DeepVox and SAVE-CT: a contrast- and dose-independent 3D deep learning approach for thoracic aorta segmentation and aneurysm prediction using computed tomography scans.
Matheus del-ValleLariza Laura de OliveiraHenrique Cursino VieiraHenrique Min Ho LeeLucas Lembrança PinheiroMaria Fernanda PortugalNewton Shydeo Brandão MiyoshiNelson WoloskerPublished in: CoRR (2023)
Keyphrases
- computed tomography scans
- deep learning
- computed tomography
- medical imaging
- ct scans
- liver segmentation
- ct images
- medical images
- ct volume
- contrast enhanced
- ct data
- x ray
- medical image processing
- x ray images
- fully automatic
- medical image segmentation
- unsupervised learning
- image registration
- anatomical structures
- image segmentation
- segmentation algorithm
- imaging modalities
- image analysis
- medical image analysis
- three dimensional
- intraoperative
- machine learning
- level set
- image reconstruction
- automatic segmentation
- mental models
- computer aided diagnosis
- segmentation method
- image processing
- magnetic resonance imaging
- volume rendering
- weakly supervised
- deformable models
- patient specific
- coronary artery
- mr images
- region of interest
- region growing
- image guided
- energy function
- pulmonary nodules
- markov random field
- ground truth
- multiscale