Abstract
Reliable cerebrovascular analysis from 3D time-of-flight magnetic resonance angiography depends on the anatomical completeness and consistency of vascular representations. However, automated vessel segmentation may contain errors that hinder downstream analysis tasks. Identifying such errors directly in 3D is challenging due to the complex topology of the cerebrovascular anatomy. In this work, we propose a canonical multi-view framework for automated assessment of cerebrovascular segmentation quality. Rather than reasoning directly over the complete 3D vascular tree, we reformulate localized quality assessment as detection in canonical two-dimensional projection views, where anatomical structures exhibit reproducible appearance. A lightweight detection model is applied independently to complementary views, whose agreement is used to identify potentially erroneous segmentations for manual inspection. To alleviate annotation scarcity, we propose view synthesis by perturbing projection angles and slabs around anatomy-guided reference views, generating anatomically valid training examples from the same registered 3D volume. We demonstrate the framework for identifying spurious superior sagittal sinus segmentations in TOF-MRA and evaluate it on 99 subjects with manually annotated quality labels. The proposed approach achieved an F1 score of 88.31, outperforming vision-language models (VLM) operating in few-shot settings or adapted with LoRA, while relying on a lightweight task-specific detector instead of large VLMs. Our results show that canonical projection views reformulate 3D cerebrovascular quality assessment into a robust and efficient 2D detection problem, facilitating scalable construction of reliable cerebrovascular analysis pipelines. All code is available at https://github.com/erc-caravel/vascular-qc.
Links to Paper and Supplementary Materials
Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026-sat/paper/SWITCH_009.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=tLzOqy0aZB
BibTex
@InProceedings{IonBog_ProjectionBased_MICCAISAT2026,
author = { Ion, Bogdan AND Zhang, Xiaoming AND Ramil, Leonard Vincent AND Boccadifuoco, Alice AND Ourselin, Sébastien AND Cleary, Jon AND Zuluaga, Maria A.},
title = { { Projection-Based Quality Assessment of Cerebrovascular Segmentations } },
booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026 Workshops and Challenges},
year = {2026},
publisher = {Springer Nature Switzerland},
volume = {LNCS 17255},
month = {pending},
page = {pending}
}