Segmentation and morphological analysis of recanalized coiled aneurysms: Towards an automatic tool for clipping planning in microsurgery
Matthieu Coupet, Manel Meftah, Camille Lopez, Ludivine Maintier, Aziliz Guezou-Philippe, Julien Ognard, Jean-Christophe Gentric, Valérin Burdin, Elsa Magro, Guillaume Dardenne
Abstract
Intracranial aneurysms are dilatations of cerebral arteries that may rupture, leading to subarachnoid hemorrhage and high mortality. Endovascular coiling is widely used to prevent rupture; however, many treated aneurysms experience recanalization, which often necessitates follow-up interventions or surgical clipping.
Introduction
Intracranial aneurysms (IA), also known as cerebral aneurysms, are a deformation of the cerebral artery wall, leading to a fragile arterial zone that can rupture. Aneurysmal rupture systematically causes a subarachnoid hemorrhage (SAH) of variable severity, which may result in death or severe neurological sequelae.
Materials and methods
An overview of the global workflow is presented in Figure 1. There are two main tasks: the automatic segmentation of coiled aneurysms and their morphometric analysis. The proposed segmentation approach allows for the accurate delineation of the key anatomical structures of interest, including the parent artery, the aneurysm sac containing coil material and, most importantly, the recanalized compartment.
Results
Table 1 summarizes the performance metrics of the 3D nnU-Net frameworks pre-trained on CADA weights, specifically focusing on the Dice score and Jaccard index for three distinct anatomical structures: coils, vascular trees, and recanalization areas. The mean results were derived from a set of 16 test cases.
Discussion
The average Dice and Jaccard scores obtained with nnU-Net are encouraging and confirm the potential of the approach. Lower scores were mainly observed for the recanalization area, which can be explained by its overlap with the vascular tree: both structures share similar signal characteristics, making them difficult to separate reliably.
Conclusion
This study presents a proof-of-concept automated workflow for the segmentation and morphometric analysis of recanalized coiled intracranial aneurysms from 3D-RA images.
Citation: Coupet M, Meftah M, Lopez C, Maintier L, Guezou-Philippe A, Ognard J, et al. (2026) Segmentation and morphological analysis of recanalized coiled aneurysms: Towards an automatic tool for clipping planning in microsurgery. PLoS One 21(9): e0358945. https://doi.org/10.1371/journal.pone.0358945
Editor: Mario Tortora, Università degli Studi di Napoli Federico II: Universita degli Studi di Napoli Federico II, ITALY
Received: March 6, 2026; Accepted: September 8, 2026; Published: September 23, 2026
Copyright: © 2026 Coupet et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Data Availability: The data underlying the results presented in this study are not publicly available due to ethical and legal restrictions related to patient confidentiality. The data are held by Brest University Hospital (CHU de Brest, France), sponsor of the PREDICTNRI study (ClinicalTrials.gov identifier NCT04504695). Qualified researchers may submit data access requests to the institutional research-on-data unit of Brest University Hospital (Direction de la Recherche Clinique et de l’Innovation, cellule.rniph@chu-brest.fr). Requests are subject to applicable institutional, ethical, and legal approvals. The data remain under the institutional custody of Brest University Hospital, providing a persistent institutional route for future data access requests.
Funding: The author(s) received no specific funding for this work.
Competing interests: The authors have declared that no competing interests exist.
