用记忆相似性提升医学图像分割精度，无需复杂结构
Similarity Memory Prior is All You Need for Medical Image Segmentation
- 引入动态记忆权重注意力机制，记忆病变特征以捕捉细微纹理差异
- 在四个公开数据集上优于现有方法，显著提升小目标分割性能
- 适合研究医学图像分析、需要高精度分割的临床应用
近年来发现猕猴初级视觉皮层（V1）中的‘祖母细胞’可直接识别复杂形状的视觉输入，这启发我们探索其在医学图像分割中的价值。本文提出相似性记忆先验网络（Sim-MPNet），设计动态记忆权重-损失注意力（DMW-LA）机制，通过原型记忆库匹配并记忆特定病灶或器官的类别特征，帮助网络学习类别间细微纹理变化。该机制还通过权重-损失动态更新策略反向优化相似性记忆先验，有效促进类别特征直接提取。此外，提出双相似性全局内部增强模块（DS-GIM），利用余弦相似度与欧氏距离深入挖掘输入特征分布的内在差异。在四个公开数据集上的大量实验表明，Sim-MPNet的分割性能优于当前最优方法。代码已开源。
原文摘要 · Abstract (English)
In recent years, it has been found that "grandmother cells" in the primary visual cortex (V1) of macaques can directly recognize visual input with complex shapes. This inspires us to examine the value of these cells in promoting the research of medical image segmentation. In this paper, we design a Similarity Memory Prior Network (Sim-MPNet) for medical image segmentation. Specifically, we propose a Dynamic Memory Weights-Loss Attention (DMW-LA), which matches and remembers the category features of specific lesions or organs in medical images through the similarity memory prior in the prototype memory bank, thus helping the network to learn subtle texture changes between categories. DMW-LA also dynamically updates the similarity memory prior in reverse through Weight-Loss Dynamic (W-LD) update strategy, effectively assisting the network directly extract category features. In addition, we propose the Double-Similarity Global Internal Enhancement Module (DS-GIM) to deeply explore the internal differences in the feature distribution of input data through cosine similarity and euclidean distance. Extensive experiments on four public datasets show that Sim-MPNet has better segmentation performance than other state-of-the-art methods. Our code is available on https://github.com/vpsg-research/Sim-MPNet.
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。