Warmstart Approach for Accelerating Deep Image Prior Reconstruction in Dynamic Tomography

Volume
172
Start Page
713
End Page
725
Citation
5th International Conference on Medical Imaging with Deep Learning (MIDL 2022)
Contribution to Conference
5th International Conference on Medical Imaging with Deep Learning, MIDL 2022
Scopus ID
2-s2.0-85175426643
Deep image prior (DIP) has been successfully used in the field of tomography to obtain high-quality images from under-sampled and noisy measurements. The key advantage of DIP compared to conventional deep-learning based image reconstruction techniques is that it requires no training data and thus can be used in a flexible manner without incorporating domain specific knowledge. The downside of DIP is that it shifts the training step to reconstruction time where usually fast algorithms are required to reduced the latency between acquisition and display of the reconstructed image. In this work we tackle this problem for dynamic tomography scenarios in which a large number of temporally resolved images are taken over time. By initializing the DIP network using a previous frame of the time series, it is possible to significantly reduce the overall reconstruction time. To cope with abrupt changes in the captured time-series, we propose to use an adaptive restart method having the ability to switch between warm- and coldstart depending on the amount of inter-frame changes.
Subjects
deep image prior
dynamic tomography
image reconstruction
magnetic particle imaging
warmstart