MR-CT multi-atlas registration guided by fully automated brain structure segmentation with CNNs.
Sina WalluscheckLuca CanaliniHannah StrohmSusanne DiekmannJan KleinStefan HeldmannPublished in: International journal of computer assisted radiology and surgery (2022)
Our registration approach is a fully automated solution to register MRI atlas images to CT scans and thus obtain detailed anatomical information. The proposed CNN segmentation method can be used to obtain masks of ventricles and brain volume which guide the registration.
Keyphrases
- deep learning
- contrast enhanced
- convolutional neural network
- computed tomography
- magnetic resonance imaging
- dual energy
- magnetic resonance
- resting state
- white matter
- single cell
- machine learning
- image quality
- diffusion weighted imaging
- high throughput
- functional connectivity
- positron emission tomography
- blood brain barrier