Comparison of manual and automated digital image analysis systems for quantification of cellular protein expression

Abstract

Objective. Quantifying protein expression in immunohistochemically stained histological slides is an important tool for oncologic research. The use of comput er-ai ded eval uat i on of IHC-st ai ned sl i des significantly contributes to objectify measurements. Manual digital image analysis (mDIA) requires a userdependent annotation of the region of interest (ROI). Others have built-in machine learning algorithms with automated digital image analysis (aDIA) and can detect the ROIs automatically. We aimed to investigate the agreement between the results obtained by aDIA and those derived from mDIA systems. Methods. We quantified chromogenic intensity (CI) and calculated the positive index (PI) in cohorts of tissue microarrays (TMA) using mDIA and aDIA. To consider the different distributions of staining within cellular subcompartments and different tumor architecture our study encompassed nuclear and cytoplasmatic stainings in adenocarcinomas and squamous cell carcinomas. Results. Within all cohorts, we were able to show a high correlation between mDIA and aDIA for the CI (p<0. 001) al ong wi t h hi gh agreement for t he PI. Moreover, we were able to show that the cell detections of the programs were comparable as well and both pr oved t o be r el i abl e when compar ed t o manual counting. Concl usi on. mDI A and aDI A show a hi gh correlation in acquired IHC data. Both proved to be suitable to stratify patients for evaluation with clinical data. As both produce the same level of information, aDIA might be preferable as it is time-saving, can easily be reproduced, and enables regular and efficient output in large studies in a reasonable time period.