Statistical Considerations and Tools to Improve Histopathologic Protocols with Spectroscopic Imaging

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.

Automated summary

Advancements in infrared spectroscopic imaging and data science offer unique opportunities for histopathology validation studies. This study examines the discrimination potential of infrared metrics for different histologic classes and introduces an automated annotation transfer tool for large-scale training/validation. Results from supervised and unsupervised analysis provide insights for identifying diagnostic groups/patterns and improving training of histopathological models.