Deep spectral learning for label-free optical imaging oximetry with uncertainty quantification

Rongrong Liu; Shiyi Cheng; Lei Tian; Ji Yi

doi:10.1038/s41377-019-0216-0

Go to Nature Website

Your Location：

Home >

Browse articles >

Deep spectral learning for label-free optical imaging oximetry with uncertainty quantification

Article

- Deep spectral learning for label-free optical imaging oximetry with uncertainty quantification
- Deep spectral learning for label-free optical imaging oximetry with uncertainty quantification
- LSA 2019年8卷第6期页码：1020-1032
- Affiliations：
  
  1.Department of Biomedical Engineering, Northwestern University, Evanston, IL 60208, USA
  2.Department of Electrical and Computer Engineering, Boston University, Boston, MA 02215, USA
  3.Department of Biomedical Engineering, Boston University, Boston, MA 02215, USA
  4.Department of Medicine, Boston University School of Medicine, Boston Medical Center, Boston, MA 02118, USA
- Author bio：
  
  Ji Yi (jiyi@bu.edu)
- Funds：
- DOI：10.1038/s41377-019-0216-0
  中图分类号：
- 纸质出版日期：2019，
  
  网络出版日期：2019-11-20，
  
  收稿日期：2019-07-08，
  
  修回日期：2019-10-17，
  
  录用日期：2019-11-01
- Accepted：
Scan QR Code
Deep spectral learning for label-free optical imaging oximetry with uncertainty quantification[J]. LSA, 2019,8(6):1020-1032.

Liu, R. R. et al. Deep spectral learning for label-free optical imaging oximetry with uncertainty quantification. Light: Science & Applications, 8, 1020-1032 (2019).
Deep spectral learning for label-free optical imaging oximetry with uncertainty quantification[J]. LSA, 2019,8(6):1020-1032. DOI： 10.1038/s41377-019-0216-0.

Liu, R. R. et al. Deep spectral learning for label-free optical imaging oximetry with uncertainty quantification. Light: Science & Applications, 8, 1020-1032 (2019). DOI： 10.1038/s41377-019-0216-0.

摘要

Abstract

Measurement of blood oxygen saturation (

) by optical imaging oximetry provides invaluable insight into local tissue functions and metabolism. Despite different embodiments and modalities

all label-free optical-imaging oximetry techniques utilize the same principle of

-dependent spectral contrast from haemoglobin. Traditional approaches for quantifying

often rely on analytical models that are fitted by the spectral measurements. These approaches in practice suffer from uncertainties due to biological variability

tissue geometry

light scattering

systemic spectral bias

and variations in the experimental conditions. Here

we propose a new data-driven approach

termed deep spectral learning (DSL)

to achieve oximetry that is highly robust to experimental variations and

more importantly

able to provide uncertainty quantification for each

prediction. To demonstrate the robustness and generalizability of DSL

we analyse data from two visible light optical coherence tomography (vis-OCT) setups across two separate in vivo experiments on rat retinas. Predictions made by DSL are highly adaptive to experimental variabilities as well as the depth-dependent backscattering spectr

a. Two neural-network-based models are tested and compared with the traditional least-squares fitting (LSF) method. The DSL-predicted

shows significantly lower mean-square errors than those of the LSF. For the first time

we have demonstrated

en face

maps of retinal oximetry along with a pixel-wise confidence assessment. Our DSL overcomes several limitations of traditional approaches and provides a more flexible

robust

and reliable deep learning approach for in vivo non-invasive label-free optical oximetry.

关键词

Keywords

references

Stefánsson, E. Ocular oxygenation and the treatment of diabetic retinopathy.Surv. Ophthalmol.51, 364-380 (2006)..

Vajkoczy, P., Ullrich, A.&Menger, M. D. Intravital fluorescence videomicroscopy to study tumor angiogenesis and microcirculation.Neoplasia2, 53-61 (2002)..

Levy, B. I. et al. Impaired tissue perfu37sion: a pathology common to hypertension, obesity, and diabetes mellitus.Circulation118, 968-976 (2008)..

Edwards-Richards, A. et al. Capillary rarefaction: an early marker of microvascular disease in young hemodialysis patients.Clin. Kidney J.7, 569-574 (2014)..

Kalaria, R. N. Neurodegenerative disease: diabetes, microvascular pathology and Alzheimer disease.Nat. Rev. Neurol. Vol.5, 305-306 (2009)..

