|国家预印本平台
首页|Similarity Memory Prior is All You Need for Medical Image Segmentation

Similarity Memory Prior is All You Need for Medical Image Segmentation

Similarity Memory Prior is All You Need for Medical Image Segmentation

来源:Arxiv_logoArxiv
英文摘要

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.

Tang Hao、Guo ZhiQing、Wang LieJun、Liu Chao

医学研究方法基础医学

Tang Hao,Guo ZhiQing,Wang LieJun,Liu Chao.Similarity Memory Prior is All You Need for Medical Image Segmentation[EB/OL].(2025-07-03)[2025-07-09].https://arxiv.org/abs/2507.00585.点此复制

评论