Journal article · 2026 · Open access

Universal CT representations from anatomy to disease phenotype through stage-wise pretraining

Yuheng Li, Yuan Gao, Haoyu Dong, Yuxiang Lai, Shansong Wang, Mojtaba Safari, James E. Baciak, Xiaofeng Yang

npj Digital Medicine · Published 7 October 2026 · DOI 10.1038/s41746-026-03343-5

Open PDFView at the publisherCite this paper

In brief

“Universal CT representations from anatomy to disease phenotype through stage-wise pretraining” is a 2026 journal article by Yuheng Li and 7 co-authors, published in npj Digital Medicine. OpenAlex counts 8 citations as of 17 November 2026, which puts it in the top 2% of works published in 2026 by citations. It is open access under a CC BY-NC-ND licence: the full text is free to read at npj Digital Medicine.

Citations
8
Most cited in
2026 (8)
Field-weighted impact
9.61
References
54
Authors
8

Abstract

Computed tomography (CT) is central to three-dimensional medical imaging, yet CT-based artificial intelligence remains fragmented across task-specific models for segmentation, classification, registration, and report analysis. Here we present FlexiCT, a family of CT foundation models trained by stage-wise pretraining on 266,227 CT volumes from 56 publicly available datasets, forming a large-scale public resource for CT representation learning. FlexiCT uses sequential pretraining across three stages: two-dimensional axial pretraining, three-dimensional anatomical pretraining and report-guided semantic alignment. This training strategy supports slice-level, volume-level, and vision-language analysis. Across five downstream task families (segmentation, classification, registration, vision-language understanding and clinical retrieval), FlexiCT matches or exceeds prior task-specific approaches on multiple benchmarks. Its embeddings further organize CT scans along gradients associated with various tumor stages, suggesting that CT foundation models can capture imaging features relevant to disease phenotype characterization. Project page and code are available at: https://ricklisz.github.io/flexict.github.io and https://github.com/ricklisz/FlexiCT .

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Li, Y., Gao, Y., Dong, H., Lai, Y., Wang, S., Safari, M., Baciak, J. E., & Yang, X. (2026). Universal CT representations from anatomy to disease phenotype through stage-wise pretraining. npj Digital Medicine. https://doi.org/10.1038/s41746-026-03343-5

MLA 9

Li, Yuheng, et al. “Universal CT representations from anatomy to disease phenotype through stage-wise pretraining.” npj Digital Medicine, 2026. https://doi.org/10.1038/s41746-026-03343-5.

Chicago

Li, Yuheng, Yuan Gao, Haoyu Dong, Yuxiang Lai, Shansong Wang, Mojtaba Safari, James E. Baciak, and Xiaofeng Yang. 2026. “Universal CT representations from anatomy to disease phenotype through stage-wise pretraining.” npj Digital Medicine. https://doi.org/10.1038/s41746-026-03343-5.

Harvard

Li, Y. et al. (2026) ‘Universal CT representations from anatomy to disease phenotype through stage-wise pretraining’, npj Digital Medicine. doi:10.1038/s41746-026-03343-5.

IEEE

Y. Li et al., “Universal CT representations from anatomy to disease phenotype through stage-wise pretraining,” npj Digital Medicine, 2026, doi: 10.1038/s41746-026-03343-5.

BibTeX

@article{li2026universal,
  title     = {{Universal CT representations from anatomy to disease phenotype through stage-wise pretraining}},
  author    = {Li, Yuheng and Gao, Yuan and Dong, Haoyu and Lai, Yuxiang and Wang, Shansong and Safari, Mojtaba and Baciak, James E. and Yang, Xiaofeng},
  journal   = {npj Digital Medicine},
  year      = {2026},
  doi       = {10.1038/s41746-026-03343-5},
  url       = {https://doi.org/10.1038/s41746-026-03343-5}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education

  • computed tomography
  • CT image segmentation
  • CT image classification
  • CT registration
  • visual language understanding
  • tumor staging
  • disease phenotypes
  • vision-language pre-training

Work with this paper

Most-cited papers in Medicine

All highly cited Medicine papers

Questions about this paper

How do I cite this paper in APA style?

Li, Y., Gao, Y., Dong, H., Lai, Y., Wang, S., Safari, M., Baciak, J. E., & Yang, X. (2026). Universal CT representations from anatomy to disease phenotype through stage-wise pretraining. npj Digital Medicine. https://doi.org/10.1038/s41746-026-03343-5

How many times has this paper been cited?

8 times, according to OpenAlex on 17 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at npj Digital Medicine: sign in and open the PDF from this page.

Who wrote this paper?

Yuheng Li, Yuan Gao, Haoyu Dong, Yuxiang Lai, Shansong Wang, Mojtaba Safari, James E. Baciak, Xiaofeng Yang.

What is the DOI of this paper?

10.1038/s41746-026-03343-5, permanently at https://doi.org/10.1038/s41746-026-03343-5. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 17 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.