Multiple illumination learned spectral decoloring for quantitative optoacoustic oximetry imaging

Kirchner, Thomas; Frenz, Martin

doi:10.1117/1.jbo.26.8.085001

Cited by 10 publications

(12 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This would of course also increase computational costs. Using lightGBM is accurate, computationally cheap and greatly reduced memory usage compared to the random forests of our previous work [26].…”

Section: Discussionmentioning

confidence: 90%

“…These absorbed energy spectra are each normalized with their respective L1 norm resulting into Ĥ𝐼 (𝝀); this is done for each illumination 𝐼 separately. As shown in previous work [26], this normalization makes them equivalent to normalized measured OA signal spectra Ŝ𝐼 (𝝀).…”

Section: Blood Oxygen Saturation Estimation Methodsmentioning

confidence: 98%

“…Our method is an extension of learned spectral decoloring (LSD) [19] and is based on our prior work validating multiple illumination LSD (MI-LSD) on copper and nickel sulfate phantoms [26].…”

Section: Blood Oxygen Saturation Estimation Methodsmentioning

confidence: 99%

“…As machine learning algorithms we used gradient boosting machine regressors as implemented by the LightGBM framework [35]. In initial experiments on data from previous work [26] they proved faster and less memory intensive than random forests, while providing the same precision. Specifically we used a LGBMRegressor with the regression_l1 objective function and 300 estimators (boosting trees) with a maximum of 200 leaves.…”

Section: Blood Oxygen Saturation Estimation Methodsmentioning

confidence: 99%

“…In earlier work [26] we validated such an approach on a highly controlled copper and nickel sulfate [27] phantom model of sO 2 . In this work we:…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Machine learning enabled multiple illumination quantitative optoacoustic imaging of blood oxygenation in humans

Kirchner¹,

Jaeger²,

Frenz³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Optoacoustic (OA) imaging is a promising modality for quantifying blood oxygen saturation (sO 2 ) in various biomedical applications -in diagnosis, monitoring of organ function or even tumor treatment planning. We present an accurate and practically feasible real-time capable method for quantitative imaging of sO 2 based on combining multispectral (MS) and multiple illumination (MI) OA imaging with learned spectral decoloring (LSD). For this purpose we developed a hybrid real-time MI MS OA imaging setup with ultrasound (US) imaging capability; we trained gradient boosting machines on MI spectrally colored absorbed energy spectra generated by generic Monte Carlo simulations, and used the trained models to estimate sO 2 on real OA measurements. We validated MI-LSD in silico and on in vivo image sequences of radial arteries and accompanying veins of five healthy human volunteers. We compared the performance of the method to prior LSD work and conventional linear unmixing. MI-LSD provided highly accurate results in silico and consistently plausible results in vivo. This preliminary study shows a potentially high applicability of quantitative OA oximetry imaging, using our method.

show abstract

Section: Discussionmentioning

confidence: 90%

Section: Blood Oxygen Saturation Estimation Methodsmentioning

confidence: 98%

Section: Blood Oxygen Saturation Estimation Methodsmentioning

confidence: 99%

Section: Blood Oxygen Saturation Estimation Methodsmentioning

confidence: 99%

“…In earlier work [26] we validated such an approach on a highly controlled copper and nickel sulfate [27] phantom model of sO 2 . In this work we:…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Machine learning enabled multiple illumination quantitative optoacoustic imaging of blood oxygenation in humans

Kirchner¹,

Jaeger²,

Frenz³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

Optimizing quantitative photoacoustic imaging systems: the Bayesian Cramér–Rao bound approach

Scope Crafts,

Anastasio,

Villa

2024

Inverse Problems

View full text Add to dashboard Cite

Quantitative photoacoustic computed tomography (qPACT) is an emerging medical imaging modality that carries the promise of high-contrast, ﬁne-resolution imaging of clinically relevant quantities like hemoglobin concentration and blood-oxygen saturation. However, qPACT image reconstruction is governed by a multiphysics, partial differential equation (PDE) based inverse problem that is highly non-linear and severely ill-posed. Compounding the di culty of the problem is the lack of established design standards for qPACT imaging systems, as there is currently a proliferation of qPACT system designs for various applications and it is unknown which ones are optimal or how to best modify the systems under various design constraints. This work introduces a novel computational approach for the optimal experimental design (OED) of qPACT imaging systems based on the Bayesian Cramér-Rao bound (CRB). Our approach incorporates several techniques to address challenges associated with forming the bound in the inﬁnite-dimensional function space setting of qPACT, including priors with trace-class covariance operators and the use of the variational adjoint method to compute derivatives of the log-likelihood function needed in the bound computation. The resulting Bayesian CRB based design metric is computationally efficient and independent of the choice of estimator used to solve the inverse problem. The efficacy of the bound in guiding experimental design was demonstrated in a numerical study of qPACT design schemes under a stylized two-dimensional imaging geometry. To the best of our knowledge, this is the ﬁrst work to propose a Bayesian CRB-based design for systems governed by PDEs.

show abstract

Machine-learning-based mapping of blood oxygen saturation from dual-wavelength optoacoustic measurements

Kurakina,

Kirillin,

Khilov

et al. 2024

Laser Phys. Lett.

View full text Add to dashboard Cite

We developed a novel machine-learning-based algorithm based on a gradient boosting regressor for three-dimensional pixel-by-pixel mapping of blood oxygen saturation based on dual-wavelength optoacoustic data. Algorithm training was performed on in silico data produced from Monte-Carlo-generated absorbed light energy distributions in tissue-like vascularized media for probing wavelengths of 532 and 1064 nm and the empirical instrumental function of the optoacoustic imaging setup with further validation of the independent in silico data. In vivo optoacoustic data for rabbit-ear vasculature was employed as a testing dataset. The developed algorithm allowed in vivo blood oxygen saturation mapping and showed clear differences in blood oxygen saturation values in veins at 15 °C and 43 °C due to functional arteriovenous anastomoses. These results indicated that dual-wavelength optoacoustic imaging could serve as a cost-effective alternative to complicated multiwavelength quantitative optoacoustic imaging.

show abstract

Multiple illumination learned spectral decoloring for quantitative optoacoustic oximetry imaging

Cited by 10 publications

References 35 publications

Machine learning enabled multiple illumination quantitative optoacoustic imaging of blood oxygenation in humans

Machine learning enabled multiple illumination quantitative optoacoustic imaging of blood oxygenation in humans

Optimizing quantitative photoacoustic imaging systems: the Bayesian Cramér–Rao bound approach

Machine-learning-based mapping of blood oxygen saturation from dual-wavelength optoacoustic measurements

Contact Info

Product

Resources

About