Faber, D. J. et al. Oxygen saturation dependent absorption and scattering of whole blood. Proceedings Volume 5316, Coherence Domain Optical Methods and Optical Coherence Tomography in Biomedicine Ⅷ. San Jose, CA, United States: SPIE, 2004.

Nguyen, J. Q. M. et al. Spatial frequency domain imaging of burn wounds in a preclinical49 model of graded burn severity.J. Biomed. Opt.18, 066010 (2013)..

Gioux, S. et al. First-in-human pilot study of a spatial frequency domain oxygenation imaging system.J. Biomed. Opt.16, 086015 (2011)..

Delori, F. C. Noninvasive technique for oximetry of blood in retinal vessels.Appl. Opt.27, 1113-1125 (1988)..

Palsson, O. et al. Retinal oximetry images must be standardized: a methodological analysis.Investig. Ophthalmol. Vis. Sci.53, 1729-1733 (2012)..

Blair, N. P. et al. Retinal oximetry and vessel diameter measurements with a commercially available scanning laser ophthalmoscope in diabetic retinopathy.Investig. Ophthalmol. Vis. Sci.58, 5556-5563 (2017)..

Kristjansdottir, J. V. et al. Retinal oximetry with a scanning laser ophthalmoscope.Investig. Ophthalmol. Vis. Sci.55, 3120-3126 (2014)..

Yi, J. et al. Visible light optical coherence tomography measures retinal oxygen metabolic response to systemic oxygenation.Light.: Sci. Appl. Vol.4, e334 (2015)..

Shu, X. et al. Visible-light optical coherence tomography: a review.J. Biomed. Opt.22, 121707 (2017).

Chen, S. Y., Yi, J.&Zhang, H. F. Measuring oxygen saturation in retinal and choroidal circulations in rats using visible light optical coherence tomography angiography.Biomed. Opt. Express6, 2840-2853 (2015)..

Liu, R. R. et al. Theoretical model for optical oximetry at the capillary level: exploring hemoglobin oxygen saturation through backscattering of single red blood cells.J. Biomed. Opt.22, 025002 (2017)..

Liu, R. et al. Single capillary oximetry and tissue ultrastructural sensing by dual-band dual-scan inverse spectroscopic optical coherence tomography.Light.: Sci. Appl. Vol.7, 57 (2018)..

Liu, R. R. et al. Quantitative quality-control metrics for in vivo oximetry in small vessels by visible light optical coherence tomography angiography.Biomed. Opt. Express10, 465-486 (2019)..

Pi, S. H. et al. Rodent retinal circulation organization and oxygen metabolism revealed by visible-light optical coherence tomography.Biomed. Opt. Express9, 5851-5862 (2018)..

Pi, S. H. et al. Automated spectroscopic retinal oximetry with visible-light optical coherence tomography.Biomed. Opt. Express9, 2056-2067 (2018)..

Soetikno, B. T. et al. Visible-light optical coherence tomography oximetry based on circumpapillary scan and graph-search segmentation.Biomed. Opt. Express9, 3640-3652 (2018)..

Robles, F. E. et al. Molecular imaging true-colour spectroscopic optical coherence tomography.Nat. Photonics5, 744-747 (2011)..

Yi,J.&Li, X. Estimation of oxygen saturation from erythrocytes by high-resolution spectroscopic optical coherence tomography.Opt. Lett.35, 2094-2096 (2010)..

Yi, J. et al. In vivo functional microangiography by visible-light optical coherence tomography.Biomed. Opt. Express5, 3603-3612 (2014)..

Yi, J. et al. Visible-light optical coherence tomography for retinal oximetry.Opt. Lett.38, 1796-1798 (2013)..

Tan, Y. H. et al. Surface area and pore size characteristics of nanoporous gold subjected to thermal, mechanical, or surface modification studied using gas adsorption isotherms, cyclic voltammetry, thermogravimetric analysis, and scanning electron microscopy.J. Mater. Chem.22, 6733-6745 (2012)..

Wang, L. D., Maslov, K.&Wang, L. V. Single-cell label-free photoacoustic flowoxigraphy in vivo.Proc. Natl Acad. Sci. USA110, 5759-5764 (2013)..

Kuranov, R. V. et al. Depth-resolved blood oxygen saturation measurement by dual-wavelength photothermal (DWP) optical coherence tomography.Biomed. Opt. Express2, 491-504 (2011)..

Kuranov, R. V. et al. In vivo depth-resolved oxygen saturation by dual-wavelength photothermal (DWP) OCT.Opt. Express19, 23831-23844 (2011)..

Cox, B. T. et al. Quantitative spectroscopic photoacoustic imaging: a review.J. Biomed. Opt.17, 061202 (2012)..

