Disentanglement of Biological and Technical Factors via Latent Space Rotation in Clinical Imaging Improves Disease Pattern Discovery
This work addresses the challenge of disentangling biological and technical factors in multi-center clinical imaging data to improve biomarker discovery, representing a domain-specific incremental advance.
The paper tackled the problem of domain shifts in medical imaging due to technical factors, which impede disease pattern discovery, and introduced a latent space rotation method that improved cluster consistency by up to 19.01% and enhanced survival prediction in idiopathic pulmonary fibrosis patients.
Identifying new disease-related patterns in medical imaging data with the help of machine learning enlarges the vocabulary of recognizable findings. This supports diagnostic and prognostic assessment. However, image appearance varies not only due to biological differences, but also due to imaging technology linked to vendors, scanning- or re- construction parameters. The resulting domain shifts impedes data representation learning strategies and the discovery of biologically meaningful cluster appearances. To address these challenges, we introduce an approach to actively learn the domain shift via post-hoc rotation of the data latent space, enabling disentanglement of biological and technical factors. Results on real-world heterogeneous clinical data showcase that the learned disentangled representation leads to stable clusters representing tissue-types across different acquisition settings. Cluster consistency is improved by +19.01% (ARI), +16.85% (NMI), and +12.39% (Dice) compared to the entangled representation, outperforming four state-of-the-art harmonization methods. When using the clusters to quantify tissue composition on idiopathic pulmonary fibrosis patients, the learned profiles enhance Cox survival prediction. This indicates that the proposed label-free framework facilitates biomarker discovery in multi-center routine imaging data. Code is available on GitHub https://github.com/cirmuw/latent-space-rotation-disentanglement.