Workshop on Machine Learning for Medical Image Reconstruction Call for Papers
Call for papers MLMIR 2018
1st Workshop on Machine Learning for Medical Image Reconstruction
(in conjunction with MICCAI 2018),
16th September 2018, Granada, Spain
Image reconstruction is currently undergoing a paradigm shift that is
driven by advances in machine learning. Whereas traditionally
transform-based or optimization-based methods have dominated methods
for image reconstruction, machine learning has opened up the
opportunity for new data-driven approaches which have demonstrated a
number of advantages over traditional approaches. In particular, deep
learning techniques have shown significant potential for image
reconstruction and offer interesting new approaches. Finally, machine
learning approaches also offer to the possibility for
application-specific image reconstruction, e.g. in motion-compensated
cardiac or fetal imaging.
This is supported by success of machine learning in other inverse
problems by multiple groups worldwide, with encouraging results and
increasing interest. Coincidentally, this year is the centenary of
the Radon transform and the 250th anniversary of Joseph Fourier’s
birthday, the two transforms that provide the mathematical foundation
for tomography and medical imaging. It seems appropriate and timely
to consider how to invert the Radon transform and Fourier transform
via machine learning, and have this workshop serve as a forum to
reflect this emerging trend of image reconstruction research. In this
respect, it will frame a fresh new way to recharge or redefine the
reconstruction algorithms with extensive prior knowledge for superior
diagnostic performance.
The aim of the workshop is to drive scientific discussion of advanced
machine learning techniques for image acquisition and image
reconstruction, opportunities for new applications as well as
challenges in the evaluation and validation of ML based
reconstruction approaches. Specifically, this will include the topics
such as those listed below (but not limited to):
* Compressed sensing methods
* Sparsity and low-rank methods
* Machine learning for image super-resolution
* Machine learning for image synthesis
* Machine learning for quantitative imaging (including MRF)
* Deep learning for image reconstruction including
o CNN-based approaches
o RNN-based approaches
o Adversarial and generative approaches
o Fusion with traditional reconstruction techniques
* Machine learning for
o X-ray CT image reconstruction (such as for low-dose imaging) ?
o MR image reconstruction (such as for fast imaging)
o SPECT and PET image reconstruction
o Ultrasound and optical imaging
o Multimodality fusion or joint image reconstruction across two or more modalities ?
* Applications of ML for image reconstruction in
o Neuroimaging
o Cardiac imaging
o Abdominal imaging
o Fetal and/or neonatal imaging
* Validation of ML for image reconstruction
Organisers
Daniel Rueckert, Imperial College London, UK
Florian Knoll, New York University, US
Andreas Maier, University of Erlangen, Germany
Keynote Speakers
Jong Chul Ye (KAIST)
Michael Unser (EPFL)
More to follow
Timeline
MICCAI paper results released: 22nd May 2018
Paper submission deadline: 11th
Decisions to authors: 2nd July 2018
Camera-ready submission: 17th July 2018
Workshop: 16th September 2018 (am), Granada, Spain
Website: https://sites.google.com/view/mlmir2018/home