University of Cambridge > > Isaac Newton Institute Seminar Series > Machine learning tools for large tomographic inverse problems with limited training data

Machine learning tools for large tomographic inverse problems with limited training data

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact nobody.

RNTW02 - Rich and non-linear tomography in medical imaging, materials and non destructive testing

X-ray tomographic inverse problems with limited measurements require strong non-linear constraints. Increasingly, machine learning tools are used to learn these constraints from large collections of representative training data. When using X-ray tomography to image manufactured components, it is often beneficial to target the training data to the specific application, as this can lead to very strong constraints that will allow image reconstruction even if significant amounts of measurements are missing. There are however two fundamental problems with this approach for real applications. Firstly, it is often difficult to collect sufficient training data to train the most advanced machine learning models. Secondly, the inverse problem is extremely large, with billions of measurements used to estimate 3D images with billions of voxels. This further restricts the models that can be trained and used on most computing hardware. We here report on the use of block based 3D image models and show how they can be trained on a single 3D image. This approach can be used for image de-noising as well as a building block in an unrolled optimisation algorithm to solve the tomographic inverse problem. 

This talk is part of the Isaac Newton Institute Seminar Series series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


© 2006-2023, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity