Imaging sub-diffuse optical properties of cancerous and normal skin tissue using machine learning-aided spatial frequency domain imaging

Abstract. Significance: Sub-diffuse optical properties may serve as useful cancer biomarkers, and wide-field heatmaps of these properties could aid physicians in identifying cancerous tissue. Sub-diffuse spatial frequency domain imaging (sd-SFDI) can reveal such wide-field maps, but the current time cost of experimentally validated methods for rendering these heatmaps precludes this technology from potential real-time applications. Aim: Our study renders heatmaps of sub-diffuse optical properties from experimental sd-SFDI images in real time and reports these properties for cancerous and normal skin tissue subtypes. Approach: A phase function sampling method was used to simulate sd-SFDI spectra over a wide range of optical properties. A machine learning model trained on these simulations and tested on tissue phantoms was used to render sub-diffuse optical property heatmaps from sd-SFDI images of cancerous and normal skin tissue. Results: The model accurately rendered heatmaps from experimental sd-SFDI images in real time. In addition, heatmaps of a small number of tissue samples are presented to inform hypotheses on sub-diffuse optical property differences across skin tissue subtypes. Conclusion: These results bring the overall process of sd-SFDI a fundamental step closer to real-time speeds and set a foundation for future real-time medical applications of sd-SFDI such as image guided surgery.

[1]  Xavier Intes,et al.  Real-time, wide-field and high-quality single snapshot imaging of optical properties with profile correction using deep learning. , 2020, Biomedical optics express.

[2]  Yanyu Zhao,et al.  Feasibility of spatial frequency domain imaging (SFDI) for optically characterizing a preclinical oncology model. , 2016, Biomedical optics express.

[3]  Miran Bürmen,et al.  Phase functions with large domain size for improved estimation of optical properties from subdiffusive reflectance , 2020, BiOS.

[4]  Kenneth R. Keymel,et al.  Preoperative mapping of nonmelanoma skin cancer using spatial frequency domain and ultrasound imaging. , 2014, Academic radiology.

[5]  M S Patterson,et al.  Influence of layered tissue architecture on estimates of tissue optical properties obtained from spatially resolved diffuse reflectometry. , 1998, Applied optics.

[6]  L. C. Henyey,et al.  Diffuse radiation in the Galaxy , 1940 .

[7]  Mia K Markey,et al.  Monte Carlo lookup table-based inverse model for extracting optical properties from tissue-simulating phantoms using diffuse reflectance spectroscopy , 2013, Journal of biomedical optics.

[8]  Austin J. Moy,et al.  Diffuse reflectance spectroscopy as a potential method for nonmelanoma skin cancer margin assessment , 2020, Translational Biophotonics.

[9]  Sylvain Gioux,et al.  Single snapshot imaging of optical properties. , 2013, Biomedical optics express.

[10]  Angela A. Eick,et al.  Mechanisms of light scattering from biological cells relevant to noninvasive optical-tissue diagnostics. , 1998, Applied optics.

[11]  Alwin Kienle,et al.  Sources of errors in spatial frequency domain imaging of scattering media , 2014, Journal of biomedical optics.

[12]  Jason R. Gunn,et al.  Enhanced scatter contrast color imaging of tissue: methods for comparing high spatial frequency domain and cross-polarization scatter images , 2017, BiOS.

[13]  W. Goth.  Rapid wide-field imaging of soft-tissue microstructure , 2019 .

[14]  Miran Bürmen,et al.  Efficient estimation of subdiffusive optical parameters in real time from spatially resolved reflectance by artificial neural networks. , 2018, Optics letters.

[15]  Elena Salomatina,et al.  Optical properties of normal and cancerous human skin in the visible and near-infrared spectral range. , 2006, Journal of biomedical optics.

[16]  Katherine W. Calabro,et al.  Modeling scattering in turbid media using the Gegenbauer phase function , 2015, Photonics West - Biomedical Optics.

[17]  A. N. Bashkatov,et al.  Optical properties of human skin, subcutaneous and mucous tissues in the wavelength range from 400 to 2000 nm , 2005 .

[18]  A. Amelink,et al.  In vivo quantification of the scattering properties of tissue using multi-diameter single fiber reflectance spectroscopy , 2013, Biomedical optics express.

