{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T00:45:29Z","timestamp":1771029929010,"version":"3.50.1"},"reference-count":58,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2018,12,10]],"date-time":"2018-12-10T00:00:00Z","timestamp":1544400000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000781","name":"European Research Council","doi-asserted-by":"publisher","award":["ERC-2015-StG-37960"],"award-info":[{"award-number":["ERC-2015-StG-37960"]}],"id":[{"id":"10.13039\/501100000781","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>In medical applications, the accuracy and robustness of imaging methods are of crucial importance to ensure optimal patient care. While photoacoustic imaging (PAI) is an emerging modality with promising clinical applicability, state-of-the-art approaches to quantitative photoacoustic imaging (qPAI), which aim to solve the ill-posed inverse problem of recovering optical absorption from the measurements obtained, currently cannot comply with these high standards. This can be attributed to the fact that existing methods often rely on several simplifying a priori assumptions of the underlying physical tissue properties or cannot deal with realistic noise levels. In this manuscript, we address this issue with a new method for estimating an indicator of the uncertainty of an estimated optical property. Specifically, our method uses a deep learning model to compute error estimates for optical parameter estimations of a qPAI algorithm. Functional tissue parameters, such as blood oxygen saturation, are usually derived by averaging over entire signal intensity-based regions of interest (ROIs). Therefore, we propose to reduce the systematic error of the ROI samples by additionally discarding those pixels for which our method estimates a high error and thus a low confidence. In silico experiments show an improvement in the accuracy of optical absorption quantification when applying our method to refine the ROI, and it might thus become a valuable tool for increasing the robustness of qPAI methods.<\/jats:p>","DOI":"10.3390\/jimaging4120147","type":"journal-article","created":{"date-parts":[[2018,12,10]],"date-time":"2018-12-10T11:31:16Z","timestamp":1544441476000},"page":"147","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":26,"title":["Confidence Estimation for Machine Learning-Based Quantitative Photoacoustics"],"prefix":"10.3390","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5332-4856","authenticated-orcid":false,"given":"Janek","family":"Gr\u00f6hl","sequence":"first","affiliation":[{"name":"Division of Computer Assisted Medical Interventions (CAMI), German Cancer Research Center (DKFZ), 69120 Heidelberg, Germany"},{"name":"Medical Faculty, Heidelberg University, 69120 Heidelberg, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3819-1987","authenticated-orcid":false,"given":"Thomas","family":"Kirchner","sequence":"additional","affiliation":[{"name":"Division of Computer Assisted Medical Interventions (CAMI), German Cancer Research Center (DKFZ), 69120 Heidelberg, Germany"},{"name":"Faculty of Physics and Astronomy, Heidelberg University, 69120 Heidelberg, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3424-6629","authenticated-orcid":false,"given":"Tim","family":"Adler","sequence":"additional","affiliation":[{"name":"Division of Computer Assisted Medical Interventions (CAMI), German Cancer Research Center (DKFZ), 69120 Heidelberg, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4910-9368","authenticated-orcid":false,"given":"Lena","family":"Maier-Hein","sequence":"additional","affiliation":[{"name":"Division of Computer Assisted Medical Interventions (CAMI), German Cancer Research Center (DKFZ), 69120 Heidelberg, Germany"},{"name":"Medical Faculty, Heidelberg University, 69120 Heidelberg, Germany"}]}],"member":"1968","published-online":{"date-parts":[[2018,12,10]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"267","DOI":"10.14366\/usg.16035","article-title":"Clinical photoacoustic imaging of cancer","volume":"35","author":"Valluru","year":"2016","journal-title":"Ultrason"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1292","DOI":"10.1056\/NEJMc1612455","article-title":"Multispectral Optoacoustic Tomography for Assessment of Crohn\u2019s Disease Activity","volume":"376","author":"Knieling","year":"2017","journal-title":"N. Engl. J. Med."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Laufer, J. (2018). Photoacoustic Imaging: Principles and Applications. Quantification of Biophysical Parameters in Medical Imaging, Springer.","DOI":"10.1007\/978-3-319-65924-4_13"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1016\/j.pacs.2017.06.004","article-title":"Photoacoustic-based SO2 estimation through excised bovine prostate tissue with interstitial light delivery","volume":"7","author":"Mitcham","year":"2017","journal-title":"Photoacoust"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"R37","DOI":"10.1088\/0031-9155\/58\/11\/R37","article-title":"Optical properties of biological tissues: A review","volume":"58","author":"Jacques","year":"2013","journal-title":"Phys. Med. Boil."