Automated MRI-Based Segmentation of the Cranio-Cervical Venous System Using a Dedicated Deep Learning Pipeline

Read the full article See related articles

Listed in

This article is not in any list yet, why not save it to one of your lists.
Log in to save this article

Abstract

PURPOSE

To develop an automated magnetic resonance imaging based segmentation pipeline for the cranio-cervical venous system (CCVS), a complex anatomical network for which no dedicated segmentation tool is currently available.

MATERIALS AND METHODS

A retrospective single-center cohort of 194 contrast-enhanced cranio-cervical MRI examinations acquired between 2019 and 2024 was used. Manual reference segmentations were initially performed on 50 examinations using 3D Slicer. A nnU-Net v2-based segmentation model was then trained through an iterative process combining automatic segmentation, manual correction, and retraining. A dedicated intermediate model was developed to distinguish the vertebral artery from the surrounding vertebral venous plexus. Segmentation performance was assessed using the Dice Similarity Coefficient (DSC). The complete processing pipeline was integrated into an open-source software application, VenousNetworkAnalyzer (VNA).

RESULTS

The final model achieved a mean DSC of 0.94 (95% CI, 0.93–0.95) in five-fold cross-validation on 106 examinations with manual reference segmentations. Iterative optimization progressively reduced manual processing time from approximately 10 hours of fully manual segmentation to less than 10 minutes of manual correction per patient. Application of the final model to the entire cohort enabled the generation of patient-specific three-dimensional reconstructions of the cranio-cervical venous system. The segmentation workflow was successfully integrated into the VNA software environment, allowing automated processing and visualization of MRI datasets.

CONCLUSION

This study demonstrates the feasibility of automated segmentation of the cranio-cervical venous system from contrast-enhanced MRI using a dedicated deep-learning pipeline. The resulting reduction in processing time and integration into an open-source software platform provide a foundation for future large-scale anatomical studies of cranio-cervical venous drainage.

Summary Statement

An automated nnU-Net-based MRI pipeline enabled segmentation and three-dimensional visualization of the cranio-cervical venous system, reducing manual correction time less than 10 minutes per case.

Key Points

  • -

    A dedicated nnU-Net v2-based pipeline was developed for MRI-based segmentation of the cranio-cervical venous system

  • -

    Iterative model optimization reduced manual processing time from approximately 10 hours to less than 10 minutes per case.

  • -

    The pipeline enabled patient-specific three-dimensional reconstructions and was integrated into a dedicated software environment for visualization and analyzis.

  • Article activity feed