Quantifying emphysema in lung screening computed tomography with robust automated lobe segmentation.
Thomas Z LiHo Hin LeeKaiwen XuRiqiang GaoBenoit M DawantFabien MaldonadoKim L SandlerBennett A LandmanPublished in: Journal of medical imaging (Bellingham, Wash.) (2023)
We are the first to develop and validate an automated lobe segmentation algorithm that is robust to smoking-related pathology. We discover a quantitative risk factor, lending further evidence that regional emphysema is independently associated with increased lung cancer incidence. The algorithm is provided at https://github.com/MASILab/EmphysemaSeg.
Keyphrases
- deep learning
- risk factors
- computed tomography
- convolutional neural network
- chronic obstructive pulmonary disease
- machine learning
- lung function
- pulmonary fibrosis
- idiopathic pulmonary fibrosis
- positron emission tomography
- smoking cessation
- magnetic resonance imaging
- high resolution
- dual energy
- cystic fibrosis
- contrast enhanced
- air pollution
- image quality
- single cell
- drug induced
- neural network