1. Denoising and artefact removal for transthoracic echocardiographic imaging in congenital heart disease: utility of diagnosis specific deep learning algorithms
- Author
-
Wei Li, Robert M Radke, Helmut Baumgartner, Gerhard-Paul Diller, Sonya V. Babu-Narayan, Stefan Orwat, Astrid E. Lammers, and Michael A. Gatzoulis
- Subjects
Adult ,Heart Defects, Congenital ,Male ,Heart disease ,Image quality ,Noise reduction ,Signal-To-Noise Ratio ,030204 cardiovascular system & hematology ,030218 nuclear medicine & medical imaging ,Young Adult ,03 medical and health sciences ,Deep Learning ,0302 clinical medicine ,Predictive Value of Tests ,Image Interpretation, Computer-Assisted ,Humans ,Medicine ,Radiology, Nuclear Medicine and imaging ,Cardiac imaging ,business.industry ,Deep learning ,Reproducibility of Results ,Middle Aged ,medicine.disease ,Acoustic shadow ,Autoencoder ,Atrial switch ,Echocardiography ,Case-Control Studies ,Female ,Artificial intelligence ,Artifacts ,Cardiology and Cardiovascular Medicine ,business ,Algorithm - Abstract
Deep learning (DL) algorithms are increasingly used in cardiac imaging. We aimed to investigate the utility of DL algorithms in de-noising transthoracic echocardiographic images and removing acoustic shadowing artefacts specifically in patients with congenital heart disease (CHD). In addition, the performance of DL algorithms trained on CHD samples was compared to models trained entirely on structurally normal hearts. Deep neural network based autoencoders were built for denoising and removal of acoustic shadowing artefacts based on routine echocardiographic apical 4-chamber views and performance was assessed by visual assessment and quantifying cross entropy. 267 subjects (94 TGA and atrial switch and 39 with ccTGA, 10 Ebstein anomaly, 9 with uncorrected AVSD and 115 normal controls; 56.9% male, age 38.9 ± 15.6 years) with routine transthoracic examinations were included. The autoencoders significantly enhanced image quality across diagnostic subgroups (p
- Published
- 2019
- Full Text
- View/download PDF