HistDiST: Histopathological Diffusion-based Stain Transfer
This addresses the need for molecular insights in histopathology without costly IHC staining, representing a novel application of diffusion models in this domain.
The paper tackles the problem of translating Hematoxylin and Eosin (H&E) stained histopathology images to Immunohistochemistry (IHC) images as a cost-effective alternative to expensive IHC staining, proposing HistDiST, a Latent Diffusion Model framework that achieves a 28% improvement in Molecular Retrieval Accuracy on H&E-to-Ki67 translation compared to existing methods.
Hematoxylin and Eosin (H&E) staining is the cornerstone of histopathology but lacks molecular specificity. While Immunohistochemistry (IHC) provides molecular insights, it is costly and complex, motivating H&E-to-IHC translation as a cost-effective alternative. Existing translation methods are mainly GAN-based, often struggling with training instability and limited structural fidelity, while diffusion-based approaches remain underexplored. We propose HistDiST, a Latent Diffusion Model (LDM) based framework for high-fidelity H&E-to-IHC translation. HistDiST introduces a dual-conditioning strategy, utilizing Phikon-extracted morphological embeddings alongside VAE-encoded H&E representations to ensure pathology-relevant context and structural consistency. To overcome brightness biases, we incorporate a rescaled noise schedule, v-prediction, and trailing timesteps, enforcing a zero-SNR condition at the final timestep. During inference, DDIM inversion preserves the morphological structure, while an eta-cosine noise schedule introduces controlled stochasticity, balancing structural consistency and molecular fidelity. Moreover, we propose Molecular Retrieval Accuracy (MRA), a novel pathology-aware metric leveraging GigaPath embeddings to assess molecular relevance. Extensive evaluations on MIST and BCI datasets demonstrate that HistDiST significantly outperforms existing methods, achieving a 28% improvement in MRA on the H&E-to-Ki67 translation task, highlighting its effectiveness in capturing true IHC semantics.