Pulmonary emphysema subtypes defined by unsupervised machine learning on CT scans.
Elsa D AngeliniJie YangPallavi P BalteEric A HoffmanAni W ManichaikulYifei SunWei ShenJohn H M AustinNorrina B AllenEugene R BleeckerRussell BowlerMichael H ChoChristopher S CooperDavid CouperMark T DransfieldChristine Kim GarciaMeiLan K HanNadia N HanselEmlyn HughesDavid R JacobsSilva KaselaJoel Daniel KaufmanJohn Shinn KimTuuli LappalainenJoao LimaDaniel MalinskyFernando J MartinezElizabeth C OelsnerVictor E OrtegaRobert PaineWendy PostTess D PottingerMartin R PrinceStephen S RichEdwin K SilvermanBenjamin M SmithAndrew J SwiftKarol E WatsonPrescott G WoodruffAndrew F LaineR Graham BarrPublished in: Thorax (2023)
Large-scale unsupervised machine learning on CT scans defined six reproducible, familiar CT emphysema subtypes that suggest paths to specific diagnosis and personalised therapies in COPD and pre-COPD.
Keyphrases
- machine learning
- dual energy
- chronic obstructive pulmonary disease
- computed tomography
- contrast enhanced
- lung function
- image quality
- artificial intelligence
- positron emission tomography
- big data
- magnetic resonance imaging
- pulmonary hypertension
- deep learning
- magnetic resonance
- cystic fibrosis
- air pollution
- pulmonary fibrosis