PUUMA (Placental patch and whole-Uterus dual-branch U-Mamba-based Architecture): Functional MRI Prediction of Gestational Age at Birth and Preterm Risk

2025-09-08

AI Summary

Preterm birth is a leading cause of childhood mortality and lifelong morbidity, yet existing clinical prediction tools exhibit limited performance due to etiological complexity. To address this, we propose PUUMA—a dual-branch U-Mamba deep learning model leveraging T2*-weighted fetal MRI to jointly extract global uterine features and local placental functional features for automated gestational age (GA) estimation and preterm birth risk identification. Evaluated on a prospective cohort of 295 cases, PUUMA achieves a mean absolute error of 3.0 weeks in GA prediction and a sensitivity of 0.67 for preterm birth detection—performance comparable to expert manual assessment. Notably, PUUMA is the first framework to integrate the Mamba architecture into fetal functional MRI analysis, overcoming the limitations of conventional anatomical MRI. It demonstrates the clinical potential of functional MRI coupled with adaptive feature fusion for early risk stratification in high-risk pregnancies.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Reasoning under Uncertainty: Relational Probabilistic Models
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Web Mining and Content Analysis: Large pretrained models with web data
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Preterm birth is a major cause of mortality and lifelong morbidity in childhood. Its complex and multifactorial origins limit the effectiveness of current clinical predictors and impede optimal care. In this study, a dual-branch deep learning architecture (PUUMA) was developed to predict gestational age (GA) at birth using T2* fetal MRI data from 295 pregnancies, encompassing a heterogeneous and imbalanced population. The model integrates both global whole-uterus and local placental features. Its performance was benchmarked against linear regression using cervical length measurements obtained by experienced clinicians from anatomical MRI and other Deep Learning architectures. The GA at birth predictions were assessed using mean absolute error. Accuracy, sensitivity, and specificity were used to assess preterm classification. Both the fully automated MRI-based pipeline and the cervical length regression achieved comparable mean absolute errors (3 weeks) and good sensitivity (0.67) for detecting preterm birth, despite pronounced class imbalance in the dataset. These results provide a proof of concept for automated prediction of GA at birth from functional MRI, and underscore the value of whole-uterus functional imaging in identifying at-risk pregnancies. Additionally, we demonstrate that manual, high-definition cervical length measurements derived from MRI, not currently routine in clinical practice, offer valuable predictive information. Future work will focus on expanding the cohort size and incorporating additional organ-specific imaging to improve generalisability and predictive performance.

Problem

• Predicting gestational age at birth from fetal MRI data
• Assessing preterm birth risk using deep learning architecture
• Integrating global uterine and local placental imaging features

Innovation

• Dual-branch deep learning architecture for MRI prediction
• Integrates global whole-uterus and local placental features
• Automated pipeline using functional T2* fetal MRI data