Autofocus Layer

Introduction

This is a NiftyNet-based implementation of the autofocus convolutional layer [2]. The WNet implementation in NiftyNet [3][4] was adapted to a 3D WNet and tested with and without autofocus layers.

Citation

If you find the code implemented here useful, please cite the paper:

Stefani, A. (2019). Improving 3D CNNs in Combination with Autofocus Layer for Brain Tumour Segmentation in MRI Scans. (Master’s thesis). University of St Andrews, Scotland. Retrieved from http://url.com.

References

[1] Stefani, A. (2019). Improving 3D CNNs in Combination with Autofocus Layer for Brain Tumour Segmentation in MRI Scans. (Master’s thesis). University of St Andrews, Scotland. Retrieved from http://url.com.

[2] Autofocus Layer for Semantic Segmentation. Y. Qin, K. Kamnitsas, S. Ancha, J. Nanavati, G. Cottrell, A. Criminisi, A. Nori, MICCAI 2018.

[3] Gibson E., Li W., Sudre C., Fidon L., Shakir D. I., Wang G., Eaton-Rosen Z., Gray R., Doel T., Hu Y., Whyntie T., Nachev P., Modat M., Barratt D. C., Ourselin S., Cardoso M. J., Vercauteren T. (2018) NiftyNet: a deep-learning platform for medical imaging. In: Computer Methods and Programs in Biomedicine, vol 158, pages 113-122, 2018.

[4] Li W., Wang G., Fidon L., Ourselin S., Cardoso M.J., Vercauteren T. (2017) On the Compactness, Efficiency, and Representation of 3D Convolutional Networks: Brain Parcellation as a Pretext Task. In: Niethammer M. et al. (eds) Information Processing in Medical Imaging. IPMI 2017. Lecture Notes in Computer Science, vol 10265. Springer, Cham