Real-time Volumetric Imaging for Minimally-Invasive Thoracic Interventions: A Deformable Phantom Study
- 1University of Sydney
Abstract
Objectives: This study aimed to evaluate the ability of VoxelMap, a deep learning framework for 3D respiratory motion estimation, to generate volumetric images in real-time from 2D projections acquired for two deformable lung phantoms on a clinical interventional C-arm angiography system. Materials and Methods: VoxelMap was evaluated using the PixelPrint4D and Casper deformable physical thoracic respiratory phantoms. Four-dimensional cone-beam CT (4D CBCT) images acquired on a clinical fixed-room C-arm angiography system were used for network training and volumetric ground truth. Prediction accuracy was evaluated on withheld respiratory phases using structural similarity index measure (SSIM) and peak signalto-noise ratio (PSNR). Model inference time was measured to assess suitability for continuous real-time processing. Deep ensembles were also used to assess model uncertainty. Correlation between ensemble uncertainty and prediction error was evaluated for both phantoms. Results: VoxelMap achieved high prediction accuracy across withheld respiratory phases in both physical phantoms. SSIM values exceeded 0.92 in all experiments, with a higher performance observed for the Casper phantom (0.969-0.973) than for the PixelPrint4D phantom (0.927-0.943). Model inference times were less than 15 ms for both phantoms which is compatible with real-time processing. Ensemble uncertainty was positively correlated with prediction error in both phantoms, indicating that higher uncertainty was associated with less accurate volumetric predictions. Conclusions: Our study demonstrated that VoxelMap generates accurate volumetric deformations of respiratory anatomy from projections acquired on a clinical interventional C-arm system, with computational inference times compatible with continuous processing. By deriving volumetric information directly from two-dimensional fluoroscopic projections, VoxelMap has the potential to augment continuous fluoroscopic guidance with continuously updated volumetric information. Ensemble uncertainty may provide a potentially useful indicator of prediction reliability. Further studies using clinically representative training data and patient studies is required to establish clinical utility. Our code is available at https://github.com/Image-X-Institute/Voxelmap.
Related
- Unilateral biportal endoscopic thoracic costotransversectomy approach: a minimally invasive technique for thoracic disc herniation—a technical feasibility report
- Transaxillary valve surgery: innovation through simplicity in minimally invasive cardiac surgery
- Transaxillary minimally invasive mitral valve surgery: early and mid-term outcomes in 763 patients
- Optimal surgical approaches to minimally invasive myomectomy for the fertility patient.
- Minimally invasive beating-heart mitral valve surgery: How I do it
BibTeX
@misc{lin2026realtime,
title = {{Real-time Volumetric Imaging for Minimally-Invasive Thoracic Interventions: A Deformable Phantom Study}},
author = {A. S. Lin and A. Biju and A. R. Goode and J. Y. Im and P. B. Noel and M. Bazalova-Carter and T. Reynolds and N. Hindley},
howpublished = {medRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.28.26366767},
url = {https://www.medrxiv.org/content/10.64898/2026.10.28.26366767v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Real-time Volumetric Imaging for Minimally-Invasive Thoracic Interventions: A Deformable Phantom Study
AU - A. S. Lin
AU - A. Biju
AU - A. R. Goode
AU - J. Y. Im
AU - P. B. Noel
AU - M. Bazalova-Carter
AU - T. Reynolds
AU - N. Hindley
PY - 2026
DA - 2026/10/28
PB - medRxiv
DO - 10.64898/2026.10.28.26366767
UR - https://www.medrxiv.org/content/10.64898/2026.10.28.26366767v1
AB - Objectives: This study aimed to evaluate the ability of VoxelMap, a deep learning framework for 3D respiratory motion estimation, to generate volumetric images in real-time from 2D projections acquired for two deformable lung phantoms on a clinical interventional C-arm angiography system. Materials and Methods: VoxelMap was evaluated using the PixelPrint4D and Casper deformable physical thoracic respiratory phantoms. Four-dimensional cone-beam CT (4D CBCT) images acquired on a clinical fixed-room C-arm angiography system were used for network training and volumetric ground truth. Prediction accuracy was evaluated on withheld respiratory phases using structural similarity index measure (SSIM) and peak signalto-noise ratio (PSNR). Model inference time was measured to assess suitability for continuous real-time processing. Deep ensembles were also used to assess model uncertainty. Correlation between ensemble uncertainty and prediction error was evaluated for both phantoms. Results: VoxelMap achieved high prediction accuracy across withheld respiratory phases in both physical phantoms. SSIM values exceeded 0.92 in all experiments, with a higher performance observed for the Casper phantom (0.969-0.973) than for the PixelPrint4D phantom (0.927-0.943). Model inference times were less than 15 ms for both phantoms which is compatible with real-time processing. Ensemble uncertainty was positively correlated with prediction error in both phantoms, indicating that higher uncertainty was associated with less accurate volumetric predictions. Conclusions: Our study demonstrated that VoxelMap generates accurate volumetric deformations of respiratory anatomy from projections acquired on a clinical interventional C-arm system, with computational inference times compatible with continuous processing. By deriving volumetric information directly from two-dimensional fluoroscopic projections, VoxelMap has the potential to augment continuous fluoroscopic guidance with continuously updated volumetric information. Ensemble uncertainty may provide a potentially useful indicator of prediction reliability. Further studies using clinically representative training data and patient studies is required to establish clinical utility. Our code is available at https://github.com/Image-X-Institute/Voxelmap.
ER -