Statistical Considerations and Tools to Improve Histopathologic Protocols with Spectroscopic Imaging

Abstract

Advances in infrared (IR) spectroscopic imaging instrumentation and data science now present unique opportunities for large validation studies of the concept of histopathology using spectral data. In this study, we examine the discrimination potential of IR metrics for different histologic classes to estimate the sample size needed for designing validation studies to achieve a given statistical power and statistical significance. Next, we present an automated annotation transfer tool that can allow large-scale training/validation, overcoming the limitations of sparse ground truth data with current manual approaches by providing a tool to transfer pathologist annotations from stained images to IR images across diagnostic categories. Finally, the results of a combination of supervised and unsupervised analysis provide a scheme to identify diagnostic groups/patterns and isolating pure chemical pixels for each class to better train complex histopathological models. Together, these methods provide essential tools to take advantage of the emerging capabilities to record and utilize large spectroscopic imaging datasets.

Digital Histopathology by Infrared Spectroscopic Imaging

“…Increasing measurement capability will provide more data to address confounding variables. The combination of different models, effect sizes, and data used, including the numbers of tissue samples, makes it challenging to provide a ready guideline for a satisfactorily robust algorithm (134). A general consensus is that modern imaging and tissue microarrays allow data to be recorded from hundreds of patients' (relatively small) samples.…”