中文

通过组成性增强跨模态医学图像分割

计算机视觉与模式识别 2024-08-22 v1

摘要

跨模态医学图像分割是一个显著的挑战,因为不同成像模态产生的图像在分辨率、对比度和解剖结构外观上存在差异。我们在跨模态分割网络中引入组成性作为一种归纳偏置,以提高分割性能和可解释性,同时降低复杂性。该提议网络是一个端到端的跨模态分割框架,通过可学习的 von Mises-Fisher 核在所学表示上强制执行组成性。这些核 facilitate 所学表示中的内容-风格解耦, resulting in 具有组成性的内容表示,这些表示本身具有可解释性并且有效地解耦不同的解剖结构。实验结果表明,在多个医学数据集上实现了增强的分割性能和降低的计算成本。此外,我们展示了所学组成特征的可解释性。代码和检查点将在 https://github.com/Trustworthy-AI-UU-NKI/Cross-Modal-Segmentation 上公开。

关键词

引用

@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}
}

备注

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