Unlocking 2D Promptable Foundation Models for 3D Vessel Segmentation by Automatic Prompt Generation

Ziyu Zhang, Yi Yu, Yuan Xue
Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, PMLR 315:3764-3778, 2026.

Abstract

3D vessel segmentation is a core task in medical image analysis, playing a crucial role in disease diagnosis and surgical planning. While fully supervised 3D segmentation methods rely on costly high-quality annotations, promptable models (e.g., ScribblePrompt) provide a promising alternative with their zero-shot generalization capability for efficient 3D segmentation. Nevertheless, when directly applied to 3D tasks, these 2D methods require slice-wise prompts, disregarding the continuity of 3D structures and leading to low efficiency. To address this issue, we propose an innovative method based on automatic prompt generation, which integrates with pre-trained 2D interactive models to achieve efficient 3D vessel segmentation. By leveraging spatial continuity and contextual information, our method automatically generates prompts across the entire 3D volume from a single user-provided prompt. Experiments conducted on public and in-house vessel datasets demonstrate the effectiveness of the proposed method, showing that it achieves segmentation accuracy comparable to or better than state-of-the-art models, while significantly reducing the interaction cost.

Cite this Paper

BibTeX
@InProceedings{pmlr-v315-zhang26c, title = {Unlocking 2D Promptable Foundation Models for 3D Vessel Segmentation by Automatic Prompt Generation}, author = {Zhang, Ziyu and Yu, Yi and Xue, Yuan}, booktitle = {Proceedings of The 9th International Conference on Medical Imaging with Deep Learning}, pages = {3764--3778}, year = {2026}, editor = {Huo, Yuankai and Gao, Mingchen and Kuo, Chang-Fu and Jin, Yueming and Deng, Ruining}, volume = {315}, series = {Proceedings of Machine Learning Research}, month = {08--10 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v315/main/assets/zhang26c/zhang26c.pdf}, url = {https://proceedings.mlr.press/v315/zhang26c.html}, abstract = {3D vessel segmentation is a core task in medical image analysis, playing a crucial role in disease diagnosis and surgical planning. While fully supervised 3D segmentation methods rely on costly high-quality annotations, promptable models (e.g., ScribblePrompt) provide a promising alternative with their zero-shot generalization capability for efficient 3D segmentation. Nevertheless, when directly applied to 3D tasks, these 2D methods require slice-wise prompts, disregarding the continuity of 3D structures and leading to low efficiency. To address this issue, we propose an innovative method based on automatic prompt generation, which integrates with pre-trained 2D interactive models to achieve efficient 3D vessel segmentation. By leveraging spatial continuity and contextual information, our method automatically generates prompts across the entire 3D volume from a single user-provided prompt. Experiments conducted on public and in-house vessel datasets demonstrate the effectiveness of the proposed method, showing that it achieves segmentation accuracy comparable to or better than state-of-the-art models, while significantly reducing the interaction cost.} }
Endnote
%0 Conference Paper %T Unlocking 2D Promptable Foundation Models for 3D Vessel Segmentation by Automatic Prompt Generation %A Ziyu Zhang %A Yi Yu %A Yuan Xue %B Proceedings of The 9th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2026 %E Yuankai Huo %E Mingchen Gao %E Chang-Fu Kuo %E Yueming Jin %E Ruining Deng %F pmlr-v315-zhang26c %I PMLR %P 3764--3778 %U https://proceedings.mlr.press/v315/zhang26c.html %V 315 %X 3D vessel segmentation is a core task in medical image analysis, playing a crucial role in disease diagnosis and surgical planning. While fully supervised 3D segmentation methods rely on costly high-quality annotations, promptable models (e.g., ScribblePrompt) provide a promising alternative with their zero-shot generalization capability for efficient 3D segmentation. Nevertheless, when directly applied to 3D tasks, these 2D methods require slice-wise prompts, disregarding the continuity of 3D structures and leading to low efficiency. To address this issue, we propose an innovative method based on automatic prompt generation, which integrates with pre-trained 2D interactive models to achieve efficient 3D vessel segmentation. By leveraging spatial continuity and contextual information, our method automatically generates prompts across the entire 3D volume from a single user-provided prompt. Experiments conducted on public and in-house vessel datasets demonstrate the effectiveness of the proposed method, showing that it achieves segmentation accuracy comparable to or better than state-of-the-art models, while significantly reducing the interaction cost.
APA
Zhang, Z., Yu, Y. & Xue, Y.. (2026). Unlocking 2D Promptable Foundation Models for 3D Vessel Segmentation by Automatic Prompt Generation. Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 315:3764-3778 Available from https://proceedings.mlr.press/v315/zhang26c.html.

Related Material