X-ray transferable polyrepresentation learning

TL;DR

This paper introduces a novel polyrepresentation approach that combines multiple feature representations from different sources to improve X-ray image analysis and demonstrates its transferability to smaller datasets, enhancing generalization.

Contribution

The paper proposes a new polyrepresentation method that integrates diverse feature sources for X-ray images and shows its transferability to smaller datasets, advancing feature extraction techniques.

Findings

Polyrepresentation improves performance over single representations.

Transferability of polyrepresentation to smaller datasets is effective.

Versatility of the approach across different domains is demonstrated.

Abstract

The success of machine learning algorithms is inherently related to the extraction of meaningful features, as they play a pivotal role in the performance of these algorithms. Central to this challenge is the quality of data representation. However, the ability to generalize and extract these features effectively from unseen datasets is also crucial. In light of this, we introduce a novel concept: the polyrepresentation. Polyrepresentation integrates multiple representations of the same modality extracted from distinct sources, for example, vector embeddings from the Siamese Network, self-supervised models, and interpretable radiomic features. This approach yields better performance metrics compared to relying on a single representation. Additionally, in the context of X-ray images, we demonstrate the transferability of the created polyrepresentation to a smaller dataset, underscoring its potential as a pragmatic and resource-efficient approach in various image-related solutions. It is worth noting that the concept of polyprepresentation on the example of medical data can also be applied to other domains, showcasing its versatility and broad potential impact.