Machine learning-based rapid diagnosis of human borderline ovarian cancer on second-harmonic generation images

Background: The collagen architecture in high grade serous ovarian cancer (HGSOC) is highly remodeled compared to the normal ovary and the fallopian tubes (FT). We previously used Second Harmonic Generation (SHG) microscopy and machine learning to classify the changes in collagen fiber morphology occurring in serous tubal intraepithelial carcinoma (STIC) lesions that are concurrent with HGSOC. We now extend these studies to examine collagen remodeling in pure p53 signatures, STICs and normal regions in tissues that have no concurrent HGSOC. This is an important distinction as high-grade disease can result in distant collagen changes through a field effect mechanism. Methods: We trained a linear discriminant model based on SHG texture and image features as a classifier to discriminate the tissue groups. We additionally performed mass spectrometry analysis of normal and HGSOC tissues to associate the differential expression of collagen isoforms with collagen fiber morphology alterations. Results: We quantified the differences in the collagen architecture between normal tissue and the precursors with good classification accuracy. Through proteomic analysis, we identified the downregulation of single α-chains including those for Col I and III, where these results are consistent with our previous SHG-based supramolecular analyses. Conclusion: This work provides new insights into ECM remodeling in early ovarian cancer and suggests the combined use of SHG microscopy and mass spectrometry as a new diagnostic/prognostic approach.

Download Full-text

Applications of Second-Harmonic Generation Imaging Microscopy in Ovarian and Breast Cancer

Perspectives in Medicinal Chemistry ◽

10.4137/pmc.s13214 ◽

2015 ◽

Vol 7 ◽

pp. PMC.S13214 ◽

Cited By ~ 22

Author(s):

Karissa Tilbury ◽

Paul J. Campagnola

Keyword(s):

Ovarian Cancer ◽

Second Harmonic Generation ◽

Harmonic Generation ◽

Second Harmonic ◽

Imaging Techniques ◽

Great Sensitivity ◽

Fiber Morphology ◽

Breast And Ovarian Cancer ◽

Epithelial Cancers ◽

Computationally Intensive

In this perspective, we discuss how the nonlinear optical technique of second-harmonic generation (SHG) microscopy has been used to greatly enhance our understanding of the tumor microenvironment (TME) of breast and ovarian cancer. Striking changes in collagen architecture are associated with these epithelial cancers, and SHG can image these changes with great sensitivity and specificity with submicrometer resolution. This information has not historically been exploited by pathologists but has the potential to enhance diagnostic and prognostic capabilities. We summarize the utility of image processing tools that analyze fiber morphology in SHG images of breast and ovarian cancer in human tissues and animal models. We also describe methods that exploit the SHG physical underpinnings that are effective in delineating normal and malignant tissues. First we describe the use of polarization-resolved SHG that yields metrics related to macromolecular and supramolecular structures. The coherence and corresponding phase-matching process of SHG results in emission directionality (forward to backward), which is related to sub-resolution fibrillar assembly. These analyses are more general and more broadly applicable than purely morphology-based analyses; however, they are more computationally intensive. Intravital imaging techniques are also emerging that incorporate all of these quantitative analyses. Now, all these techniques can be coupled with rapidly advancing miniaturization of imaging systems to afford their use in clinical situations including enhancing pathology analysis and also in assisting in real-time surgical determination of tumor margins.

Download Full-text