CREATE-FFPE: Cross-Resolution Compensated and Multi-Frequency Enhanced FS-to-FFPE Stain Transfer for Intraoperative IHC Images

2025-03-02

AI Summary

Intraoperative frozen-section (FS) immunohistochemistry (IHC) images suffer from artifacts—including tissue contamination and blurred nuclear details—hindering rapid benign/malignant assessment; meanwhile, high-fidelity formalin-fixed paraffin-embedded (FFPE) IHC images are unsuitable for intraoperative use due to lengthy preparation. To bridge this gap, we propose the first cross-modal staining transfer framework from FS to FFPE. Our method introduces two novel modules: a Cross-Resolution Compensation Module (CRCM) for multi-scale feature alignment and compensation, and a Wavelet Detail-Guided Module (WDGM) that leverages discrete wavelet transform to model and reconstruct subcellular structures in the frequency domain, jointly enhancing contamination robustness and structural fidelity. Evaluated on a custom-built dataset, our approach reduces Fréchet Inception Distance (FID) by 44.4% and Kernel Inception Distance (KID × 100) by 71.2%. Moreover, downstream microsatellite instability (MSI) prediction accuracy shows significant improvement.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Feature Construction/Reformulation
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

In the immunohistochemical (IHC) analysis during surgery, frozen-section (FS) images are used to determine the benignity or malignancy of the tumor. However, FS image faces problems such as image contamination and poor nuclear detail, which may disturb the pathologist's diagnosis. In contrast, formalin-fixed and paraffin-embedded (FFPE) image has a higher staining quality, but it requires quite a long time to prepare and thus is not feasible during surgery. To help pathologists observe IHC images with high quality in surgery, this paper proposes a Cross-REsolution compensATed and multi-frequency Enhanced FS-to-FFPE (CREATE-FFPE) stain transfer framework, which is the first FS-to-FFPE method for the intraoperative IHC images. To solve the slide contamination and poor nuclear detail mentioned above, we propose the cross-resolution compensation module (CRCM) and the wavelet detail guidance module (WDGM). Specifically, CRCM compensates for information loss due to contamination by providing more tissue information across multiple resolutions, while WDGM produces the desirable details in a wavelet way, and the details can be used to guide the stain transfer to be more precise. Experiments show our method can beat all the competing methods on our dataset. In addition, the FID has decreased by 44.4%, and KID*100 has decreased by 71.2% by adding the proposed CRCM and WDGM in ablation studies, and the performance of a downstream microsatellite instability prediction task with public dataset can be greatly improved by performing our FS-to-FFPE stain transfer.

Problem

• Improves intraoperative IHC image quality for tumor diagnosis.
• Addresses FS image contamination and poor nuclear detail issues.
• Enhances stain transfer from FS to FFPE for better pathology analysis.

Innovation

• Cross-resolution compensation for tissue information
• Wavelet detail guidance for precise stain transfer
• FS-to-FFPE stain transfer for intraoperative IHC images