Abstract
The importance of fibrillar collagen topology and organization in disease progression and prognostication in different types of cancer has been characterized extensively in many research studies. These explorations have either used specialized imaging approaches, such as specific stains (e.g., picrosirius red), or advanced and costly imaging modalities (e.g., second harmonic generation imaging (SHG)) that are not currently in the clinical workflow. To facilitate the analysis of stromal biomarkers in clinical workflows, it would be ideal to have technical approaches that can characterize fibrillar collagen on standard H&E stained slides produced during routine diagnostic work. Here, we present a machine learning-based stromal collagen image synthesis algorithm that can be incorporated into existing H&E-based histopathology workflow. Specifically, this solution applies a convolutional neural network (CNN) directly onto clinically standard H&E bright field images to extract information about collagen fiber arrangement and alignment, without requiring additional specialized imaging stains, systems or equipment.
Highlights
The importance of fibrillar collagen topology and organization in disease progression and prognostication in different types of cancer has been characterized extensively in many research studies
We showed that LC-PolScope, a sensitive polarization imaging system, can be used for imaging collagen in histopathology slides without the need for intensifying birefringence using picrosirius red staining, with results comparable to Second Harmonic Generation imaging (SHG) when quantifying fiber orientation or alignment[11,20], LC-Polscope is simpler and very cost effective compared to SHG imaging, and does not require additional staining methods, this modality requires several modifications to the pathologist’s microscope including additions of a chromatic filter, special variable retarders, and circular and linear polarizers
This alteration can facilitate fiber tracking in CurveAlign[40]. This discontinuity is due to unmet phase matching conditions in SHG imaging that we will address in the discussion
Summary
The importance of fibrillar collagen topology and organization in disease progression and prognostication in different types of cancer has been characterized extensively in many research studies. These explorations have either used specialized imaging approaches, such as specific stains (e.g., picrosirius red), or advanced and costly imaging modalities (e.g., second harmonic generation imaging (SHG)) that are not currently in the clinical workflow. We present a machine learning-based stromal collagen image synthesis algorithm that can be incorporated into existing H&E-based histopathology workflow This solution applies a convolutional neural network (CNN) directly onto clinically standard H&E bright field images to extract information about collagen fiber arrangement and alignment, without requiring additional specialized imaging stains, systems or equipment. This adds more steps making it less suitable for incorporation into real-time pathology workflows
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
