Cross-modal medical image segmentation presents a significant challenge, as different imaging modalities produce images with varying resolutions, contrasts, and appearances of anatomical structures. We introduce compositionality as an inductive bias in a cross-modal segmentation network to improve segmentation performance and interpretability while reducing complexity. The proposed network is an end-to-end cross-modal segmentation framework that enforces compositionality on the learned representations using learnable von Mises-Fisher kernels. These kernels facilitate content-style disentanglement in the learned representations, resulting in compositional content representations that are inherently interpretable and effectively disentangle different anatomical structures. The experimental results demonstrate enhanced segmentation performance and reduced computational costs on multiple medical datasets. Additionally, we demonstrate the interpretability of the learned compositional features. Code and checkpoints will be publicly available at: https://github.com/Trustworthy-AI-UU-NKI/Cross-Modal-Segmentation.
@article{arxiv.2408.11733,
title = {Enhancing Cross-Modal Medical Image Segmentation through Compositionality},
author = {Aniek Eijpe and Valentina Corbetta and Kalina Chupetlovska and Regina Beets-Tan and Wilson Silva},
journal= {arXiv preprint arXiv:2408.11733},
year = {2024}
}
Comments
11 pages, 3 figures, 2 tables. Accepted at Deep Generative Models workshop @ MICCAI 2024 (DGM4MICCAI). This is the submitted manuscript with added link to github repo, funding acknowledgements and authors' names and affiliations. No further post submission improvements or corrections were integrated. Final version not published yet