医学图像密集对比表示学习中的假阳性和假阴性问题的同胚先验

Homeomorphism Prior for False Positive and Negative Problem in Medical Image Dense Contrastive Representation Learning

February 7, 2025

作者: Yuting He, Boyu Wang, Rongjun Ge, Yang Chen, Guanyu Yang, Shuo Li

cs.AI

摘要

密集对比表示学习（DCRL）极大地提高了图像密集预测任务的学习效率，展现了减少医学图像收集和密集标注成本的巨大潜力。然而，医学图像的特性使得不可靠的对应发现，带来了DCRL中大规模假阳性和假阴性（FP&N）对的一个开放问题。本文提出了嵌入同胚先验到DCRL中的GEoMetric vIsual deNse sImilarity（GEMINI）学习，实现了可靠的对应发现以进行有效的密集对比。我们提出了一种可变同胚学习（DHL），该方法对医学图像的同胚性进行建模，并学习估计可变形映射以预测像素的对应关系，同时保持拓扑性质。它有效地减少了配对的搜索空间，并通过梯度隐式地、柔性地学习负对。我们还提出了几何语义相似性（GSS），用于提取特征中的语义信息，以衡量对应关系学习的对齐程度。这将提升学习效率和变形性能，可靠地构建正对。我们在实验中对两个典型的表示学习任务实现了两种实用的变体。在七个数据集上取得的有希望的结果超过了现有方法，展示了我们的巨大优势。我们将在以下伴随链接上发布我们的代码：https://github.com/YutingHe-list/GEMINI。

English

Dense contrastive representation learning (DCRL) has greatly improved the learning efficiency for image-dense prediction tasks, showing its great potential to reduce the large costs of medical image collection and dense annotation. However, the properties of medical images make unreliable correspondence discovery, bringing an open problem of large-scale false positive and negative (FP&N) pairs in DCRL. In this paper, we propose GEoMetric vIsual deNse sImilarity (GEMINI) learning which embeds the homeomorphism prior to DCRL and enables a reliable correspondence discovery for effective dense contrast. We propose a deformable homeomorphism learning (DHL) which models the homeomorphism of medical images and learns to estimate a deformable mapping to predict the pixels' correspondence under topological preservation. It effectively reduces the searching space of pairing and drives an implicit and soft learning of negative pairs via a gradient. We also propose a geometric semantic similarity (GSS) which extracts semantic information in features to measure the alignment degree for the correspondence learning. It will promote the learning efficiency and performance of deformation, constructing positive pairs reliably. We implement two practical variants on two typical representation learning tasks in our experiments. Our promising results on seven datasets which outperform the existing methods show our great superiority. We will release our code on a companion link: https://github.com/YutingHe-list/GEMINI.