用可学习的去卷积技术替代注意力机制，提升医学图像分割精度与效率
Deconver: A Deconvolutional Network for Medical Image Segmentation
- 在U型结构中引入可反向传播的非负去卷积层，替代昂贵注意力模块
- 在4个数据集上达到最优Dice分数，同时计算量降低最高达90%
- 适合资源受限场景下的高精度医学图像分割任务
尽管卷积神经网络（CNN）和视觉变换器（ViTs）推动了医学图像分割的发展，但各自存在固有局限：CNN受局部感受野限制，而ViTs计算复杂度高。本文提出Deconver，一种将传统图像恢复中的去卷积技术作为核心可学习组件的新型网络，嵌入到U型架构中。Deconver以高效的非负去卷积（NDC）操作替代计算成本高昂的注意力机制，实现高频细节恢复并抑制伪影。关键创新包括基于可证明单调更新规则的可反向传播NDC层，以及参数高效设计。在涵盖2D与3D分割任务的四个数据集（ISLES'22、BraTS'23、GlaS、FIVES）上评估，Deconver在Dice分数和豪斯多夫距离上均达到当前最优表现，同时相比领先基线将计算量（FLOPs）降低高达90%。该工作通过连接传统图像恢复与深度学习，为资源受限临床环境提供了高精度分割的实用方案。项目地址：https://github.com/pashtari/deconver。
原文摘要 · Abstract (English)
While convolutional neural networks (CNNs) and vision transformers (ViTs) have advanced medical image segmentation, they face inherent limitations such as local receptive fields in CNNs and high computational complexity in ViTs. This paper introduces Deconver, a novel network that integrates traditional deconvolution techniques from image restoration as a core learnable component within a U-shaped architecture. Deconver replaces computationally expensive attention mechanisms with efficient nonnegative deconvolution (NDC) operations, enabling the restoration of high-frequency details while suppressing artifacts. Key innovations include a backpropagation-friendly NDC layer based on a provably monotonic update rule and a parameter-efficient design. Evaluated across four datasets (ISLES'22, BraTS'23, GlaS, FIVES) covering both 2D and 3D segmentation tasks, Deconver achieves state-of-the-art performance in Dice scores and Hausdorff distance while reducing computational costs (FLOPs) by up to 90% compared to leading baselines. By bridging traditional image restoration with deep learning, this work offers a practical solution for high-precision segmentation in resource-constrained clinical workflows. The project is available at https://github.com/pashtari/deconver.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。