2020
DOI: 10.1109/tmi.2019.2936522
|View full text |Cite
|
Sign up to set email alerts
|

Deep Learning Diffuse Optical Tomography

Abstract: and AW is currently with the NUTECH

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
105
0
1

Year Published

2020
2020
2023
2023

Publication Types

Select...
6
2

Relationship

1
7

Authors

Journals

citations
Cited by 102 publications
(106 citation statements)
references
References 31 publications
0
105
0
1
Order By: Relevance
“…The readers were fellowship-trained, dedicated breast radiologists and had more than 7 years of experience with DBT. They also had experience with DOT using biomimetic phantoms and animals, and had participated in previous study involving DOT technology 19 . Each reader independently completed three separate sessions: (1) reconstructed DBT alone, (2) reconstructed DOT alone, and (3) DBT/DOT fusion images.…”
Section: Methodsmentioning
confidence: 99%
“…The readers were fellowship-trained, dedicated breast radiologists and had more than 7 years of experience with DBT. They also had experience with DOT using biomimetic phantoms and animals, and had participated in previous study involving DOT technology 19 . Each reader independently completed three separate sessions: (1) reconstructed DBT alone, (2) reconstructed DOT alone, and (3) DBT/DOT fusion images.…”
Section: Methodsmentioning
confidence: 99%
“…First condition is that no photons travel in an inward direction at boundary except source photons. Diffusion equation also cannot satisfy this condition precisely, rather it is assumed that total inward directed current is zero [11]- [15].…”
Section: Boundary Conditionsmentioning
confidence: 99%
“…An ill-posed problem has no solutions in desired class or has many solution, or solution procedure is unstable [15] [16] [17] [18]. In this research case, this means that there are a smaller number of independent measurements than unknown pixel values.…”
Section: Ill-posednessmentioning
confidence: 99%
“…While our approach is consistent with the recent trend of using deep learning architectures for image reconstruction [22][23][24][25][26][27][28][29][30], it is fundamentally different in the sense that due to multiple scattering our measurement operator is both nonlinear and object dependent (and hence unknown). Our approach is also related to the recent work on reverse photon migration for diffuse optical tomography [31]. However, our focus is on diffractive imaging, where the light propagation is assumed to be deterministic, rather than stochastic as in [31].…”
Section: Introductionmentioning
confidence: 99%
“…Our approach is also related to the recent work on reverse photon migration for diffuse optical tomography [31]. However, our focus is on diffractive imaging, where the light propagation is assumed to be deterministic, rather than stochastic as in [31]. Finally, we extensively validated the proposed method on several simulated and real datasets by comparing the method against recent optimization-based approaches based on the Lippmann-Schwinger (LS) model and the TV regularizer [12,14].…”
Section: Introductionmentioning
confidence: 99%