通过相关性感知的条件特征编辑实现可解释的病理科特征可视化
Explainable Pathomics Feature Visualization via Correlation-aware Conditional Feature Editing
AI总结：
本文提出了一种Manifold-Aware Diffusion框架，通过正则化解耦潜在空间中的特征轨迹，实现可控且生物合理的细胞核编辑，提升病理科特征的可解释性与图像生成质量。
摘要：
病理科是一种最近的方法，提供了比黑箱深度学习更丰富的定量特征，支持在数字病理学中更具可重复性和可解释性的生物标志物。然而，许多衍生特征（例如“二阶矩”）仍然难以解释，尤其是在不同临床背景下，这限制了它们的实际应用。条件扩散模型通过特征编辑显示出可解释性的潜力，但它们通常假设特征独立性——这一假设被内在相关病理科特征所违反。因此，在编辑一个特征的同时固定其他特征可能会将模型推离生物流形并产生不真实的伪影。为了解决这个问题，我们提出了一种Manifold-Aware Diffusion（MAD）框架，用于可控且生物上合理的细胞核编辑。与现有方法不同，我们的方法在由变分自编码器（VAE）学习的解耦潜在空间中正则化了特征轨迹。这确保了操纵目标特征会自动调整相关属性，以保持在真实细胞学习的分布中。这些优化后的特征然后指导条件扩散模型合成高质量图像。实验表明，我们的方法在编辑这些特征时能够导航病理科特征的流形。所提出的方法在条件特征编辑方面优于基线方法，同时保持结构一致性。
英文摘要：
Pathomics is a recent approach that offers rich quantitative features beyond what black-box deep learning can provide, supporting more reproducible and explainable biomarkers in digital pathology. However, many derived features (e.g., "second-order moment") remain difficult to interpret, especially across different clinical contexts, which limits their practical adoption. Conditional diffusion models show promise for explainability through feature editing, but they typically assume feature independence**--**an assumption violated by intrinsically correlated pathomics features. Consequently, editing one feature while fixing others can push the model off the biological manifold and produce unrealistic artifacts. To address this, we propose a Manifold-Aware Diffusion (MAD) framework for controllable and biologically plausible cell nuclei editing. Unlike existing approaches, our method regularizes feature trajectories within a disentangled latent space learned by a variational auto-encoder (VAE). This ensures that manipulating a target feature automatically adjusts correlated attributes to remain within the learned distribution of real cells. These optimized features then guide a conditional diffusion model to synthesize high-fidelity images. Experiments demonstrate that our approach is able to navigate the manifold of pathomics features when editing those features. The proposed method outperforms baseline methods in conditional feature editing while preserving structural coherence.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
