MvBody: Multi-View-Based Hybrid Transformer Using Optical 3D Body Scan for Explainable Cesarean Section Prediction

📅 2025-11-05
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
This study addresses the challenge of early cesarean section (CS) risk assessment in resource-limited or home-based prenatal settings. We propose an interpretable predictive framework integrating self-reported late-pregnancy clinical data with portable 3D optical body scanning. Methodologically, we introduce MvBody—a novel multi-view Transformer architecture that jointly models 3D geometric body shape features (particularly head-shoulder morphology) and clinical variables for the first time. To enhance generalization under limited sample sizes, we incorporate metric learning; interpretability is ensured via Integrated Gradients, yielding clinically actionable feature attributions. Evaluated on an independent test set, our method achieves 84.62% accuracy and an AUC-ROC of 0.724. Results validate 3D body shape as a low-cost, non-invasive biomarker for CS risk prediction and establish a new paradigm for scalable, explainable antenatal risk stratification in primary care.

Technology Category

Application Category

📝 Abstract
Accurately assessing the risk of cesarean section (CS) delivery is critical, especially in settings with limited medical resources, where access to healthcare is often restricted. Early and reliable risk prediction allows better-informed prenatal care decisions and can improve maternal and neonatal outcomes. However, most existing predictive models are tailored for in-hospital use during labor and rely on parameters that are often unavailable in resource-limited or home-based settings. In this study, we conduct a pilot investigation to examine the feasibility of using 3D body shape for CS risk assessment for future applications with more affordable general devices. We propose a novel multi-view-based Transformer network, MvBody, which predicts CS risk using only self-reported medical data and 3D optical body scans obtained between the 31st and 38th weeks of gestation. To enhance training efficiency and model generalizability in data-scarce environments, we incorporate a metric learning loss into the network. Compared to widely used machine learning models and the latest advanced 3D analysis methods, our method demonstrates superior performance, achieving an accuracy of 84.62% and an Area Under the Receiver Operating Characteristic Curve (AUC-ROC) of 0.724 on the independent test set. To improve transparency and trust in the model's predictions, we apply the Integrated Gradients algorithm to provide theoretically grounded explanations of the model's decision-making process. Our results indicate that pre-pregnancy weight, maternal age, obstetric history, previous CS history, and body shape, particularly around the head and shoulders, are key contributors to CS risk prediction.
Problem

Research questions and friction points this paper is trying to address.

Predicts cesarean section risk using 3D body scans and medical data
Addresses limited medical resources with affordable general devices
Provides explainable predictions for maternal healthcare decisions
Innovation

Methods, ideas, or system contributions that make the work stand out.

Multi-view Transformer network for 3D body scan analysis
Metric learning loss enhances training in data-scarce environments
Integrated Gradients algorithm provides explainable model predictions
🔎 Similar Papers
No similar papers found.
R
Ruting Cheng
Department of Computer Science, The George Washington University, 800 22nd Street NW, Washington DC, 20052, , USA.
Boyuan Feng
Boyuan Feng
Ph.D.@UCSB; SWE@PyTorch
Y
Yijiang Zheng
Department of Computer Science, The George Washington University, 800 22nd Street NW, Washington DC, 20052, , USA.
C
Chuhui Qiu
Department of Computer Science, The George Washington University, 800 22nd Street NW, Washington DC, 20052, , USA.
A
Aizierjiang Aiersilan
Department of Computer Science, The George Washington University, 800 22nd Street NW, Washington DC, 20052, , USA.
J
Joaquin A. Calderon
Department of Obstetrics and Gynecology, The George Washington University, 2150 Pennsylvania Ave. NW, Washington DC, 20037, , USA.
W
Wentao Zhao
Department of Integrative Bioscience and Biomedical Engineering, Waseda University, Takadanobaba, Shinjuku-ku, Tokyo, 162-0075, , Japan.
Q
Qing Pan
Department of Biostatistics and Bioinformatics, The George Washington University, 800 22nd Street NW, Washington DC, 20052, , USA.
J
James K. Hahn
Department of Computer Science, The George Washington University, 800 22nd Street NW, Washington DC, 20052, , USA.