Fully convolutional networks in medical imaging: Applications to image enhancement and recognition
Baumgartner CF, Oktay O, Rueckert D (2017)
Publication Type: Book chapter / Article in edited volumes
Publication year: 2017
Publisher: Springer London
Series: Advances in Computer Vision and Pattern Recognition
Pages Range: 159-179
DOI: 10.1007/978-3-319-42999-1_10
Abstract
Convolutional neural networks (CNNs) are hierarchical models that have immense representational capacity and have been successfully applied to computer vision problems including object localisation, classification and super-resolution. A particular example of CN Nmodels, knownas fully convolutional network (FCN), has been shown to offer improved computational efficiency and representation learning capabilities due to simplermodel parametrisation and spatial consistency of extracted features. In this chapter, we demonstrate the power and applicability of this particular model on two medical imaging tasks, image enhancement via super-resolution and image recognition. In both examples, experimental results show that FCN models can significantly outperform traditional learning-based approaches while achieving real-time performance. Additionally, we demonstrate that the proposed image classification FCN model can be used in organ localisation task as well without requiring additional training data.
Involved external institutions
United Kingdom (GB)How to cite
APA:
Baumgartner, C.F., Oktay, O., & Rueckert, D. (2017). Fully convolutional networks in medical imaging: Applications to image enhancement and recognition. In (pp. 159-179). Springer London.
MLA:
Baumgartner, Christian F., Ozan Oktay, and Daniel Rueckert. "Fully convolutional networks in medical imaging: Applications to image enhancement and recognition." Springer London, 2017. 159-179.
BibTeX: Download