BPD-Neo: An MRI Dataset for Lung-Trachea Segmentation with Clinical Data for Neonatal Bronchopulmonary Dysplasia

TL;DR

This paper introduces BPD-Neo, a comprehensive MRI dataset with clinical data and segmentation models for neonatal lung and trachea, aimed at improving diagnosis and understanding of bronchopulmonary dysplasia.

Contribution

It provides a novel high-resolution 3D MRI dataset with paired segmentations and clinical data for neonatal lung analysis, supporting research in BPD diagnosis.

Findings

Dataset includes 40 neonatal MRI scans with lung and trachea segmentations.

Baseline segmentation models validated against clinical assessments.

Provides clinical data to facilitate further research in neonatal lung imaging.

Abstract

Bronchopulmonary dysplasia (BPD) is a common complication among preterm neonates, with portable X-ray imaging serving as the standard diagnostic modality in neonatal intensive care units (NICUs). However, lung magnetic resonance imaging (MRI) offers a non-invasive alternative that avoids sedation and radiation while providing detailed insights into the underlying mechanisms of BPD. Leveraging high-resolution 3D MRI data, advanced image processing and semantic segmentation algorithms can be developed to assist clinicians in identifying the etiology of BPD. In this dataset, we present MRI scans paired with corresponding semantic segmentations of the lungs and trachea for 40 neonates, the majority of whom are diagnosed with BPD. The imaging data consist of free-breathing 3D stack-of-stars radial gradient echo acquisitions, known as the StarVIBE series. Additionally, we provide comprehensive clinical data and baseline segmentation models, validated against clinical assessments, to support further research and development in neonatal lung imaging.