Abstract
Modeling medical vessel-like anatomy is challenging due to its intricate topology and sensitivity to dataset shifts. Consequently, task-specific models often suffer from topological inconsistencies, including artificial disconnections and spurious merges. Motivated by the promise of multimodal large language models (MLLMs) for zero-shot generalization, we propose TubeMLLM, a unified foundation model that couples structured understanding with controllable generation for medical vessel-like anatomy. By integrating topological priors through explicit natural language prompting and aligning them with visual representations in a shared-attention architecture, TubeMLLM significantly enhances topology-aware perception. Furthermore, we construct TubeMData, a pionner multimodal benchmark comprising comprehensive topology-centric tasks, and introduce an adaptive loss weighting strategy to emphasize topology-critical regions during training. Extensive experiments demonstrate that, even without task-specific finetuning, TubeMLLM exhibits superior generalization on out-of-distribution vessel datasets. It significantly enhances both topological fidelity and segmentation accuracy, effectively reducing topological errors while maintaining robustness against degradations such as blur, noise, and low resolution.
Links to Paper and Supplementary Materials
Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026-sat/paper/MedAGI_019.pdf
SharedIt Link: Not yet available
SpringerLink (DOI): Not yet available
Supplementary Material: Not Submitted
Link to Open Review
Open Review Page: https://openreview.net/forum?id=hPWjCEIkXB
BibTex
@InProceedings{LiuYao_TubeMLLM_MICCAISAT2026,
author = { Liu, Yaoyu AND Zhang, Minghui AND Wang, Kefan AND You, Xin AND Zhang, Hanxiao AND Li, Qingbiao AND Chen, Yirong AND Gu, Yun AND Zhang, Xinglin},
title = { { TubeMLLM: A Foundation Model for Topology Knowledge Exploration in Vessel-like Anatomy } },
booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026 Workshops and Challenges},
year = {2026},
publisher = {Springer Nature Switzerland},
volume = {LNCS 17261},
month = {pending},
page = {pending}
}