Salvato in:
Dettagli Bibliografici
Autori principali: Li, Yuheng, Gao, Yuan, Dong, Haoyu, Lai, Yuxiang, Wang, Shansong, Safari, Mojtaba, Baciak, James E., Yang, Xiaofeng
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2605.21906
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913153836646400
author Li, Yuheng
Gao, Yuan
Dong, Haoyu
Lai, Yuxiang
Wang, Shansong
Safari, Mojtaba
Baciak, James E.
Yang, Xiaofeng
author_facet Li, Yuheng
Gao, Yuan
Dong, Haoyu
Lai, Yuxiang
Wang, Shansong
Safari, Mojtaba
Baciak, James E.
Yang, Xiaofeng
contents Computed tomography (CT) is a 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 agglomerative continual pretraining on 266,227 CT volumes from 56 publicly available datasets, forming a large-scale public resource for CT representation learning. FlexiCT uses agglomerative 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_21906
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Universal CT Representations from Anatomy to Disease Phenotype through Agglomerative Pretraining
Li, Yuheng
Gao, Yuan
Dong, Haoyu
Lai, Yuxiang
Wang, Shansong
Safari, Mojtaba
Baciak, James E.
Yang, Xiaofeng
Computer Vision and Pattern Recognition
Computed tomography (CT) is a 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 agglomerative continual pretraining on 266,227 CT volumes from 56 publicly available datasets, forming a large-scale public resource for CT representation learning. FlexiCT uses agglomerative 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.
title Universal CT Representations from Anatomy to Disease Phenotype through Agglomerative Pretraining
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.21906