MRI lung lobe segmentation in pediatric cystic fibrosis patients using a recurrent neural network trained with publicly accessible CT datasets.
Orso PusterlaRahel HeuleFrancesco SantiniThomas WeikertC Corin WillersSimon AndermattRobin SandkühlerSylvia NyilasPhilipp LatzinOliver BieriGrzegorz BaumanPublished in: Magnetic resonance in medicine (2022)
Recurrent neural network lung lobe segmentation of 2D ufSSFP imaging is feasible, in good agreement with manual segmentations. The proposed workflow might provide access to automated lobe segmentations for various lung MRI examinations and quantitative analyses.
Keyphrases
- neural network
- contrast enhanced
- deep learning
- cystic fibrosis
- end stage renal disease
- magnetic resonance imaging
- high resolution
- convolutional neural network
- ejection fraction
- computed tomography
- newly diagnosed
- chronic kidney disease
- machine learning
- diffusion weighted imaging
- pseudomonas aeruginosa
- prognostic factors
- high throughput
- magnetic resonance
- lung function
- mass spectrometry
- rna seq