When Does Synthetic CT Transfer? A Label-Free Donor/Host Diagnostic for Medical Vision-Language Model Routing on Real Lung CT
On the map: Multimodal LLMs / vision-language models → Medical vision-language models
Abstract (arXiv)
A synthetic measurement of model competence is useful only if it survives the move to real data, yet the real labels that would verify it are exactly what medical imaging lacks. We ask whether transfer can be predicted in advance, label-free, and answer with a mechanism: on synthetic digital twins, competence that is donor-driven (a property of the transplanted nodule) survives the synthetic to real change of host, while host-driven competence (a property of the surrounding anatomy) need not. We test this on three lung CT vision-language tasks chosen to span that axis, across five public VLMs, four guidance conditions, and seven real datasets. The prediction holds in every case: presence and size orderings transfer (R2 >= 0.96), lobe does not; the split survives leave-source-out calibration, and the diagnostic names that boundary before any real label. TrialCouncil, a training-free council calibrated only on synthetic CT, confirms it by matching the best fixed model exactly where transfer is predicted. The contribution is not the router but the finding that transfer itself is predictable, label-free, from synthetic data alone.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 22 of its 30 references that are in the map. First posted on arXiv 28 Jun 2026.
Builds on
22 of 30 references.
Closest ancestors · 4
Same direction, newest first
- 2025Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning8 Jun
- 2024CARES: A Comprehensive Benchmark of Trustworthiness in Medical Vision Language Models10 Jun
- 2024Vision-Language Models for Medical Report Generation and Visual Question Answering: A Review4 Mar
- 2023LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day1 Jun
Other references · 18
- 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
- 2025Qwen2.5-VL Technical Reportcited by 5,418
- 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,413
- 2020Shortcut Learning in Deep Neural Networkscited by 1,928
- 2017Selective Classification for Deep Neural Networkscited by 799
- 2023BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairscited by 506
- 2025MedGemma Technical Reportcited by 398
- 2020Consistent Estimators for Learning to Defer to an Expertcited by 262
- 2016Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: the LUNA16 challengecited by 198
- 2024MAISI: Medical AI for Synthetic Imagingcited by 86
- 2019LNDb: A Lung Nodule Database on Computed Tomographycited by 27
- 2024Open (Clinical) LLMs are Sensitive to Instruction Phrasingscited by 23
6 more
- 2024To Ensemble or Not: Assessing Majority Voting Strategies for Phishing Detection with Large Language Modelscited by 12
- 2023Regression with Cost-based Rejectioncited by 11
- 2024Virtual Lung Screening Trial (VLST): An In Silico Study Inspired by the National Lung Screening Trial for Lung Cancer Detectioncited by 6
- 2023The Utility of the Virtual Imaging Trials Methodology for Objective Characterization of AI Systems and Training Datacited by 4
- 2025NodMAISI: Nodule-Oriented Medical AI for Synthetic Imagingcited by 2
- 2026iTRIALSPACE: Programmable Virtual Lesion Trials for Controlled Evaluation of Lung CT Modelscited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2022Spot the fake lungs: Generating Synthetic Medical Images using Neural Diffusion Models
- 2026When Can Test-Time Adaptation Help Zero-Shot CT Vision-Language Models?
- 2024Multi-Conditioned Denoising Diffusion Probabilistic Model (mDDPM) for Medical Image Synthesis
- 2025Trustworthy Few-Shot Transfer of Medical VLMs through Split Conformal Prediction
- 2025Lung-DDPM: Semantic Layout-guided Diffusion Models for Thoracic CT Image Synthesis
- 2026Agentic Autoresearch for CT Reconstruction
- 2026What Do Medical Vision-Language Models Learn in Radiology? Transfer, Alignment, and Source-Proxy Leakage Under Distribution Shift
- 2026Learning How Much, Not Just What: Cross-Patient Burden Order for CT Vision-Language Pretraining