[19]  Yanyu Zhao,et al.  Deep learning model for ultrafast multifrequency optical property extractions for spatial frequency domain imaging. , 2018, Optics letters.

[20]  Darren Roblyer,et al.  High-speed spatial frequency domain imaging with temporally modulated light , 2017, Journal of biomedical optics.

[21]  Vadim Backman,et al.  Microscopic imaging and spectroscopy with scattered light. , 2010, Annual review of biomedical engineering.

[22]  Anthony J. Durkin,et al.  Modulated imaging: quantitative analysis and tomography of turbid media in the spatial-frequency domain. , 2005, Optics letters.

[23]  Norman J. McCormick,et al.  Approximate two-parameter phase function for light scattering , 1980 .

[24]  Sylvain Gioux,et al.  Machine learning approach for rapid and accurate estimation of optical properties using spatial frequency domain imaging , 2018, Journal of biomedical optics.

[25]  Stefan Andersson-Engels,et al.  Next-generation acceleration and code optimization for light transport in turbid media using GPUs , 2010, Biomedical optics express.

[26]  Mia K. Markey,et al.  Machine learning and the Gegenbauer Kernel improve mapping of sub-diffuse optical properties in the spatial frequency domain , 2021, BiOS.

[27]  Wilfried Uhring,et al.  Real-time, wide-field, and quantitative oxygenation imaging using spatiotemporal modulation of light , 2019, Journal of biomedical optics.

[28]  Miran Bürmen,et al.  OpenCL framework for fast estimation of optical properties from spatial frequency domain images , 2019, BiOS.

[29]  Miran Bürmen,et al.  Portable measurement system for real-time acquisition and analysis of in-vivo spatially resolved reflectance in the subdiffusive regime , 2018, BiOS.

[30]  P. Robins.  Mohs micrographic surgery. , 1993, The Journal of dermatologic surgery and oncology.

[31]  Suephy C. Chen,et al.  Mohs micrographic surgery vs traditional surgical excision: a cost comparison analysis. , 2004, Archives of dermatology.

[32]  Yibin Ying,et al.  An artificial neural network model for accurate and efficient optical property mapping from spatial-frequency domain images , 2021, Comput. Electron. Agric..

[33]  Anthony J. Durkin,et al.  Characterizing reduced scattering coefficient of normal human skin across different anatomic locations and Fitzpatrick skin types using spatial frequency domain imaging , 2021, Journal of biomedical optics.

[34]  Alicia C B Allen,et al.  Non-Destructive Reflectance Mapping of Collagen Fiber Alignment in Heart Valve Leaflets , 2019, Annals of Biomedical Engineering.

[35]  Nicholas J. Durr,et al.  GANPOP: Generative Adversarial Network Prediction of Optical Properties From Single Snapshot Wide-Field Images , 2019, IEEE Transactions on Medical Imaging.

[36]  W. Woodward,et al.  DCIS Margins and Breast Conservation: MD Anderson Cancer Center Multidisciplinary Practice Guidelines and Outcomes , 2017, Journal of Cancer.

[37]  D. Roblyer,et al.  Quantitative real-time pulse oximetry with ultrafast frequency-domain diffuse optics and deep neural network processing. , 2018, Biomedical optics express.

[38]  Bernard Choi,et al.  Quantitative assessment of graded burn wounds in a porcine model using spatial frequency domain imaging (SFDI) and laser speckle imaging (LSI). , 2014, Biomedical optics express.

[39]  Bruce J Tromberg,et al.  Characterization of nonmelanoma skin cancer for light therapy using spatial frequency domain imaging. , 2015, Biomedical optics express.

[40]  S. Jacques.  Optical properties of biological tissues: a review , 2013, Physics in medicine and biology.

[41]  Miran Bürmen,et al.  Lookup table-based sampling of the phase function for Monte Carlo simulations of light propagation in turbid media. , 2017, Biomedical optics express.

[42]  Christian Depeursinge,et al.  Physical interpretation of the phase function related parameter γ studied with a fractal distribution of spherical scatterers. , 2010, Optics express.

