Near-Exact Recovery for Tomographic Inverse Problems via Deep Learning

Martin Genzel, Ingo Gühring, Jan Macdonald, Maximilian März
Proceedings of the 39th International Conference on Machine Learning, PMLR 162:7368-7381, 2022.

Abstract

This work is concerned with the following fundamental question in scientific machine learning: Can deep-learning-based methods solve noise-free inverse problems to near-perfect accuracy? Positive evidence is provided for the first time, focusing on a prototypical computed tomography (CT) setup. We demonstrate that an iterative end-to-end network scheme enables reconstructions close to numerical precision, comparable to classical compressed sensing strategies. Our results build on our winning submission to the recent AAPM DL-Sparse-View CT Challenge. Its goal was to identify the state-of-the-art in solving the sparse-view CT inverse problem with data-driven techniques. A specific difficulty of the challenge setup was that the precise forward model remained unknown to the participants. Therefore, a key feature of our approach was to initially estimate the unknown fanbeam geometry in a data-driven calibration step. Apart from an in-depth analysis of our methodology, we also demonstrate its state-of-the-art performance on the open-access real-world dataset LoDoPaB CT.

Cite this Paper

BibTeX
@InProceedings{pmlr-v162-genzel22a, title = {Near-Exact Recovery for Tomographic Inverse Problems via Deep Learning}, author = {Genzel, Martin and G{\"u}hring, Ingo and Macdonald, Jan and M{\"a}rz, Maximilian}, booktitle = {Proceedings of the 39th International Conference on Machine Learning}, pages = {7368--7381}, year = {2022}, editor = {Chaudhuri, Kamalika and Jegelka, Stefanie and Song, Le and Szepesvari, Csaba and Niu, Gang and Sabato, Sivan}, volume = {162}, series = {Proceedings of Machine Learning Research}, month = {17--23 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v162/genzel22a/genzel22a.pdf}, url = {https://proceedings.mlr.press/v162/genzel22a.html}, abstract = {This work is concerned with the following fundamental question in scientific machine learning: Can deep-learning-based methods solve noise-free inverse problems to near-perfect accuracy? Positive evidence is provided for the first time, focusing on a prototypical computed tomography (CT) setup. We demonstrate that an iterative end-to-end network scheme enables reconstructions close to numerical precision, comparable to classical compressed sensing strategies. Our results build on our winning submission to the recent AAPM DL-Sparse-View CT Challenge. Its goal was to identify the state-of-the-art in solving the sparse-view CT inverse problem with data-driven techniques. A specific difficulty of the challenge setup was that the precise forward model remained unknown to the participants. Therefore, a key feature of our approach was to initially estimate the unknown fanbeam geometry in a data-driven calibration step. Apart from an in-depth analysis of our methodology, we also demonstrate its state-of-the-art performance on the open-access real-world dataset LoDoPaB CT.} }
Endnote
%0 Conference Paper %T Near-Exact Recovery for Tomographic Inverse Problems via Deep Learning %A Martin Genzel %A Ingo Gühring %A Jan Macdonald %A Maximilian März %B Proceedings of the 39th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2022 %E Kamalika Chaudhuri %E Stefanie Jegelka %E Le Song %E Csaba Szepesvari %E Gang Niu %E Sivan Sabato %F pmlr-v162-genzel22a %I PMLR %P 7368--7381 %U https://proceedings.mlr.press/v162/genzel22a.html %V 162 %X This work is concerned with the following fundamental question in scientific machine learning: Can deep-learning-based methods solve noise-free inverse problems to near-perfect accuracy? Positive evidence is provided for the first time, focusing on a prototypical computed tomography (CT) setup. We demonstrate that an iterative end-to-end network scheme enables reconstructions close to numerical precision, comparable to classical compressed sensing strategies. Our results build on our winning submission to the recent AAPM DL-Sparse-View CT Challenge. Its goal was to identify the state-of-the-art in solving the sparse-view CT inverse problem with data-driven techniques. A specific difficulty of the challenge setup was that the precise forward model remained unknown to the participants. Therefore, a key feature of our approach was to initially estimate the unknown fanbeam geometry in a data-driven calibration step. Apart from an in-depth analysis of our methodology, we also demonstrate its state-of-the-art performance on the open-access real-world dataset LoDoPaB CT.
APA
Genzel, M., Gühring, I., Macdonald, J. & März, M.. (2022). Near-Exact Recovery for Tomographic Inverse Problems via Deep Learning. Proceedings of the 39th International Conference on Machine Learning, in Proceedings of Machine Learning Research 162:7368-7381 Available from https://proceedings.mlr.press/v162/genzel22a.html.

Related Material