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"12121","DOI":"10.1038\/ncomms12121","article-title":"Eigenspectra optoacoustic tomography achieves quantitative blood oxygenation imaging deep in tissues","volume":"7","author":"Tzoumas","year":"2016","journal-title":"Nat. Commun."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1866","DOI":"10.1364\/AO.45.001866","article-title":"Two-dimensional quantitative photoacoustic image reconstruction of absorption distributions in scattering media by use of a simple iterative method","volume":"45","author":"Cox","year":"2006","journal-title":"Appl. Opt."},{"key":"ref_8","first-page":"717713","article-title":"The challenges for quantitative photoacoustic imaging. Photons Plus Ultrasound: Imaging and Sensing","volume":"7177","author":"Cox","year":"2009","journal-title":"Int. Soc. Opt. Photonics"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"061202","DOI":"10.1117\/1.JBO.17.6.061202","article-title":"Quantitative spectroscopic photoacoustic imaging: A review","volume":"17","author":"Cox","year":"2012","journal-title":"J. Biomed. Opt."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"231101","DOI":"10.1063\/1.2209883","article-title":"Quantitative photoacoustic tomography: Recovery of optical absorption coefficient maps of heterogeneous media","volume":"88","author":"Yuan","year":"2006","journal-title":"Appl. Phys. Lett."},{"key":"ref_11","first-page":"3043","article-title":"Quantitative photoacoustic tomography","volume":"367","author":"Yuan","year":"2009","journal-title":"Philos. Trans. R. Soc. Lond. A Math. Phys. Eng. Sci."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"3778","DOI":"10.1364\/BOE.8.003778","article-title":"Toward whole-body quantitative photoacoustic tomography of small-animals with multi-angle light-sheet illuminations","volume":"8","author":"Wang","year":"2017","journal-title":"Biomed. Opt. Express"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"075006","DOI":"10.1088\/0266-5611\/29\/7\/075006","article-title":"A gradient-based method for quantitative photoacoustic tomography using the radiative transfer equation","volume":"29","author":"Saratoon","year":"2013","journal-title":"Inverse Probl."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Tarvainen, T., Pulkkinen, A., Cox, B.T., and Arridge, S.R. (2017). Utilising the radiative transfer equation in quantitative photoacoustic tomography. Photons Plus Ultrasound Imaging Sens., 10064.","DOI":"10.1117\/12.2249310"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"065005","DOI":"10.1088\/0266-5611\/31\/6\/065005","article-title":"Single-stage reconstruction algorithm for quantitative photoacoustic tomography","volume":"31","author":"Haltmeier","year":"2015","journal-title":"Inverse Probl."},{"key":"ref_16","first-page":"100645J","article-title":"Monte-Carlo-based inversion scheme for 3D quantitative photoacoustic tomography. Photons Plus Ultrasound: Imaging and Sensing","volume":"10064","author":"Kaplan","year":"2017","journal-title":"Int. Soc. Opt. Photonics"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"20170262","DOI":"10.1098\/rsta.2017.0262","article-title":"Spectral unmixing techniques for optoacoustic imaging of tissue pathophysiology","volume":"375","author":"Tzoumas","year":"2017","journal-title":"Philos. Trans. R. Soc. A"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"3979","DOI":"10.1364\/BOE.7.003979","article-title":"Optimal wavelengths for optoacoustic measurements of blood oxygen saturation in biological tissues","volume":"7","author":"Perekatova","year":"2016","journal-title":"Biomed. Opt. Express"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"3175","DOI":"10.1364\/OE.19.003175","article-title":"Blind source unmixing in multi-spectral optoacoustic tomography","volume":"19","author":"Glatz","year":"2011","journal-title":"Opt. Express"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"2752","DOI":"10.1364\/OL.43.002752","article-title":"End-to-end deep neural network for optical inversion in quantitative photoacoustic imaging","volume":"43","author":"Cai","year":"2018","journal-title":"Opt. Lett."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"056008","DOI":"10.1117\/1.JBO.23.5.056008","article-title":"Context encoding enables machine learning-based quantitative photoacoustics","volume":"23","author":"Kirchner","year":"2018","journal-title":"J. Biomed. Opt."