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

TL;DR

This paper introduces GEMINI, a novel dense contrastive learning method for medical images that incorporates a homeomorphism prior to improve correspondence accuracy and reduce false positives and negatives.

Contribution

The paper proposes a deformable homeomorphism learning approach and a geometric semantic similarity measure to enhance dense contrastive learning in medical imaging.

Findings

Outperforms existing methods on seven datasets

Effectively reduces false positive and negative pairs

Improves learning efficiency and representation quality

Abstract

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.