications, including medical image analysis. Recent years have seen an increase in the complexity of medical image segmentation approaches based on sophisticated convolutional neural network architectures. This progress has led to incremental enhancements in performance on widely recognised benchmark datasets. However, most of the existing approaches are computationally demanding, which limits their practical applicability. This paper presents an expand-squeeze dual multiscale residual network (ESDMR-Net), which is a fully convolutional network that is particularly well-suited for resource-constrained computing hardware such as mobile devices. ESDMR-Net focuses on extracting multiscale features, enabling the learning of contextual dependencies among semantically distinct features. The ESDMR-Net architecture allows dual-stream information flow within encoder-decoder pairs. The expansion operation (depthwise separable convolution) makes all of the rich features with multiscale information available to the squeeze operation (bottleneck layer), which then extracts the necessary information for the segmentation task. The Expand-Squeeze (ES) block helps the network pay more attention to under-represented classes, which contributes to improved segmentation accuracy. To enhance the flow of information across multiple resolutions or scales, we integrated dual multiscale residual (DMR) blocks into the skip connection. This integration enables the decoder to access features from various levels of abstraction, ultimately resulting in more comprehensive feature representations. We present experiments on seven datasets from five distinct examples of applications. Our model achieved the best results despite having significantly fewer trainable parameters, with a reduction of two or even three orders of magnitude.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
