Img2ST-Net: efficient high-resolution spatial omics prediction from whole-slide histology images via fully convolutional image-to-image learning
We present a scalable, biologically coherent framework for high-resolution ST prediction. Img2ST-Net offers a principled solution for efficient and accurate ST inference at scale. Our contributions lay the groundwork for next-generation ST modeling that is robust and resolution-aware.
Authors
- Ruining Deng (ORCID: https://orcid.org/0000-0001-6300-8518)
- Yucheng Tang (ORCID: https://orcid.org/0000-0002-6008-9700)
- Daguang Xu (ORCID: https://orcid.org/0000-0002-4621-881X)
- Tianyuan Yao (ORCID: https://orcid.org/0000-0002-1848-079X)
- Yuankai Huo (ORCID: https://orcid.org/0000-0002-2096-8065)
- Junlin Guo (ORCID: https://orcid.org/0000-0002-3388-1970)
- Haichun Yang (ORCID: https://orcid.org/0000-0003-4265-7492)
- Shilin Zhao (ORCID: https://orcid.org/0000-0002-3921-3965)
- Junchao Zhu (ORCID: https://orcid.org/0000-0002-2576-5312)
- Yu Wang (ORCID: https://orcid.org/0000-0003-3511-0288)
- Chongyu Qu (ORCID: https://orcid.org/0009-0008-8893-2748)
- Mengmeng Yin
- Juming Xiong
Institutions
- Vanderbilt University (US)
- Cornell University (US)
- Nvidia (United States) (US)
- Weill Cornell Medicine (US)
- Vanderbilt University Medical Center (US)
Publication Details
- Journal
- Journal of Medical Imaging
- Published
- 2025-11-07
- DOI
- https://doi.org/10.1117/1.jmi.12.6.061410
- Primary Topic
- Cell Image Analysis Techniques
- Type
- article
- Field-Weighted Citation Impact
- 0.00