Related Experiment Video
Updated: Jun 20, 2026
Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
Published on: December 19, 2020
Automated MRI Lung Segmentation and 3D Morphologic Features for Quantification of Neonatal Lung Disease
Benedikt Mairhörmann1, Alejandra Castelblanco1, Friederike Häfner1
1From the Computational Health Center (B.M., A.C., D.W., B.S.), Institute for Lung Health and Immunity and Comprehensive Pneumology Center (F.H., L.H., A.H.), and Institute of AI for Health (D.W.), Helmholtz Zentrum München, Member of the German Center for Lung Research (DZL), Ingolstädter Landstrasse 1, 85764 Neuherberg, Germany; Department of Neonatology, Perinatal Center (F.H., A.F., K.F.), Department of Radiology (V.K., S.S., O.D.), and Center for Comprehensive Developmental Care (CDeCLMU) at the Interdisciplinary Social Pediatric Center, Dr. von Hauner Children's Hospital (A.H.), Hospital of the Ludwig-Maximilian University, Munich, Germany; Department of General Pediatrics & Neonatology, Justus-Liebig-University, Member of the German Center for Lung Research (DZL), Giessen, Germany (H.E.); Division of Neonatology and Pediatric Intensive Care Medicine, Department of Pediatrics and Adolescent Medicine, University Medical Center Ulm, Ulm, Germany (H.E.); and Department of Mathematics, Technical University of Munich, Munich, Germany (B.S.).
Purpose:
To analyze the performance of deep learning (DL) models for segmentation of the neonatal lung in MRI and investigate the use of automated MRI-based features for assessment of neonatal lung disease.
Materials And Methods:
Quiet-breathing MRI was prospectively performed in two independent cohorts of preterm infants (median gestational age, 26.57 weeks; IQR, 25.3-28.6 weeks; 55 female and 48 male infants) with (n = 86) and without (n = 21) chronic lung disease (bronchopulmonary dysplasia [BPD]). Convolutional neural networks were developed for lung segmentation, and a three-dimensional reconstruction was used to calculate MRI features for lung volume, shape, pixel intensity, and surface. These features were explored as indicators of BPD and disease-associated lung structural remodeling through correlation with lung injury scores and multinomial models for BPD severity stratification.
Results:
The lung segmentation model reached a volumetric Dice coefficient of 0.908 in cross-validation and 0.880 on the independent test dataset, matching expert-level performance across disease grades. MRI lung features demonstrated significant correlations with lung injury scores and added structural information for the separation of neonates with BPD (BPD vs no BPD: average area under the receiver operating characteristic curve [AUC], 0.92 ± 0.02 [SD]; no or mild BPD vs moderate or severe BPD: average AUC, 0.84 ± 0.03).
Conclusion:
This study demonstrated high performance of DL models for MRI neonatal lung segmentation and showed the potential of automated MRI features for diagnostic assessment of neonatal lung disease while avoiding radiation exposure.Keywords: Bronchopulmonary Dysplasia, Chronic Lung Disease, Preterm Infant, Lung Segmentation, Lung MRI, BPD Severity Assessment, Deep Learning, Lung Imaging Biomarkers, Lung Topology Supplemental material is available for this article. Published under a CC BY 4.0 license.See also the commentary by Parraga and Sharma in this issue.
