Quantifying the Impact of Upright Patient Positioning on Cardiac Substructures Using Deep Learning
Abstract
Upright patient positioners with diagnostic-quality vertical CT at treatment isocenter may improve image-guided radiation therapy (RT). However, cardiac substructure (CS) geometry in upright patients remains insufficiently characterized. This work evaluated if a supine-trained deep-learning (DL) CS segmentation model generalizes to upright CT images and quantified posture-dependent CS changes in thoracic patients, to assess potential CS-sparing benefits. 8 thoracic proton therapy patients underwent paired supine/upright 4DCT imaging. 20 CS and lungs were manually labeled on both datasets for positional comparisons. A previously developed supine-trained, DL pipeline generated the same CS, and performance was evaluated using Dice similarity coefficient (DSC) and 95% Hausdorff distance (HD95). Upright CTs were rigidly registered to corresponding supine CTs by aligning the thoracic vertebrae, and CS centroid shifts were measured in the registered coordinate frame and relative to the carina. Paired differences were assessed using Wilcoxon signed-rank tests (p<0.05). The DL model successfully predicted all 20 CS on both upright (DSC, 0.65(0.24); HD95, 7.6(5.6)mm) and supine (DSC, 0.72(0.19); HD95, 5.8(2.6)mm) images yet with lower (p<0.05) performance upright. Upright positioning significantly increased median lung volume by 20.6% (range, -8.9%-42.8%). After vertebral alignment, most CS centroids shifted significantly inferior (median heart shift, 23mm; range, 18-37mm) and anterior (median heart shift, 5.0mm; range, 1.0-13.0mm) when upright. Relative to the carina, most CS shifted significantly inferior and closer anterior-posterior. A supine-trained DL model generalized to upright CT images for CS segmentation. Upright positioning produced increased lung volumes and significant inferior CS displacement, suggesting favorable geometry changes that may support cardiac-sparing workflows.
Related
- Omnidirectional Radiation Detector with Perpendicular Dual Silicon Photomultiplier Readout - Directional Sensitivity and Machine Learning Source Positioning
- Quantifying Patient Setup Error in Total Body Irradiation With Megavoltage Computed Tomography-guided Helical Tomotherapy
- Clinical Commissioning of the First Ultra-Compact Gantry-less Upright Proton Therapy System
- Robust Star Identification and Geometric Correction for Wide-Field Astrometric Positioning
- Real-time APD-based visible light positioning system with quality-aware RSS selection and embedded tracking
BibTeX
@misc{summerfield2026quantifying,
title = {{Quantifying the Impact of Upright Patient Positioning on Cardiac Substructures Using Deep Learning}},
author = {Nicholas Summerfield and Yuhao Yan and Chase Ruff and Mark Pankuch and Shae Gans and Niek Schreuder and Carri K Glide-Hurst},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.36449},
eprint = {2609.36449},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.36449},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Quantifying the Impact of Upright Patient Positioning on Cardiac Substructures Using Deep Learning
AU - Nicholas Summerfield
AU - Yuhao Yan
AU - Chase Ruff
AU - Mark Pankuch
AU - Shae Gans
AU - Niek Schreuder
AU - Carri K Glide-Hurst
PY - 2026
DA - 2026/09/29
PB - arXiv
DO - 10.48550/arxiv.2609.36449
UR - https://arxiv.org/abs/2609.36449
AB - Upright patient positioners with diagnostic-quality vertical CT at treatment isocenter may improve image-guided radiation therapy (RT). However, cardiac substructure (CS) geometry in upright patients remains insufficiently characterized. This work evaluated if a supine-trained deep-learning (DL) CS segmentation model generalizes to upright CT images and quantified posture-dependent CS changes in thoracic patients, to assess potential CS-sparing benefits. 8 thoracic proton therapy patients underwent paired supine/upright 4DCT imaging. 20 CS and lungs were manually labeled on both datasets for positional comparisons. A previously developed supine-trained, DL pipeline generated the same CS, and performance was evaluated using Dice similarity coefficient (DSC) and 95% Hausdorff distance (HD95). Upright CTs were rigidly registered to corresponding supine CTs by aligning the thoracic vertebrae, and CS centroid shifts were measured in the registered coordinate frame and relative to the carina. Paired differences were assessed using Wilcoxon signed-rank tests (p<0.05). The DL model successfully predicted all 20 CS on both upright (DSC, 0.65(0.24); HD95, 7.6(5.6)mm) and supine (DSC, 0.72(0.19); HD95, 5.8(2.6)mm) images yet with lower (p<0.05) performance upright. Upright positioning significantly increased median lung volume by 20.6% (range, -8.9%-42.8%). After vertebral alignment, most CS centroids shifted significantly inferior (median heart shift, 23mm; range, 18-37mm) and anterior (median heart shift, 5.0mm; range, 1.0-13.0mm) when upright. Relative to the carina, most CS shifted significantly inferior and closer anterior-posterior. A supine-trained DL model generalized to upright CT images for CS segmentation. Upright positioning produced increased lung volumes and significant inferior CS displacement, suggesting favorable geometry changes that may support cardiac-sparing workflows.
ER -