Image- versus histogram-based considerations in semantic segmentation of pulmonary hyperpolarized gas images.
Nicholas James TustisonTalissa A AltesKun QingMu HeG Wilson MillerBrian B AvantsYun M ShimJames C GeeJohn P MuglerJaime F MataPublished in: Magnetic resonance in medicine (2021)
Direct optimization within the image domain using convolutional neural networks leverages spatial information, which mitigates problematic issues associated with histogram-based approaches and suggests a preferred future research direction. Further, the entire processing and evaluation framework, including the newly reported deep learning functionality, is available as open source through the well-known Advanced Normalization Tools ecosystem.
Keyphrases
- deep learning
- convolutional neural network
- artificial intelligence
- diffusion weighted imaging
- contrast enhanced
- machine learning
- pulmonary hypertension
- climate change
- diffusion weighted
- current status
- human health
- room temperature
- health information
- magnetic resonance imaging
- risk assessment
- computed tomography
- radiation induced
- radiation therapy
- optical coherence tomography
- clinical evaluation