},{"key":"ref_22","first-page":"97084X","article-title":"Sensitivity of quantitative photoacoustic tomography inversion schemes to experimental uncertainty. SPIE BiOS","volume":"9708","author":"Fonseca","year":"2016","journal-title":"Int. Soc. Opt. Photonics"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1520","DOI":"10.1109\/TPAMI.2011.248","article-title":"Convergent Iterative Closest-Point Algorithm to Accomodate Anisotropic and Inhomogenous Localization Error","volume":"34","author":"Franz","year":"2012","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1361","DOI":"10.1177\/0278364908097661","article-title":"Motion Planning Under Uncertainty for Image-guided Medical Needle Steering","volume":"27","author":"Alterovitz","year":"2008","journal-title":"Int. J. Robot. Res."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"7263","DOI":"10.1088\/0031-9155\/54\/24\/002","article-title":"Investigation of uncertainties in image registration of cone beam CT to CT on an image-guided radiotherapy system","volume":"54","author":"Sykes","year":"2009","journal-title":"Phys. Med. Boil."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"538","DOI":"10.1016\/j.media.2013.03.002","article-title":"Bayesian characterization of uncertainty in intra-subject non-rigid registration","volume":"17","author":"Risholm","year":"2013","journal-title":"Med. Image Anal."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Nair, T., Precup, D., Arnold, D.L., and Arbel, T. (2018, January 16\u201320). Exploring Uncertainty Measures in Deep Networks for Multiple Sclerosis Lesion Detection and Segmentation. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Granada, Spain.","DOI":"10.1007\/978-3-030-00928-1_74"},{"key":"ref_28","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref_29","unstructured":"Gal, Y., and Ghahramani, Z. (2016, January 19\u201324). Dropout as a Bayesian approximation: Representing model uncertainty in deep learning. Proceedings of the International Conference on Machine Learning, New York, NY, USA."},{"key":"ref_30","unstructured":"Li, Y., and Gal, Y. (arXiv, 2017). Dropout Inference in Bayesian Neural Networks with Alpha-divergences, arXiv."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"17816","DOI":"10.1038\/s41598-017-17876-z","article-title":"Leveraging uncertainty information from deep neural networks for disease detection","volume":"7","author":"Leibig","year":"2017","journal-title":"Sci. Rep."},{"key":"ref_32","unstructured":"Feindt, M. (arXiv, 2004). A Neural Bayesian Estimator for Conditional Probability Densities, arXiv."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1016\/j.jcp.2018.04.018","article-title":"Bayesian deep convolutional encoder-decoder networks for surrogate modeling and uncertainty quantification","volume":"366","author":"Zhu","year":"2018","journal-title":"J. Comput. Phys."},{"key":"ref_34","unstructured":"Kohl, S.A., Romera-Paredes, B., Meyer, C., De Fauw, J., Ledsam, J.R., Maier-Hein, K.H., Eslami, S., Rezende, D.J., and Ronneberger, O. (arXiv, 2018). A Probabilistic U-Net for Segmentation of Ambiguous Images, arXiv."},{"key":"ref_35","unstructured":"Kingma, D.P., and Welling, M. (arXiv, 2013). Auto-encoding variational bayes, arXiv."},{"key":"ref_36","unstructured":"Mescheder, L., Nowozin, S., and Geiger, A. (arXiv, 2017). Adversarial variational bayes: Unifying variational autoencoders and generative adversarial networks, arXiv."},{"key":"ref_37","unstructured":"Ardizzone, L., Kruse, J., Wirkert, S., Rahner, D., Pellegrini, E.W., Klessen, R.S., Maier-Hein, L., Rother, C., and K\u00f6the, U. (arXiv, 2018). Analyzing Inverse Problems with Invertible Neural Networks, arXiv."},{"key":"ref_38","unstructured":"Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., and Garnett, R. (2017). Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles. Advances in Neural Information Processing Systems 30, Curran Associates, Inc."},{"key":"ref_39","unstructured":"Smith, L., and Gal, Y. (arXiv, 2018). Understanding Measures of Uncertainty for Adversarial Example Detection, arXiv."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"2497","DOI":"10.1109\/TMI.2016.2581211","article-title":"Direct estimation of optical parameters from photoacoustic time series in quantitative photoacoustic tomography","volume":"35","author":"Pulkkinen","year":"2016","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_41","first-page":"100643N","article-title":"Estimation and uncertainty quantification of optical properties directly from the photoacoustic time series. Photons Plus Ultrasound: Imaging and Sensing 2017","volume":"10064","author":"Pulkkinen","year":"2017","journal-title":"Int. Soc. Opt. Photonics"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"1951","DOI":"10.1121\/1.4945990","article-title":"Image reconstruction with uncertainty quantification in photoacoustic tomography","volume":"139","author":"Tick","year":"2016","journal-title":"J. Acoust. Soc. Am."