The authors of this review aimed to provide definitions for understanding the methods of machine learning, deep learning, and convolutional neural networks (CNN) and to dive into their roles and potential in the area of thoracic imaging.
Key points
- Deep learning outperforms other machine learning techniques for number of tasks in radiology.
- Convolutional neural network is the most popular deep learning architecture in medical imaging.
- Numerous deep learning algorithms are being currently developed; some of them may become part of clinical routine in the near future.
Article: Deep learning: definition and perspectives for thoracic imaging
Authors: Guillaume Chassagnon, Maria Vakalopolou, Nikos Paragios & Marie-Pierre Revel
