Deep Learning-Based Spectral Unmixing for Optoacoustic Imaging of Tissue Oxygen Saturation

Olefir, Ivan; Tzoumas, Stratis; Restivo, Courtney; Mohajerani, Pouyan; Li, Xing; Ntziachristos, Vasilis

doi:10.1109/tmi.2020.3001750

Cited by 56 publications

(44 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, it is challenging to constrain a conventional minimization algorithm to yield a unique solution when used on handheld PA device geometries. In recent work of Olefir et al 26 it was shown that deep learning algorithms can help to mitigate these issues. One of the core assumptions of learned spectral decoloring (LSD) is that the optimal set of constraints for the inversion can be learned from the wavelength-dependent changes of using data-driven approaches.…”

Section: Methodsmentioning

confidence: 99%

Learned spectral decoloring enables photoacoustic oximetry

Gröhl

Kirchner

Adler

et al. 2021

Sci Rep

View full text Add to dashboard Cite

The ability of photoacoustic imaging to measure functional tissue properties, such as blood oxygenation sO$$_2$$ 2 , enables a wide variety of possible applications. sO$$_2$$ 2 can be computed from the ratio of oxyhemoglobin HbO$$_2$$ 2 and deoxyhemoglobin Hb, which can be distuinguished by multispectral photoacoustic imaging due to their distinct wavelength-dependent absorption. However, current methods for estimating sO$$_2$$ 2 yield inaccurate results in realistic settings, due to the unknown and wavelength-dependent influence of the light fluence on the signal. In this work, we propose learned spectral decoloring to enable blood oxygenation measurements to be inferred from multispectral photoacoustic imaging. The method computes sO$$_2$$ 2 pixel-wise, directly from initial pressure spectra $$S_{\text {p}_0}(\lambda , \mathbf {x})$$ S p 0 ( λ , x ) , which represent initial pressure values at a fixed spatial location $$\mathbf {x}$$ x over all recorded wavelengths $$\lambda$$ λ . The method is compared to linear unmixing approaches, as well as pO$$_2$$ 2 and blood gas analysis reference measurements. Experimental results suggest that the proposed method is able to obtain sO$$_2$$ 2 estimates from multispectral photoacoustic measurements in silico, in vitro, and in vivo.

show abstract

Section: Methodsmentioning

confidence: 99%

Learned spectral decoloring enables photoacoustic oximetry

Gröhl

Kirchner

Adler

et al. 2021

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Combining DL with traditional reconstruction methods is a good choice, which has yielded good results in all types of task. 68 , 109 , 110 , 132 Among them, applying DL in iterative model-based methods to calculate the update or the regularization term has been the most successful, probably because it can best leverage the prior information about the PA physics and the imaged object. In addition, the iterative method is more robust than other models (including preprocessing model, postprocessing model, and direct reconstruction model).…”

Section: Discussionmentioning

confidence: 99%

“… 175 Olefir et al. 132 combined the eigenspectra concept and DL and named the new method as DL-eMSOT. They used LSTM and CNN to calculate the weights of four spectral bases for predicting the eigenfluence.…”

Section: Applications Of DL In Paimentioning

confidence: 99%

Deep learning in photoacoustic imaging: a review

et al. 2021

View full text Add to dashboard Cite

. Significance: Photoacoustic (PA) imaging can provide structural, functional, and molecular information for preclinical and clinical studies. For PA imaging (PAI), non-ideal signal detection deteriorates image quality, and quantitative PAI (QPAI) remains challenging due to the unknown light fluence spectra in deep tissue. In recent years, deep learning (DL) has shown outstanding performance when implemented in PAI, with applications in image reconstruction, quantification, and understanding. Aim: We provide (i) a comprehensive overview of the DL techniques that have been applied in PAI, (ii) references for designing DL models for various PAI tasks, and (iii) a summary of the future challenges and opportunities. Approach: Papers published before November 2020 in the area of applying DL in PAI were reviewed. We categorized them into three types: image understanding, reconstruction of the initial pressure distribution, and QPAI. Results: When applied in PAI, DL can effectively process images, improve reconstruction quality, fuse information, and assist quantitative analysis. Conclusion: DL has become a powerful tool in PAI. With the development of DL theory and technology, it will continue to boost the performance and facilitate the clinical translation of PAI.

show abstract

“…However, it becomes a very challenging job because of the high heterogeneity in living tissue that heavily increases the complexity in fluence distribution. Several approaches are being explored, including the direct calculation of the fluence based on numerically solving the radiative transfer equation [ [14] , [15] , [16] ], spectral unmixing methods [ 17 , 18 ], and most recently machine learning algorithms [ [19] , [20] , [21] ]. In this work, we employed the first approach.…”

Section: Introductionmentioning

confidence: 99%