Confidence Estimation for Machine Learning-Based Quantitative Photoacoustics

Gröhl, Janek; Kirchner, Thomas; Adler, Tim; Maier-Hein, Lena

doi:10.3390/jimaging4120147

Cited by 33 publications

(28 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is especially relevant in deep tissue due to fluence dependent spectral coloring. While there are promising approaches to address these fluence effects in general [29,30,31] and spectral coloring specifically [28], the translation of quantitative PA imaging deep in tissue remains a major challenge. Values are averaged over one minute beginning at the time after start of the recording.…”

Section: Resultsmentioning

confidence: 99%

Photoacoustic monitoring of blood oxygenation during neurosurgical interventions

Kirchner

Gröhl²,

Herrera³

et al. 2019

Photons Plus Ultrasound: Imaging and Sensing 2019

Self Cite

View full text Add to dashboard Cite

Multispectral photoacoustic (PA) imaging is a prime modality to monitor hemodynamics and changes in blood oxygenation (sO2). Although sO2 changes can be an indicator of brain activity both in normal and in pathological conditions, PA imaging of the brain has mainly focused on small animal models with lissencephalic brains. Therefore, the purpose of this work was to investigate the usefulness of multispectral PA imaging in assessing sO2 in a gyrencephalic brain. To this end, we continuously imaged a porcine brain as part of an open neurosurgical intervention with a handheld PA and ultrasonic (US) imaging system in vivo. Throughout the experiment, we varied respiratory oxygen and continuously measured arterial blood gases. The arterial blood oxygenation (SaO2) values derived by the blood gas analyzer were used as a reference to compare the performance of linear spectral unmixing algorithms in this scenario. According to our experiment, PA imaging can be used to monitor sO2 in the porcine cerebral cortex. While linear spectral unmixing algorithms are well-suited for detecting changes in oxygenation, there are limits with respect to the accurate quantification of sO2, especially in depth. Overall, we conclude that multispectral PA imaging can potentially be a valuable tool for change detection of sO2 in the cerebral cortex of a gyrencephalic brain. The spectral unmixing algorithms investigated in this work will be made publicly available as part of the open-source software platform Medical Imaging Interaction Toolkit (MITK).

show abstract

Section: Resultsmentioning

confidence: 99%

Photoacoustic monitoring of blood oxygenation during neurosurgical interventions

Kirchner

Gröhl²,

Herrera³

et al. 2019

Photons Plus Ultrasound: Imaging and Sensing 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…This implies that large multiscale networks are needed to transform the signal into the sought-after PAT image effectively. In early studies by Waibel et al 104 and Gröhl et al, 126 it was shown that using an asymmetric U-Net to reconstruct the PA image directly from raw sensor data is feasible in a limitedview setting. In comparison to a postprocessing approach using a U-Net, it was competitive in terms of mean reconstruction error, but exhibited a higher variance in reconstruction error.…”

Section: Convolutional Approachesmentioning

confidence: 99%

“…In a detailed study, Gröhl et al 126 used U-Nets to estimate the absorption coefficient in various ways. In two fluence-estimation approaches, asymmetric and symmetric U-Nets were used to estimate the fluence map ϕ from time series data g and from initial pressure distribution f, respectively.…”

Section: U-net-based Optical Inversionsmentioning

confidence: 99%

“…One of the difficulties with translating sO 2 estimation techniques, for example, to a clinical setting is knowing how much confidence one should have in the estimates. This problem is tackled by Gröhl et al, 126 who trained a U-Net to act as an error-estimating network, using {(PAT image, error image)} pairs, to give an estimate of the uncertainty in the μ a estimates. The uncertainty correlated well with the actual error in the images in this in silico study.…”

Section: Learned Uncertainty Estimationmentioning

confidence: 99%

See 1 more Smart Citation

Deep learning in photoacoustic tomography: current approaches and future directions

2020

View full text Add to dashboard Cite

Biomedical photoacoustic tomography, which can provide high-resolution 3D soft tissue images based on optical absorption, has advanced to the stage at which translation from the laboratory to clinical settings is becoming possible. The need for rapid image formation and the practical restrictions on data acquisition that arise from the constraints of a clinical workflow are presenting new image reconstruction challenges. There are many classical approaches to image reconstruction, but ameliorating the effects of incomplete or imperfect data through the incorporation of accurate priors is challenging and leads to slow algorithms. Recently, the application of deep learning (DL), or deep neural networks, to this problem has received a great deal of attention. We review the literature on learned image reconstruction, summarizing the current trends and explain how these approaches fit within, and to some extent have arisen from, a framework that encompasses classical reconstruction methods. In particular, it shows how these techniques can be understood from a Bayesian perspective, providing useful insights. We also provide a concise tutorial demonstration of three prototypical approaches to learned image reconstruction. The code and data sets for these demonstrations are available to researchers. It is anticipated that it is in in vivo applications-where data may be sparse, fast imaging critical, and priors difficult to construct by hand-that DL will have the most impact. With this in mind, we conclude with some indications of possible future research directions. © The Authors. Published by SPIE under a Creative Commons Attribution 4.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.

show abstract

“…9,13,14 One major aspect that has recently gained increasing attention is assessing the reliability of the quantitative results. 15,16 In this paper, we focus on estimating the uncertainty of the SO 2 levels retrieved from spectral fitting, independently of the methods used for OA data acquisition, image reconstruction, or for the correction of spectral distortions. More precisely, we dwell on the fact that fitted SO 2 values that are physiologically reasonable do not necessarily imply that the measured OA spectra follow the trend of real blood spectra.…”

Section: Introductionmentioning

confidence: 99%

Reliability assessment for blood oxygen saturation levels measured with optoacoustic imaging

et al. 2020

View full text Add to dashboard Cite

Significance: Quantitative optoacoustic (OA) imaging has the potential to provide blood oxygen saturation (SO 2 ) estimates due to the proportionality between the measured signal and the blood's absorption coefficient. However, due to the wavelength-dependent attenuation of light in tissue, a spectral correction of the OA signals is required, and a prime challenge is the validation of both the optical characterization of the tissue and the SO 2 .Aim: We propose to assess the reliability of SO 2 levels retrieved from spectral fitting by measuring the similarity of OA spectra to the fitted blood absorption spectra.Approach: We introduce a metric that quantifies the trends of blood spectra by assigning a pair of spectral slopes to each spectrum. The applicability of the metric is illustrated with in vivo measurements on a human forearm. Results:We show that physiologically sound SO 2 values do not necessarily imply a successful spectral correction and demonstrate how the metric can be used to distinguish SO 2 values that are trustworthy from unreliable ones. Conclusions:The metric is independent of the methods used for the OA data acquisition, image reconstruction, and spectral correction, thus it can be readily combined with existing approaches, in order to monitor the accuracy of quantitative OA imaging.

show abstract

Confidence Estimation for Machine Learning-Based Quantitative Photoacoustics

Cited by 33 publications

References 46 publications

Photoacoustic monitoring of blood oxygenation during neurosurgical interventions

Photoacoustic monitoring of blood oxygenation during neurosurgical interventions

Deep learning in photoacoustic tomography: current approaches and future directions

Reliability assessment for blood oxygen saturation levels measured with optoacoustic imaging

Contact Info

Product

Resources

About