Convolutional neural network-based approach to estimate bulk optical properties in diffuse optical tomography

Sabir, Sohail; Cho, Sanghoon; Kim, Yejin; Pua, Rizza; Heo, Duchang; Kim, Kee Hyun; Choi, Young-Wook; Cho, Seungryong

doi:10.1364/ao.377810

Cited by 36 publications

(29 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This can be explained in parts by the difficulty to obtain high quality training data, costly model evaluations, and limitations of direct reconstruction approaches. Therefore, the initial applications of deep learning methods for DOT have been based on directly learning a non-linear mapping from the boundary measurement data to the spatially distributed optical coefficients [33]- [35] where the reconstruction operator was learned either by classical neural networks [33] or using convolutional neural networks (CNNs) [34], [35]. The approach was utilised in estimating absolute absorption coefficients [33], difference scattering coefficients [34], and spatially-constant values of both the coefficients [35].…”

Section: Introductionmentioning

confidence: 99%

“…Therefore, the initial applications of deep learning methods for DOT have been based on directly learning a non-linear mapping from the boundary measurement data to the spatially distributed optical coefficients [33]- [35] where the reconstruction operator was learned either by classical neural networks [33] or using convolutional neural networks (CNNs) [34], [35]. The approach was utilised in estimating absolute absorption coefficients [33], difference scattering coefficients [34], and spatially-constant values of both the coefficients [35]. The methods were validated with simulations [33], [34] and with two homogeneous experimental phantoms [35].…”

Section: Introductionmentioning

confidence: 99%

“…The approach was utilised in estimating absolute absorption coefficients [33], difference scattering coefficients [34], and spatially-constant values of both the coefficients [35]. The methods were validated with simulations [33], [34] and with two homogeneous experimental phantoms [35]. Improved estimates in terms of estimation accuracy and computation time were reported.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Model-Based Iterative Learning Approach for Diffuse Optical Tomography

Mozumder

Hauptmann

Nissilä

et al. 2022

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

Diffuse optical tomography (DOT) utilises near-infrared light for imaging spatially distributed optical parameters, typically the absorption and scattering coefficients. The image reconstruction problem of DOT is an ill-posed inverse problem, due to the non-linear light propagation in tissues and limited boundary measurements. The ill-posedness means that the image reconstruction is sensitive to measurement and modelling errors. The Bayesian approach for the inverse problem of DOT offers the possibility of incorporating prior information about the unknowns, rendering the problem less ill-posed. It also allows marginalisation of modelling errors utilising the socalled Bayesian approximation error method. A more recent trend in image reconstruction techniques is the use of deep learning , which has shown promising results in various applications from image processing to tomographic reconstructions. In this work, we study the non-linear DOT inverse problem of estimating the (absolute) absorption and scattering coefficients utilising a 'model-based' learning approach, essentially intertwining learned components with the model equations of DOT. The proposed approach was validated with 2D simulations and 3D experimental data.We demonstrated improved absorption and scattering estimates for targets with a mix of smooth and sharp image features, implying that the proposed approach could learn image features that are difficult to model using standard Gaussian priors. Furthermore, it was shown that the approach can be utilised in compensating for modelling errors due to coarse discretisation enabling computationally efficient solutions. Overall, the approach provided improved computation times compared to a standard Gauss-Newton iteration.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Model-Based Iterative Learning Approach for Diffuse Optical Tomography

Mozumder

Hauptmann

Nissilä

et al. 2022

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

show abstract

“…Deep learning has also been applied to spatial frequencydomain imaging (SFDI) to recover the optical properties accurately and quickly from the diffuse reflectance image. [24][25][26][27] Additionally, Sabir et al 28 used a popular deep learning algorithm, convolutional neural network (CNN), to estimate the bulk tissue optical properties. However, they studied only a homogenous, semi-infinite medium and did not consider the presence of the chest wall.…”

Section: Introductionmentioning

confidence: 99%

Deep learning-based method to accurately estimate breast tissue optical properties in the presence of the chest wall

Zhang

Zou

et al. 2021

J. Biomed. Opt.

View full text Add to dashboard Cite

Significance: In general, image reconstruction methods used in diffuse optical tomography (DOT) are based on diffusion approximation, and they consider the breast tissue as a homogenous, semi-infinite medium. However, the semi-infinite medium assumption used in DOT reconstruction is not valid when the chest wall is underneath the breast tissue. Aim:We aim to reduce the chest wall's effect on the estimated average optical properties of breast tissue and obtain accurate forward model for DOT reconstruction.Approach: We propose a deep learning-based neural network approach where a convolution neural network (CNN) is trained to simultaneously obtain accurate optical property values for both the breast tissue and the chest wall.Results: The CNN model shows great promise in reducing errors in estimating the optical properties of the breast tissue in the presence of a shallow chest wall. For patient data, the CNN model predicted the breast tissue optical absorption coefficient, which was independent of chest wall depth.Conclusions: Our proposed method can be readily used in DOT and diffuse spectroscopy measurements to improve the accuracy of estimated tissue optical properties.

show abstract

“…This can be explained in parts by the difficulty to obtain high quality training data, costly model evaluations, and limitations of direct reconstruction approaches. Therefore, the initial applications of deep learning methods for DOT have been based on directly learning a non-linear mapping from the boundary measurement data to the spatially distributed optical coefficients [29][30][31] where the reconstruction operator was learned either by a classic neural networks [29] by or using convolutional neural networks (CNNs) [30,31]. The approach was utilised in estimating absolute absorption coefficients [29], difference scattering coefficients [30], and spatially-constant values of both the coefficients [31].…”

Section: Introductionmentioning

confidence: 99%

A model-based iterative learning approach for diffuse optical tomography

Mozumder¹,

Hauptmann²,

Nissilä³

et al. 2021

Preprint

View full text Add to dashboard Cite

Diffuse optical tomography (DOT) utilises near-infrared light for imaging spatially distributed optical parameters, typically the absorption and scattering coefficients. The image reconstruction problem of DOT is an ill-posed inverse problem, due to the non-linear light propagation in tissues and limited boundary measurements. The ill-posedness means that the image reconstruction is sensitive to measurement and modelling errors. The Bayesian approach for the inverse problem of DOT offers the possibility of incorporating prior information about the unknowns, rendering the problem less ill-posed. It also allows marginalisation of modelling errors utilising the so-called Bayesian approximation error method. A more recent trend in image reconstruction techniques is the use of deep learning techniques, which has shown promising results in various applications from image processing to tomographic reconstructions. In this work, we study the non-linear DOT inverse problem of estimating the absorption and scattering coefficients utilising a 'modelbased' learning approach, essentially intertwining learned components with the model equations of DOT. The proposed approach was validated with 2D simulations and 3D experimental data. We demonstrated improved absorption and scattering estimates for targets with a mix of smooth and sharp image features, implying that the proposed approach could learn image features that are difficult to model using standard Gaussian priors. Furthermore, it was shown that the approach can be utilised in compensating for modelling errors due to coarse discretisation enabling computationally efficient solutions. Overall, the approach provided improved computation times compared to a standard Gauss-Newton iteration.

show abstract

Convolutional neural network-based approach to estimate bulk optical properties in diffuse optical tomography

Cited by 36 publications

References 51 publications

A Model-Based Iterative Learning Approach for Diffuse Optical Tomography

A Model-Based Iterative Learning Approach for Diffuse Optical Tomography

Deep learning-based method to accurately estimate breast tissue optical properties in the presence of the chest wall

A model-based iterative learning approach for diffuse optical tomography

Contact Info

Product

Resources

About