Automatic segmentation of the carotid artery and internal jugular vein from 2D ultrasound images for 3D vascular reconst
- PDF / 4,449,196 Bytes
- 12 Pages / 595.276 x 790.866 pts Page_size
- 48 Downloads / 200 Views
ORIGINAL ARTICLE
Automatic segmentation of the carotid artery and internal jugular vein from 2D ultrasound images for 3D vascular reconstruction Leah A. Groves1 Elvis C. S. Chen4
· Blake VanBerlo2 · Natan Veinberg2 · Abdulrahman Alboog3 · Terry M. Peters4 ·
Received: 18 November 2019 / Accepted: 14 August 2020 © CARS 2020
Abstract Purpose In the context of analyzing neck vascular morphology, this work formulates and compares Mask R-CNN and UNet-based algorithms to automatically segment the carotid artery (CA) and internal jugular vein (IJV) from transverse neck ultrasound (US). Methods US scans of the neck vasculature were collected to produce a dataset of 2439 images and their respective manual segmentations. Fourfold cross-validation was employed to train and evaluate Mask RCNN and U-Net models. The U-Net algorithm includes a post-processing step that selects the largest connected segmentation for each class. A Mask R-CNN-based vascular reconstruction pipeline was validated by performing a surface-to-surface distance comparison between US and CT reconstructions from the same patient. Results The average CA and IJV Dice scores produced by the Mask R-CNN across the evaluation data from all four sets were 0.90±0.08 and 0.88±0.14. The average Dice scores produced by the post-processed U-Net were 0.81±0.21 and 0.71±0.23, for the CA and IJV, respectively. The reconstruction algorithm utilizing the Mask R-CNN was capable of producing accurate 3D reconstructions with majority of US reconstruction surface points being within 2 mm of the CT equivalent. Conclusions On average, the Mask R-CNN produced more accurate vascular segmentations compared to U-Net. The Mask R-CNN models were used to produce 3D reconstructed vasculature with a similar accuracy to that of a manually segmented CT scan. This implementation of the Mask R-CNN network enables automatic analysis of the neck vasculature and facilitates 3D vascular reconstruction. Keywords Deep learning · US · Surface reconstruction · Surgical guidance · Vasculature · Automatic segmentation
Introduction
B
Leah A. Groves [email protected] Terry M. Peters [email protected] Elvis C. S. Chen [email protected]
1
School of Biomedical Engineering, Western University, London, Canada
2
Schulich School of Medicine and Dentistry, Western University, London, Canada
3
Department of Anesthesia and Perioperative Medicine, Western University, London, Canada
4
Department of Medical Biophysics, School of Biomedical Engineering, Robarts Research, London, Canada
Percutaneous internal jugular vein (IJV) needle insertions are used to access the central venous system [4]. Carotid artery (CA) punctures are one of the most common and severe complications that occur during IJV cannulation [4]. Ultrasound-(US)-guided needle insertions have the potential to reduce complications by providing clinicians with a realtime cross-sectional view of the neck anatomy to visualize the relationship between the IJV and CA in 2D [9,21]. The fact that neck vasculature is extremely variable across the pati
Data Loading...
