Improved bias and reproducibility of coronary artery calcification features using deconvolution.
Yingnan SongAmmar HooriHao WuMani VembarSadeer Al-KindiLeslie CiancibelloJames G TerryDavid R JacobsJohn Jeffrey CarrPublished in: Journal of medical imaging (Bellingham, Wash.) (2023)
Deconvolution improves bias and reproducibility of multiple features extracted from individual calcifications in CT calcium score exams. Blind deconvolution is useful for improving feature assessments of coronary calcification in archived datasets.
Keyphrases
- coronary artery
- pulmonary artery
- chronic kidney disease
- coronary artery disease
- computed tomography
- machine learning
- image quality
- contrast enhanced
- deep learning
- magnetic resonance imaging
- rna seq
- heart failure
- magnetic resonance
- positron emission tomography
- single cell
- pulmonary hypertension
- aortic stenosis
- pulmonary arterial hypertension