A robust and scalable image analysis framework for phenotyping human thoracic aorta
- 1University of Miami
Abstract
Large-scale phenotyping of the thoracic aorta requires a workflow in which every step, from segmentation to phenotype extraction, runs without manual intervention. We present a robust and scalable framework that converts contrast-enhanced CT into anatomical landmarks, a patient-specific quadrilateral mesh, a wall-stress field and regional phenotypes of the thoracic aorta. Four nnU-Net segmentation tasks delineate the aorta, its anatomical regions and two partitions of the aortic root. A surface-curve-point procedure derives the annulus, the sinotubular junction, the ostia of the supra-aortic branches, the cusp nadirs and the commissures from the interfaces between segmented regions. We fit a structured template of 24,882 quadrilateral elements to the segmented aortic surface by staged, differentiable mesh deformation and compute the transmural mean wall stress with PyTorch-FEA. The structured mesh provides node-to-node correspondence across patients, anchored to the anatomy by the landmarks, from which the framework extracts regional morphological and biomechanical phenotypes.
Related
- A miniaturized Arabidopsis thaliana - Botrytis cinerea seedling pathosystem and the GreenDayz workflow for longitudinal image-based phenotyping
- Deep aerenchyma: a transformer-based pipeline for scalable phenotyping of rice root aerenchyma lacunae across environments
- FaceKit: a Toolkit for Interpretable Facial Phenotyping, Synthetic Image Generation and Privacy Analysis in Rare Diseases
- From smartphone to gene: Automated image-based phenotyping captures flowering diversity of common buckwheat
- Large-scale GWAS integrated with image-based phenotyping reveals loci and trait-associated markers for Perilla frutescens seed traits.
BibTeX
@misc{chen2026robust,
title = {{A robust and scalable image analysis framework for phenotyping human thoracic aorta}},
author = {J. Chen and L. Qian and R. Gong and C. Sun and T. Pham and C. Martin and M. Zafar and J. Elefteriades and W. Sun and L. Liang},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.11.758402},
url = {https://www.biorxiv.org/content/10.64898/2026.10.11.758402v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - A robust and scalable image analysis framework for phenotyping human thoracic aorta
AU - J. Chen
AU - L. Qian
AU - R. Gong
AU - C. Sun
AU - T. Pham
AU - C. Martin
AU - M. Zafar
AU - J. Elefteriades
AU - W. Sun
AU - L. Liang
PY - 2026
DA - 2026/10/11
PB - bioRxiv
DO - 10.64898/2026.10.11.758402
UR - https://www.biorxiv.org/content/10.64898/2026.10.11.758402v1
AB - Large-scale phenotyping of the thoracic aorta requires a workflow in which every step, from segmentation to phenotype extraction, runs without manual intervention. We present a robust and scalable framework that converts contrast-enhanced CT into anatomical landmarks, a patient-specific quadrilateral mesh, a wall-stress field and regional phenotypes of the thoracic aorta. Four nnU-Net segmentation tasks delineate the aorta, its anatomical regions and two partitions of the aortic root. A surface-curve-point procedure derives the annulus, the sinotubular junction, the ostia of the supra-aortic branches, the cusp nadirs and the commissures from the interfaces between segmented regions. We fit a structured template of 24,882 quadrilateral elements to the segmented aortic surface by staged, differentiable mesh deformation and compute the transmural mean wall stress with PyTorch-FEA. The structured mesh provides node-to-node correspondence across patients, anchored to the anatomy by the landmarks, from which the framework extracts regional morphological and biomechanical phenotypes.
ER -