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.

翻译：病理组学是一种新兴方法，能够提供超越黑盒深度学习模型的丰富定量特征，为数字病理学提供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（如"二阶矩"）仍难以解释，尤其是在不同临床背景下，这限制了其实际应用。条件扩散模型通过特征编辑展现出可解释性潜力，但它们通常假设特征相互独立——这一假设与病理组学特征固有的相关性相悖。因此，在固定其他特征的同时编辑某个特征，可能导致模型偏离生物流形并产生不真实的伪影。为解决这一问题，我们提出了一种流形感知扩散（MAD）框架，用于实现可控且生物学合理的细胞核编辑。与现有方法不同，我们的方法通过变分自编码器（VAE）学习解耦的潜在空间，在此空间中对特征轨迹进行正则化。这确保在操纵目标特征时，相关属性会自动调整以保持在真实细胞学习分布范围内。这些优化后的特征随后指导条件扩散模型合成高保真图像。实验表明，我们的方法在编辑病理组学特征时能够有效导航特征流形。所提出的方法在条件特征编辑任务中优于基线方法，同时保持了结构一致性。