Learning three-dimensional aortic root assessment based on sparse annotations.
Johanna BrosigNina KrügerInna KhasyanovaIsaac WamalaMatthias IvantsitsSimon SündermannJörg KempfertStefan HeldmannAnja HennemuthPublished in: Journal of medical imaging (Bellingham, Wash.) (2024)
The presented approach facilitates reproducible annotations. The annotations allow for training accurate segmentation models of the aortic root and LVOT. The segmentation results facilitate reproducible and quantifiable measurements for TAVI planning.
Keyphrases
- aortic valve
- deep learning
- convolutional neural network
- transcatheter aortic valve replacement
- transcatheter aortic valve implantation
- left ventricular
- aortic stenosis
- pulmonary artery
- aortic dissection
- high resolution
- virtual reality
- coronary artery
- machine learning
- coronary artery disease
- pulmonary arterial hypertension
- ejection fraction