Proceedings

GeneCaDiff: Hierarchical Tissue Image Synthesis from Gene Expression via Multi-Stage Cascaded Diffusion Model

Weitian Huang, Shuaibo Gao, Bing Liu, Xiaoqi Sheng, Jiazhou Chen, Hongmin Cai

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Main Track. Pages 4376-4384.

https://doi.org/10.24963/ijcai.2026/487

Keywords

  • Machine Learning: Multi-modal learning
  • Machine Learning: Generative models
  • Multidisciplinary Topics and Applications: Bioinformatics

Abstract

The scarcity of paired gene expression and pathology images datasets poses a major bottleneck for training large-scale pathology foundation models. Although gene-to-image generative models offer a promising solution, existing methods typically employ coarse-grained conditional control strategies, resulting in entanglement between background textures and cell layouts. To address this challenge, we propose GeneCaDiff, a three-stage cascaded diffusion model that explicitly aligns the generative process with the hierarchical organization of biological tissues. Two conditional DDPMs independently synthesize tissue backgrounds and cellular foreground components, and a subsequent ControlNet-based fusion generator utilizes niche and cellular community maps as dual conditions to synthesize realistic tissue images. Quantitative and qualitative evaluations demonstrate strong realism and diversity, while controllability experiments validate hierarchical, decoupled control over niche textures and community layouts.

Weitian Huang, Shuaibo Gao, Bing Liu, Xiaoqi Sheng, Jiazhou Chen, and Hongmin Cai. 2026. GeneCaDiff: Hierarchical Tissue Image Synthesis from Gene Expression via Multi-Stage Cascaded Diffusion Model. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 4376–4384. https://doi.org/10.24963/ijcai.2026/487
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards