MRI Neonatal Lung Segmentation and 3D Morphologic Features

<p>We developed an ensemble of deep convolutional neural networks (2D-UNets) to perform automated neonatal lung segmentation from MRI sequences. A three-dimensional reconstruction is used to calculate MRI features for lung volume, shape, pixel intensity, and surface.</p> <p>In addition, ML Models for severity prediction of Bronchopulmonary Dysplasia (BPD) are implemented as an applied example of the use of MRI lung volumetric features for disease prognosis.</p> <p>This dataset comprises:</p> <ul> <li>Three pretrained 2D-UNet Models for Neonatal MRI Lung Segmentation.</li> <li>Resulting performances and features per MRI-sequence.</li> </ul> <p>See Publication:</p> <p>Automated MRI Lung Segmentation and 3D Morphologic Features for Quantification of Neonatal Lung Disease (2023)</p> <p><a href="https://doi.org/10.1148/ryai.220239">https://doi.org/10.1148/ryai.220239</a></p>