HiFusion: Hierarchical Intra-Spot Alignment and Regional Context Fusion for Spatial Gene Expression Prediction from Histopathology
By: Ziqiao Weng , Yaoyu Fang , Jiahe Qian and more
Potential Business Impact:
Reads hidden gene messages from tissue pictures.
Spatial transcriptomics (ST) bridges gene expression and tissue morphology but faces clinical adoption barriers due to technical complexity and prohibitive costs. While computational methods predict gene expression from H&E-stained whole-slide images (WSIs), existing approaches often fail to capture the intricate biological heterogeneity within spots and are susceptible to morphological noise when integrating contextual information from surrounding tissue. To overcome these limitations, we propose HiFusion, a novel deep learning framework that integrates two complementary components. First, we introduce the Hierarchical Intra-Spot Modeling module that extracts fine-grained morphological representations through multi-resolution sub-patch decomposition, guided by a feature alignment loss to ensure semantic consistency across scales. Concurrently, we present the Context-aware Cross-scale Fusion module, which employs cross-attention to selectively incorporate biologically relevant regional context, thereby enhancing representational capacity. This architecture enables comprehensive modeling of both cellular-level features and tissue microenvironmental cues, which are essential for accurate gene expression prediction. Extensive experiments on two benchmark ST datasets demonstrate that HiFusion achieves state-of-the-art performance across both 2D slide-wise cross-validation and more challenging 3D sample-specific scenarios. These results underscore HiFusion's potential as a robust, accurate, and scalable solution for ST inference from routine histopathology.
Similar Papers
3D-Guided Scalable Flow Matching for Generating Volumetric Tissue Spatial Transcriptomics from Serial Histology
CV and Pattern Recognition
Creates 3D maps of cells for better disease study.
Scalable Generation of Spatial Transcriptomics from Histology Images via Whole-Slide Flow Matching
CV and Pattern Recognition
Shows where genes are in cells faster.
Spatial Transcriptomics Expression Prediction from Histopathology Based on Cross-Modal Mask Reconstruction and Contrastive Learning
CV and Pattern Recognition
**Helps doctors find cancer by reading cell maps.**