Technology Category
Computer Vision: SegmentationIntelligent Robots: Multimodal Perception & Sensor FusionMachine Learning: Calibration & Uncertainty Quantification
Deep Learning-Based Fetal Lung Segmentation from Diffusion-weighted MRI Images and Lung Maturity Evaluation for Fetal Growth Restriction
🤖 AI Summary
Current assessment of fetal lung maturity in fetal growth restriction (FGR) relies on manual MRI segmentation—time-consuming, subjective, and poorly suited for clinical deployment. Method: We propose the first end-to-end automated framework: (1) 3D nnU-Net for automatic fetal lung segmentation on T2-weighted MRI (mean Dice score: 82.14%); and (2) voxel-wise, unsupervised bi-exponential IVIM modeling on 4D diffusion-weighted MRI to quantify microstructural and perfusion parameters. Contribution/Results: This work introduces the first application of 3D nnU-Net to fetal lung segmentation and demonstrates no statistically significant difference (p > 0.05) between IVIM parameter estimates derived from automated versus manually annotated lung masks. The pipeline substantially improves analytical efficiency, reproducibility, and scalability. It delivers a clinically deployable, quantitative imaging biomarker to support prognostication and individualized perinatal intervention in FGR.
Technology Category
Application Category
📝 Abstract
Fetal lung maturity is a critical indicator for predicting neonatal outcomes and the need for post-natal intervention, especially for pregnancies affected by fetal growth restriction. Intra-voxel incoherent motion analysis has shown promising results for non-invasive assessment of fetal lung development, but its reliance on manual segmentation is time-consuming, thus limiting its clinical applicability. In this work, we present an automated lung maturity evaluation pipeline for diffusion-weighted magnetic resonance images that consists of a deep learning-based fetal lung segmentation model and a model-fitting lung maturity assessment. A 3D nnU-Net model was trained on manually segmented images selected from the baseline frames of 4D diffusion-weighted MRI scans. The segmentation model demonstrated robust performance, yielding a mean Dice coefficient of 82.14%. Next, voxel-wise model fitting was performed based on both the nnU-Net-predicted and manual lung segmentations to quantify IVIM parameters reflecting tissue microstructure and perfusion. The results suggested no differences between the two. Our work shows that a fully automated pipeline is possible for supporting fetal lung maturity assessment and clinical decision-making.
Problem
Research questions and friction points this paper is trying to address.
Automate fetal lung segmentation from MRI for maturity assessment
Replace manual segmentation with deep learning to save time
Evaluate fetal lung maturity for growth restriction cases
Innovation
Methods, ideas, or system contributions that make the work stand out.
Deep learning automates fetal lung segmentation
3D nnU-Net model achieves 82.14% Dice score
Automated pipeline evaluates IVIM parameters non-invasively
🔎 Similar Papers
No similar papers found.