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Eskola, H., V\u00e4is\u00e4nen, O., Viik, J., and Hyttinen, J. (2018). Photoacoustic image reconstruction with uncertainty quantification. EMBEC & NBC 2017, Springer.","DOI":"10.1007\/978-981-10-5122-7"},{"key":"ref_44","first-page":"104941C","article-title":"Confidence estimation for quantitative photoacoustic imaging. Photons Plus Ultrasound: Imaging and Sensing 2018","volume":"10494","author":"Kirchner","year":"2018","journal-title":"Int. Soc. Opt. Photonics"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Welvaert, M., and Rosseel, Y. (2013). On the Definition of Signal-To-Noise Ratio and Contrast-To-Noise Ratio for fMRI Data. PLoS ONE, 8.","DOI":"10.1371\/journal.pone.0077089"},{"key":"ref_46","first-page":"234","article-title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","volume":"Volume 9351","author":"Ronneberger","year":"2015","journal-title":"Medical Image Computing and Computer-Assisted Intervention (MICCAI)"},{"key":"ref_47","unstructured":"Paszke, A., Gross, S., Chintala, S., Chanan, G., Yang, E., DeVito, Z., Lin, Z., Desmaison, A., Antiga, L., and Lerer, A. (2017, January 4\u20139). Automatic Differentiation in PyTorch. Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Isensee, F., Petersen, J., Klein, A., Zimmerer, D., Jaeger, P.F., Kohl, S., Wasserthal, J., Koehler, G., Norajitra, T., and Wirkert, S. (arXiv, 2018). nnU-Net: Self-adapting Framework for U-Net-Based Medical Image Segmentation, arXiv.","DOI":"10.1007\/978-3-658-25326-4_7"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"096016","DOI":"10.1117\/1.3626212","article-title":"Quantitative photoacoustic imaging: Correcting for heterogeneous light fluence distributions using diffuse optical tomography","volume":"16","author":"Bauer","year":"2011","journal-title":"J. Biomed. Opt."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"14117","DOI":"10.1364\/OE.20.014117","article-title":"Correcting photoacoustic signals for fluence variations using acousto-optic modulation","volume":"20","author":"Daoudi","year":"2012","journal-title":"Opt. Express"},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1016\/j.pacs.2014.09.001","article-title":"Coupling 3D Monte Carlo light transport in optically heterogeneous tissues to photoacoustic signal generation","volume":"2","author":"Jacques","year":"2014","journal-title":"Photoacoust"},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"021314","DOI":"10.1117\/1.3360308","article-title":"k-Wave: MATLAB toolbox for the simulation and reconstruction of photoacoustic wave fields","volume":"15","author":"Treeby","year":"2010","journal-title":"J. Biomed. Opt."},{"key":"ref_53","first-page":"104942S","article-title":"Reconstruction of initial pressure from limited view photoacoustic images using deep learning. Photons Plus Ultrasound: Imaging and Sensing 2018","volume":"10494","author":"Waibel","year":"2018","journal-title":"Int. Soc. Opt. Photonics"},{"key":"ref_54","first-page":"97083G","article-title":"Freehand photoacoustic tomography for 3D angiography using local gradient information","volume":"9708","author":"Kirchner","year":"2016","journal-title":"Photons Plus Ultrasound Imaging Sens."},{"key":"ref_55","unstructured":"Gr\u00f6hl, J., Kirchner, T., Adler, T., and Maier-Hein, L. (2018). Silico 2D Photoacoustic Imaging Data, Zenodo."},{"key":"ref_56","unstructured":"Zimmerer, D., Petersen, J., Koehler, G., Wasserthal, J., Adler, T., and Wirkert, A. (2018). MIC-DKFZ\/Trixi: Pre-Release, Zenodo."},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"1382","DOI":"10.1109\/TMI.2018.2820382","article-title":"Model-Based Learning for Accelerated, Limited-View 3-D Photoacoustic Tomography","volume":"37","author":"Hauptmann","year":"2018","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_58","doi-asserted-by":"crossref","unstructured":"Antholzer, S., Haltmeier, M., and Schwab, J. (2018). Deep learning for photoacoustic tomography from sparse data. Inverse Probl. Sci. Eng.","DOI":"10.1080\/17415977.2018.1518444"}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/4\/12\/147\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T15:32:46Z","timestamp":1760196766000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/4\/12\/147"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12,10]]},"references-count":58,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2018,12]]}},"alternative-id":["jimaging4120147"],"URL":"https:\/\/doi.org\/10.3390\/jimaging4120147","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,12,10]]}}}