Yao, J. J. et al. High-speed label-free functional photoacoustic microscopy of mouse brain in action.Nat. Methods12, 407-410 (2015)..

Sinha, A. et al. Lensless computational imaging through deep learning.Optica4, 1117-1125 (2017)..

Li, Y. Z., Xue, Y.&Tian, L. Deep speckle correlation: a deep learning approach toward scalable imaging through scattering media.Optica5, 1181-1190 (2018)..

Yichen, W. C. et al. Extended depth-of-field in holographic imaging using deep-learning-based autofocusing and phase recovery.Optica5, 704-710 (2018)..

Liu, X. M. et al. Semi-supervised automatic segmentation of layer and fluid region in retinal optical coherence tomography images using adversarial learning.IEEE Access7, 3046-3061 (2019)..

Xue, Y. J. et al. Reliable deep-learning-based phase imaging with uncertainty quantification.Optica6, 618-629 (2019)..

Ching, T. et al. Opportunities and obstacles for deep learning in biology and medicine.J. R. Soc. Interface15, 20170387 (2018)..

Hammer, M. et al. Retinal vessel oximetry-calibration, compensation for vessel diameter and fundus pigmentation, and reproducibility.J. Biomed. Opt.13, 054015 (2008)..

Yi, J. et al. Human retinal imaging using visible-light optical coherence tomography guided by scanning laser ophthalmoscopy.Biomed. Opt. Express6, 3701-3713 (2015)..

Zhang, T. W., Kho, A. M.&Srinivasan, V. J. Improving visible light OCT of the human retina with rapid spectral shaping and axial tracking.Biomed. Opt. Express10, 2918-2931 (2019)..

Ju, M. J. et al. Visible light sensorless adaptive optics for retinal structure and fluorescenceimaging.Opt. Lett.43, 5162-5165 (2018)..

Chen, S. Y. et al. Retinal oximetry in humans using visible-light optical coherence tomography.Biomed. Opt. Express8, 1415-1429 (2017)..

Liu, W. et al. Increased retinal oxygen metabolism precedes microvascular alterations in type 1 diabetic mice.Investig. Ophthalmol. Vis. Sci.58, 981-989 (2017)..

Soetikno, B. T. et al. Inner retinal oxygen metabolism in the 50/10 oxygen-induced retinopathy model.Sci. Rep.5, 16752 (2015)..

Song, W. Y. et al. Longitudinal detection of retinal alterations by visible and near-infrared optical coherence tomography in a dexamethasone-induced ocular hypertension mouse model.Neurophotonics6, 041103 (2019)..

Pi, S. H. et al. Monitoring retinal responses to acute intraocular pressure elevation in rats with visible light optical coherence tomography.Neurophotonics6, 041104 (2019)..

Soetikno, B. T. et al. Optical coherence tomography angiography of retinal vascular occlusions produced by imaging-guided laser photocoagulation.Biomed. Opt. Express8, 3571-3582 (2017)..

Weigert, M. et al. Content-aware image restoration: pushing the limits of fluorescence microscopy.Nat. Methods15, 1090-1097 (2018)..

Sencan, I. et al. Two-photon phosphorescence lifetime microscopy of retinal capillary plexus oxygenation in mice.J. Biomed. Opt.23, 126501 (2018).

Webster, J. G.Design of Pulse Oximeters(CRC Press, Bristol, 1997).

Nakajimi, S. et al. New pulsed-type earpiece oximeter (author's transl).Kokyu Junkan23, 709-713 (1975)..

Khan, Y. et al. A flexible organic reflectance oximeter array.Proc. Natl Acad. Sci. USA115, E11015-E11024 (2018)..

Bosschaart, N. et al. A literature review and novel theoretical approach on the optical properties of whole blood.Lasers Med. Sci.29, 453-479 (2014)..

Chong, S. P. et al. Cerebral metabolic rate of oxygen (CMRO2) assessed by combined Doppler and spectroscopic OCT.Biomed. Opt. Express6, 3941-3951 (2015)..

Kendall, A.&Gal, Y. What uncertainties do we need in bayesian deep learning for computer vision? (eds. H., Wallach, H., Larochelle, A., Beygelzimer, F., d'Alché-Buc, E., Fox.&R., Garnett.) InProc. 30th Advances Neural Information Processing Systems (NIPS). 5580-5590, The Neural Information Processing Systems Foundation: 2017.

浏览量

Downloads

CSCD

文章被引用时，请邮件提醒。

Submit

工具集

关联资源

暂无数据