[43]  Alwin Kienle,et al.  Model-based analysis on the influence of spatial frequency selection in spatial frequency domain imaging. , 2015, Applied optics.

[44]  Venkataramanan Krishnaswamy,et al.  Sub-diffusive scattering parameter maps recovered using wide-field high-frequency structured light imaging. , 2014, Biomedical optics express.

[45]  Sylvain Gioux,et al.  Ultrafast optical property map generation using lookup tables. , 2016, Journal of biomedical optics.

[46]  Sylvain Gioux,et al.  Spatial frequency domain imaging in 2019: principles, applications, and perspectives , 2019, Journal of biomedical optics.

[47]  Anthony J. Durkin,et al.  Imaging scattering orientation with spatial frequency domain imaging. , 2011, Journal of biomedical optics.

[48]  T. Minton.  Contemporary Mohs surgery applications , 2008, Current opinion in otolaryngology & head and neck surgery.

[49]  Arjen Amelink,et al.  Method to quantitatively estimate wavelength-dependent scattering properties from multidiameter single fiber reflectance spectra measured in a turbid medium. , 2011, Optics letters.

[50]  Miran Bürmen,et al.  Extraction of optical properties in the sub-diffuse regime by spatially resolved reflectance spectroscopy , 2016, SPIE BiOS.

[51]  I. Yaroslavsky,et al.  Influence of the scattering phase function approximation on the optical properties of blood determined from the integrating sphere measurements. , 1999, Journal of biomedical optics.

[52]  Stephan Saalfeld,et al.  Globally optimal stitching of tiled 3D microscopic image acquisitions , 2009, Bioinform..

[53]  Austin J. Moy,et al.  Physiological model using diffuse reflectance spectroscopy for nonmelanoma skin cancer diagnosis , 2019, Journal of biophotonics.

[54]  Brian W. Pogue,et al.  Modeling and Synthesis of Breast Cancer Optical Property Signatures With Generative Models , 2021, IEEE Transactions on Medical Imaging.

[55]  Bernard Choi,et al.  Quantitative short-wave infrared multispectral imaging of in vivo tissue optical properties. , 2014, Journal of biomedical optics.

[56]  G. Wagnières,et al.  Determination of tissue optical properties by steady-state spatial frequency-domain reflectometry , 1998, Lasers in Medical Science.

[57]  Mia K. Markey,et al.  A Machine Learning Approach to Determining Sub-Diffuse Optical Properties , 2020 .

[58]  Active line scan with spatial gating for sub-diffuse reflectance imaging of scatter microtexture. , 2020, Optics letters.

[59]  Min Xu,et al.  Real-time spatial frequency domain imaging by single snapshot multiple frequency demodulation technique , 2017, BiOS.

[60]  A. Amelink,et al.  Measurement of the reduced scattering coefficient of turbid media using single fiber reflectance spectroscopy: fiber diameter and phase function dependence , 2011, Biomedical optics express.

[61]  Anthony J. Durkin,et al.  Quantitation and mapping of tissue optical properties using modulated imaging. , 2009, Journal of biomedical optics.

[62]  Yibin Ying,et al.  Noncontact and Wide-Field Characterization of the Absorption and Scattering Properties of Apple Fruit Using Spatial-Frequency Domain Imaging , 2016, Scientific Reports.

[63]  Venkataramanan Krishnaswamy,et al.  Spectral discrimination of breast pathologies in situ using spatial frequency domain imaging , 2013, Breast Cancer Research.

[64]  Brian W Pogue,et al.  Wide-field quantitative imaging of tissue microstructure using sub-diffuse spatial frequency domain imaging. , 2016, Optica.

[65]  A. Welch,et al.  A review of the optical properties of biological tissues , 1990 .

[66]  Brian W Pogue,et al.  Light scattering measured with spatial frequency domain imaging can predict stromal versus epithelial proportions in surgically resected breast tissue , 2018, Journal of biomedical optics.

[67]  V. Ghura,et al.  Current Concepts in the Surgical Management of Non-melanoma Skin Cancers. , 2019, Clinical oncology (Royal College of Radiologists (Great Britain)).

[68]  J. Ross,et al.  Partial orchiectomy vs. radical orchiectomy for pediatric testis tumors , 2020, Translational andrology and urology.