Ultraviolet photoacoustic remote sensing microscopy provides label-free optical absorption contrast comparable to hematoxylin staining. This has been combined with 266 nm optical scattering microscopy offering eosin-like contrast. Here, we use unsupervised deep learning-based style transfer using the CycleGAN approach to render these pseudo-colored virtual histological images in a realistic stain style comparable to the H&E gold standard in unstained human and murine tissue specimens. A multi-pathologist diagnostic concordance study found a sensitivity of 89%, specificity of 91%, and accuracy of 90%. A blinded subjective stain quality survey suggested virtual histology was preferred over frozen sections at the 95% confidence level.
Previous photoacoustic remote sensing virtual histology approaches were too slow to use intraoperatively. We present a new scanning methodology with simultaneous galvanometer mirror and constant velocity mechanical scanning to greatly increase image acquisition speed. Human breast and prostate samples are imaged over an area of 4mm x 4mm in 40s with a 0.5μm resolution resolving both cancerous and healthy tissue. Histological detail is clearly visible in our images where tissue organization and subcellular nuclei density can be observed to aid histologists in determining margin status and cancer grading.
Currently, there is an inability to obtain fast realistic label-free virtual histopathological images of tissues. We previously introduced ultraviolet photoacoustic remote sensing microscopy as a method to obtain virtual hematoxylin contrast albeit without the ability to obtain virtual eosin contrast. By utilizing UV scattering as a high-resolution eosin channel we are able to produce complete H&E-like virtual histology of unstained human breast lumpectomy specimen sections. By further leveraging a novel colormap matching algorithm with this UV scattering, we generate H&E-like output that is shown to have strong concordance with true H&E-stained adjacent sections, showing promising diagnostic utility.
A combined synthetic aperture optical coherence microscopy and ultraviolet photoacoustic remote sensing system is presented, capable of fast scanning of tissues for tumor margin inspection. It provides a fast 3D OCT mode for imaging tissues to depths of ~1mm, and a superficial virtual histology mode provided by absorption contrast UV-PARS for virtual hematoxylin contrast and coherence-gated scattering microscopy for virtual eosin contrast. Breast lumpectomy specimens are scanned in each mode to evaluate the extent of features in depth and generate en-face images with histological detail and realism, providing results accurately interpretable by pathologists.
Following resection of cancerous tissues, specimens are excised from the surgical margins to be examined post-operatively for the presence of residual cancer cells. Hematoxylin and eosin (H&E) staining is the gold standard of histopathological assessment. Ultraviolet photoacoustic microscopy (UV-PARS), combined with scattering microscopy, provides virtual nuclei and cytoplasm contrast similar to H&E staining. A generative adversarial network (GAN) deep learning approach, specifically a CycleGAN, was used to perform style transfer to improve the histological realism of UV-PARS generated images. Post-CycleGAN images are easier for a pathologist to examine and can be input into existing machine learning pipelines for H&E-stained images.
Ultraviolet photoacoustic remote sensing (UV-PARS) microscopy is a non-contact imaging modality capable of producing label-free absorption contrast images of cell nuclei. This virtual hematoxylin-like imaging combined with virtual eosin-like data from 1310 nm scattering microscopy can provide complete virtual H&E histologically in unstained tissues. Here, we develop contour scanning for applying UV-PARS and scattering-based virtual histology in fresh and formalin-fixed thick tissues. Our spectral-domain OCT-guided approach initially scans specimens in 3D, and a custom algorithm extracts the surface contour. A high-resolution UV-PARS scan is then performed using a z-axis stage for dynamic focusing to compensate for sample surface irregularities.
We develop a dual-modality imaging system for virtual histology in breast tumor specimens, augmenting depth-resolved scattering contrast from OCT with sub-cellular resolution and label-free molecular specificity from UV photoacoustic remote sensing.
We demonstrate the use of Photoacoustic Remote Sensing (PARS) and scattering microscopy capable of acquiring virtual depth-resolved images of tissues with virtual contrast of hematoxylin using PARS & eosin using scattering microscopy.
Hematoxylin and Eosin (H and E) staining is the gold standard for the majority of histopathological diagnostics but requires lengthy processing times not suitable for point-of-care diagnosis. Here we demonstrate a 266-nm excitation Ultraviolet Photoacoustic Remote Sensing (UV-PARS) and Scattering Microscopy system capable of virtual H and E 3D imaging of tissues in conjunction with with confocal fluorescence microscopy (CFM) for validation in thick tissues. We demonstrate the capabilities of this dual-contrast system for en-face planar and volumetric imaging of human tissue samples exhibiting high concordance with the gold standard of H and E staining procedures as well as confocal fluorescence microscopy. To our knowledge, this is the first near real-time microscopy approach capable of volumetric imaging unstained thick tissues with virtual H and E contrast.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.