Similarity Memory Prior is All You Need for Medical Image Segmentation

TL;DR

This paper introduces Sim-MPNet, a novel medical image segmentation network that leverages a similarity memory prior and dynamic attention mechanisms to improve accuracy by capturing subtle texture differences.

Contribution

The paper proposes a new Similarity Memory Prior Network with dynamic memory updates and internal feature enhancement modules for improved medical image segmentation.

Findings

Outperforms state-of-the-art methods on four datasets.

Effectively captures subtle texture differences.

Demonstrates robustness across diverse medical imaging tasks.

Abstract

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.