Automatic generation of conclusions from neuroradiology MRI reports through natural language processing.
Pilar López-ÚbedaTeodoro Martín NoguerolJorge EscartínAntonio LunaPublished in: Neuroradiology (2024)
The methods demonstrate the potential and effectiveness of customizing state-of-the-art pre-trained models for neuroradiology, yielding automatic MRI report conclusions that nearly match expert quality. Furthermore, these results underscore the importance of designing and pre-training a dedicated language model for radiology report summarization.
Keyphrases
- contrast enhanced
- magnetic resonance imaging
- deep learning
- autism spectrum disorder
- machine learning
- diffusion weighted imaging
- randomized controlled trial
- artificial intelligence
- systematic review
- neural network
- clinical practice
- magnetic resonance
- emergency department
- adverse drug
- climate change
- electronic health record