Signal Domain Learning Approach for Optoacoustic Image Reconstruction from Limited View Data

Anna Klimovskaia Susmelj, Berkan Lafci, Firat Ozdemir, Neda Davoudi, Xose Luis Dean-Ben, Fernando Perez-Cruz, Daniel Razansky
Proceedings of The 5th International Conference on Medical Imaging with Deep Learning, PMLR 172:1173-1191, 2022.

Abstract

Multi-spectral optoacoustic tomography (MSOT) relies on optical excitation of tissues with subsequent detection of the generated ultrasound waves.Optimal image quality in MSOT is achieved by detection of signals from a broad tomographic view.However, due to physical constraints and other cost-related considerations, most imaging systems are implemented with probes having limited tomographic coverage around the imaged object, such as linear array transducers often employed for clinical ultrasound (US) imaging.MSOT image reconstruction from limited-view data results in arc-shaped image artifacts and disrupted shape of the vascular structures. Deep learning methods have previously been used to recover MSOT images from incomplete tomographic data, albeit poor performance was attained when training with data from simulations or other imaging modalities.We propose a two-step method consisting of i) style transfer for domain adaptation between simulated and experimental MSOT signals, and ii) supervised training on simulated data to recover missing tomographic signals in realistic clinical data. The method is shown capable of correcting images reconstructed from sub-optimal probe geometries using only signal domain data without the need for training with ground truth (GT) full-view images.

Cite this Paper

BibTeX
@InProceedings{pmlr-v172-susmelj22a, title = {Signal Domain Learning Approach for Optoacoustic Image Reconstruction from Limited View Data}, author = {Susmelj, Anna Klimovskaia and Lafci, Berkan and Ozdemir, Firat and Davoudi, Neda and Dean-Ben, Xose Luis and Perez-Cruz, Fernando and Razansky, Daniel}, booktitle = {Proceedings of The 5th International Conference on Medical Imaging with Deep Learning}, pages = {1173--1191}, year = {2022}, editor = {Konukoglu, Ender and Menze, Bjoern and Venkataraman, Archana and Baumgartner, Christian and Dou, Qi and Albarqouni, Shadi}, volume = {172}, series = {Proceedings of Machine Learning Research}, month = {06--08 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v172/susmelj22a/susmelj22a.pdf}, url = {https://proceedings.mlr.press/v172/susmelj22a.html}, abstract = {Multi-spectral optoacoustic tomography (MSOT) relies on optical excitation of tissues with subsequent detection of the generated ultrasound waves.Optimal image quality in MSOT is achieved by detection of signals from a broad tomographic view.However, due to physical constraints and other cost-related considerations, most imaging systems are implemented with probes having limited tomographic coverage around the imaged object, such as linear array transducers often employed for clinical ultrasound (US) imaging.MSOT image reconstruction from limited-view data results in arc-shaped image artifacts and disrupted shape of the vascular structures. Deep learning methods have previously been used to recover MSOT images from incomplete tomographic data, albeit poor performance was attained when training with data from simulations or other imaging modalities.We propose a two-step method consisting of i) style transfer for domain adaptation between simulated and experimental MSOT signals, and ii) supervised training on simulated data to recover missing tomographic signals in realistic clinical data. The method is shown capable of correcting images reconstructed from sub-optimal probe geometries using only signal domain data without the need for training with ground truth (GT) full-view images.} }
Endnote
%0 Conference Paper %T Signal Domain Learning Approach for Optoacoustic Image Reconstruction from Limited View Data %A Anna Klimovskaia Susmelj %A Berkan Lafci %A Firat Ozdemir %A Neda Davoudi %A Xose Luis Dean-Ben %A Fernando Perez-Cruz %A Daniel Razansky %B Proceedings of The 5th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2022 %E Ender Konukoglu %E Bjoern Menze %E Archana Venkataraman %E Christian Baumgartner %E Qi Dou %E Shadi Albarqouni %F pmlr-v172-susmelj22a %I PMLR %P 1173--1191 %U https://proceedings.mlr.press/v172/susmelj22a.html %V 172 %X Multi-spectral optoacoustic tomography (MSOT) relies on optical excitation of tissues with subsequent detection of the generated ultrasound waves.Optimal image quality in MSOT is achieved by detection of signals from a broad tomographic view.However, due to physical constraints and other cost-related considerations, most imaging systems are implemented with probes having limited tomographic coverage around the imaged object, such as linear array transducers often employed for clinical ultrasound (US) imaging.MSOT image reconstruction from limited-view data results in arc-shaped image artifacts and disrupted shape of the vascular structures. Deep learning methods have previously been used to recover MSOT images from incomplete tomographic data, albeit poor performance was attained when training with data from simulations or other imaging modalities.We propose a two-step method consisting of i) style transfer for domain adaptation between simulated and experimental MSOT signals, and ii) supervised training on simulated data to recover missing tomographic signals in realistic clinical data. The method is shown capable of correcting images reconstructed from sub-optimal probe geometries using only signal domain data without the need for training with ground truth (GT) full-view images.
APA
Susmelj, A.K., Lafci, B., Ozdemir, F., Davoudi, N., Dean-Ben, X.L., Perez-Cruz, F. & Razansky, D.. (2022). Signal Domain Learning Approach for Optoacoustic Image Reconstruction from Limited View Data. Proceedings of The 5th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 172:1173-1191 Available from https://proceedings.mlr.press/v172/susmelj22a.html.

Related Material