Amortized Normalizing Flows for Transcranial Ultrasound with Uncertainty Quantification

Rafael Orozco, Mathias Louboutin, Ali Siahkoohi, Gabrio Rizzuti, Tristan van Leeuwen, Felix Johan Herrmann
Medical Imaging with Deep Learning, PMLR 227:332-349, 2024.

Abstract

We present a novel approach to transcranial ultrasound computed tomography that utilizes normalizing flows to improve the speed of imaging and provide Bayesian uncertainty quantification. Our method combines physics-informed methods and data-driven methods to accelerate the reconstruction of the final image. We make use of a physics-informed summary statistic to incorporate the known ultrasound physics with the goal of compressing large incoming observations. This compression enables efficient training of the normalizing flow and standardizes the size of the data regardless of imaging configurations. The combinations of these methods results in fast uncertainty-aware image reconstruction that generalizes to a variety of transducer configurations. We evaluate our approach with in silico experiments and demonstrate that it can significantly improve the imaging speed while quantifying uncertainty. We validate the quality of our image reconstructions by comparing against the traditional physics-only method and also verify that our provided uncertainty is calibrated with the error.

Cite this Paper

BibTeX
@InProceedings{pmlr-v227-orozco24a, title = {Amortized Normalizing Flows for Transcranial Ultrasound with Uncertainty Quantification}, author = {Orozco, Rafael and Louboutin, Mathias and Siahkoohi, Ali and Rizzuti, Gabrio and van Leeuwen, Tristan and Herrmann, Felix Johan}, booktitle = {Medical Imaging with Deep Learning}, pages = {332--349}, year = {2024}, editor = {Oguz, Ipek and Noble, Jack and Li, Xiaoxiao and Styner, Martin and Baumgartner, Christian and Rusu, Mirabela and Heinmann, Tobias and Kontos, Despina and Landman, Bennett and Dawant, Benoit}, volume = {227}, series = {Proceedings of Machine Learning Research}, month = {10--12 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v227/orozco24a/orozco24a.pdf}, url = {https://proceedings.mlr.press/v227/orozco24a.html}, abstract = {We present a novel approach to transcranial ultrasound computed tomography that utilizes normalizing flows to improve the speed of imaging and provide Bayesian uncertainty quantification. Our method combines physics-informed methods and data-driven methods to accelerate the reconstruction of the final image. We make use of a physics-informed summary statistic to incorporate the known ultrasound physics with the goal of compressing large incoming observations. This compression enables efficient training of the normalizing flow and standardizes the size of the data regardless of imaging configurations. The combinations of these methods results in fast uncertainty-aware image reconstruction that generalizes to a variety of transducer configurations. We evaluate our approach with in silico experiments and demonstrate that it can significantly improve the imaging speed while quantifying uncertainty. We validate the quality of our image reconstructions by comparing against the traditional physics-only method and also verify that our provided uncertainty is calibrated with the error.} }
Endnote
%0 Conference Paper %T Amortized Normalizing Flows for Transcranial Ultrasound with Uncertainty Quantification %A Rafael Orozco %A Mathias Louboutin %A Ali Siahkoohi %A Gabrio Rizzuti %A Tristan van Leeuwen %A Felix Johan Herrmann %B Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2024 %E Ipek Oguz %E Jack Noble %E Xiaoxiao Li %E Martin Styner %E Christian Baumgartner %E Mirabela Rusu %E Tobias Heinmann %E Despina Kontos %E Bennett Landman %E Benoit Dawant %F pmlr-v227-orozco24a %I PMLR %P 332--349 %U https://proceedings.mlr.press/v227/orozco24a.html %V 227 %X We present a novel approach to transcranial ultrasound computed tomography that utilizes normalizing flows to improve the speed of imaging and provide Bayesian uncertainty quantification. Our method combines physics-informed methods and data-driven methods to accelerate the reconstruction of the final image. We make use of a physics-informed summary statistic to incorporate the known ultrasound physics with the goal of compressing large incoming observations. This compression enables efficient training of the normalizing flow and standardizes the size of the data regardless of imaging configurations. The combinations of these methods results in fast uncertainty-aware image reconstruction that generalizes to a variety of transducer configurations. We evaluate our approach with in silico experiments and demonstrate that it can significantly improve the imaging speed while quantifying uncertainty. We validate the quality of our image reconstructions by comparing against the traditional physics-only method and also verify that our provided uncertainty is calibrated with the error.
APA
Orozco, R., Louboutin, M., Siahkoohi, A., Rizzuti, G., van Leeuwen, T. & Herrmann, F.J.. (2024). Amortized Normalizing Flows for Transcranial Ultrasound with Uncertainty Quantification. Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 227:332-349 Available from https://proceedings.mlr.press/v227/orozco24a.html.

Related Material