A Promptable 3D-CT Foundation Model-Based Approach for Pulmonary Embolism

K Le Floch; E Ferreres; J Khlaut; A Prat; L Alberge; L Machado; D Tordjman; X Guerra; P Hérent; P Manceron; M Sapoval; T Boeken

doi:10.1007/s00270-026-04488-2

A Promptable 3D-CT Foundation Model-Based Approach for Pulmonary Embolism

Cardiovasc Intervent Radiol. 2026 Jun 2. doi: 10.1007/s00270-026-04488-2. Online ahead of print.

Authors

K Le Floch^{1

2}, E Ferreres³, J Khlaut^{4

3}, A Prat³, L Alberge³, L Machado^{3

5}, D Tordjman³, X Guerra⁴, P Hérent^{3

6}, P Manceron³, M Sapoval⁷, T Boeken⁸

Affiliations

¹ Department of Vascular and Oncological interventional Radiology, Hôpital Européen Georges Pompidou, HeKA PRAIRIE-PSAI, INRIA Paris, Paris, France. korentin.lefloch@aphp.fr.
² , Raidium, Paris, France. korentin.lefloch@aphp.fr.
³ , Raidium, Paris, France.
⁴ Department of Vascular and Oncological interventional Radiology, Hôpital Européen Georges Pompidou, HeKA PRAIRIE-PSAI, INRIA Paris, Paris, France.
⁵ Department of Radiology, Beaujon Hospital, Clichy, France.
⁶ Department of Radiology, Saint-Denis, France.
⁷ Department of Vascular and Oncological interventional Radiology, Hôpital Européen Georges Pompidou, HeKA PRAIRIE-PSAI, INRIA Paris, Paris, France. marc.sapoval2@aphp.fr.
⁸ Department of Vascular and Oncological interventional Radiology, Hôpital Européen Georges Pompidou, HeKA PRAIRIE-PSAI, INRIA Paris, Paris, France. tom.boeken@aphp.fr.

PMID: 42230969
DOI: 10.1007/s00270-026-04488-2

Abstract

Purpose: Blood clot volume (BCV), defined as the total three-dimensional (3D) volume of the thrombus on computed tomography angiography (CTA), is an objective biomarker of pulmonary embolism (PE) severity whose clinical use is limited by time-consuming manual segmentation. This study evaluates ClotIA (Clot Interventional AI), a foundation model (FM)-based approach designed for rapid and interactive clot segmentation in PE.

Materials and methods: RAPSv2, a foundation model derived from SAM2, was fine-tuned on a stratified sample of 309 patients from the RSPECT dataset (2020). Segmentation performance was evaluated using the Dice similarity coefficient (DSC) and compared to that of nnUNet (no-new-Net). The predicted BCV was correlated with imaging biomarkers of PE severity.

Results: ClotIA achieved a mean DSC of 0.83 ± 0.06 after guided refinement, compared to 0.79 ± 0.10 at baseline (p < 0.001) and 0.81 ± 0.13 for nnUNet (p < 0.001). The predicted BCV showed strong agreement with the reference volume (r = 0.995; mean bias + 0.12 mL) and was significantly correlated with RV/LV diameter ratio (r = 0.62, p < 0.001) and RV/LV volume ratio (r = 0.68, p < 0.001).

Conclusion: ClotIA enables rapid and reproducible 3D quantification of pulmonary embolism thrombi, correlating with established severity markers and providing the necessary basis for translating emerging biomarkers into clinical practice.

Keywords: Artificial intelligence; Blood clot volume; Foundation models; Interactive segmentation; Pulmonary embolism; Risk stratification; Thrombotic burden.