Learning Wall Segmentation in 3D Vessel Trees using Sparse Annotations

📅 2025-02-18
📈 Citations: 1
Influential: 0
📄 PDF
🤖 AI Summary
This work addresses the bottleneck of labor-intensive dense manual annotations in 3D carotid vessel wall segmentation. We propose a fully automatic 3D segmentation framework leveraging only sparse centerline annotations. Methodologically, we introduce a novel bifurcation-axis-perpendicular cross-sectional pseudo-label generation strategy, integrated with centerline-driven transverse slice sampling, adversarial 2D U-Net–based initial segmentation, geometry-aware pseudo-label projection, and end-to-end 3D U-Net optimization. This paradigm efficiently transforms easily obtainable sparse 2D centerline labels into high-fidelity 3D vessel wall segmentations, notably improving accuracy at bifurcations. Evaluated on real carotid imaging data, our method enables precise quantification of 3D biomarkers—including plaque volume—and delivers a clinically deployable, automated solution for carotid stenosis assessment.

Technology Category

Application Category

📝 Abstract
We propose a novel approach that uses sparse annotations from clinical studies to train a 3D segmentation of the carotid artery wall. We use a centerline annotation to sample perpendicular cross-sections of the carotid artery and use an adversarial 2D network to segment them. These annotations are then transformed into 3D pseudo-labels for training of a 3D convolutional neural network, circumventing the creation of manual 3D masks. For pseudo-label creation in the bifurcation area we propose the use of cross-sections perpendicular to the bifurcation axis and show that this enhances segmentation performance. Different sampling distances had a lesser impact. The proposed method allows for efficient training of 3D segmentation, offering potential improvements in the assessment of carotid artery stenosis and allowing the extraction of 3D biomarkers such as plaque volume.
Problem

Research questions and friction points this paper is trying to address.

3D segmentation of carotid artery wall
Efficient training with sparse annotations
Improved assessment of carotid artery stenosis
Innovation

Methods, ideas, or system contributions that make the work stand out.

Sparse annotations for 3D segmentation
Adversarial 2D network for cross-sections
3D pseudo-labels from 2D annotations
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
No related jobs found.
H
Hinrich Rahlfs
Institute of Computer-Assisted Cardiovascular Medicine, Charité - Universitätsmedizin Berlin, Germany
M
Markus Hullebrand
Institute of Computer-Assisted Cardiovascular Medicine, Charité - Universitätsmedizin Berlin, Germany; Fraunhofer MEVIS, Bremen, Germany; DZHK (German Centre for Cardiovascular Research), Partner Site Berlin, Germany
S
Sebastian Schmitter
Physikalisch-Technische Bundesanstalt, Berlin, Germany
C
C. Strecker
Department of Neurology and Neurophysiology, Faculty of Medicine, Medical Center—University of Freiburg, University of Freiburg, Germany
A
Andreas Harloff
Department of Neurology and Neurophysiology, Faculty of Medicine, Medical Center—University of Freiburg, University of Freiburg, Germany
A
Anja Hennemuth
Institute of Computer-Assisted Cardiovascular Medicine, Charité - Universitätsmedizin Berlin, Germany; Fraunhofer MEVIS, Bremen, Germany; DZHK (German Centre for Cardiovascular Research), Partner Site Berlin, Germany