View in EDS

Deep Learning Diffuse Optical Tomography.

Saved in:

Bibliographic Details
Title:	Deep Learning Diffuse Optical Tomography.
Authors:	Yoo, Jaejun¹ (AUTHOR) jaejun2004@gmail.com, Sabir, Sohail¹ (AUTHOR) sohail01@kaist.ac.kr, Heo, Duchang² (AUTHOR) dcheo@keri.re.kr, Kim, Kee Hyun² (AUTHOR) khkim1@keri.re.kr, Wahab, Abdul¹ (AUTHOR) wahab@kaist.ac.kr, Choi, Yoonseok³ (AUTHOR) yschoi21rad@gmail.com, Lee, Seul-I⁴ (AUTHOR) si120919@gmail.com, Chae, Eun Young⁴ (AUTHOR) chaeey@hanmail.net, Kim, Hak Hee⁴ (AUTHOR) hhkim@amc.seoul.kr, Bae, Young Min² (AUTHOR) kimbym@keri.re.kr, Choi, Young-Wook² (AUTHOR) ywchoi@keri.re.kr, Cho, Seungryong¹ (AUTHOR) scho@kaist.ac.kr, Ye, Jong Chul¹ (AUTHOR) jong.ye@kaist.ac.kr
Source:	IEEE Transactions on Medical Imaging. Apr2020, Vol. 39 Issue 4, p877-887. 11p.
Subjects:	Optical tomography, Scattering (Physics), Photon scattering, Artificial neural networks, Deep learning, Integral equations, Nonlinear optics
Abstract:	Diffuse optical tomography (DOT) has been investigated as an alternative imaging modality for breast cancer detection thanks to its excellent contrast to hemoglobin oxidization level. However, due to the complicated non-linear photon scattering physics and ill-posedness, the conventional reconstruction algorithms are sensitive to imaging parameters such as boundary conditions. To address this, here we propose a novel deep learning approach that learns non-linear photon scattering physics and obtains an accurate three dimensional (3D) distribution of optical anomalies. In contrast to the traditional black-box deep learning approaches, our deep network is designed to invert the Lippman-Schwinger integral equation using the recent mathematical theory of deep convolutional framelets. As an example of clinical relevance, we applied the method to our prototype DOT system. We show that our deep neural network, trained with only simulation data, can accurately recover the location of anomalies within biomimetic phantoms and live animals without the use of an exogenous contrast agent. [ABSTRACT FROM AUTHOR]
	Copyright of IEEE Transactions on Medical Imaging is the property of IEEE and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	Engineering Source

Description
Abstract:	Diffuse optical tomography (DOT) has been investigated as an alternative imaging modality for breast cancer detection thanks to its excellent contrast to hemoglobin oxidization level. However, due to the complicated non-linear photon scattering physics and ill-posedness, the conventional reconstruction algorithms are sensitive to imaging parameters such as boundary conditions. To address this, here we propose a novel deep learning approach that learns non-linear photon scattering physics and obtains an accurate three dimensional (3D) distribution of optical anomalies. In contrast to the traditional black-box deep learning approaches, our deep network is designed to invert the Lippman-Schwinger integral equation using the recent mathematical theory of deep convolutional framelets. As an example of clinical relevance, we applied the method to our prototype DOT system. We show that our deep neural network, trained with only simulation data, can accurately recover the location of anomalies within biomimetic phantoms and live animals without the use of an exogenous contrast agent. [ABSTRACT FROM AUTHOR]
ISSN:	02780062
DOI:	10.1109/TMI.2019.2936522