Quantitative Tissue Property Measurements with Structured Illumination and Deep Learning

We present a content-aware deep learning technique to estimate tissue optical properties and oxygenation from single structured illumination images. It is wide-field, data-efficient, and robust to various tissue types. This technique has the potential to enable rapid and accurate tissue property measurements in clinical settings.

[1]  E. Sevick-Muraca,et al.  Quantitative optical spectroscopy for tissue diagnosis. , 1996, Annual review of physical chemistry.

[2]  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.

[3]  Raymond Y. K. Lau,et al.  Least Squares Generative Adversarial Networks , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

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

[5]  Sylvain Gioux,et al.  Wavelength optimization for rapid chromophore mapping using spatial frequency domain imaging. , 2010, Journal of biomedical optics.

[6]  Faisal Mahmood,et al.  Deep learning-based depth estimation from a synthetic endoscopy image training set , 2018, Medical Imaging.

[7]  Sandra Sudarsky,et al.  Deep learning with cinematic rendering: fine-tuning deep neural networks using photorealistic medical images , 2018, Physics in medicine and biology.

[8]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[10]  Won-Ki Jeong,et al.  FusionNet: A Deep Fully Residual Convolutional Neural Network for Image Segmentation in Connectomics , 2016, Frontiers in Computer Science.

[11]  Zachary A. Steelman,et al.  Light scattering methods for tissue diagnosis. , 2019, Optica.

[12]  R. Richards-Kortum,et al.  Light scattering from cervical cells throughout neoplastic progression: influence of nuclear morphology, DNA content, and chromatin texture. , 2003, Journal of biomedical optics.

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

[14]  Simon Osindero,et al.  Conditional Generative Adversarial Nets , 2014, ArXiv.