Automated detection of immunofluorescently labeled cytomegalovirus‐infected cells in isolated peripheral blood leukocytes using decision tree analysis

Abstract

Background: Cytomegalovirus (CMV) infection continues to be a major problem for immunocompromised patients. Detection of viral antigens in leukocytes (antigenemia assay) is widely used for the diagnosis of CMV infection and for guiding antiviral therapy. The antigenemia technique, contingent upon the manual microscopic analysis of rare cells, is a laborious task that is subject to human error. In this study, we combine automated microscopy with artificial intelligence for reliable detection of fluorescently labeled CMV-infected cells. Methods: Cytospin preparations of peripheral blood leukocytes were immunofluorescently labeled for the CMV lower matrix phosphoprotein (pp65) and scanned in the Rare Event Imaging System (REIS), a fully automated image cytometer. The REIS detected potential positive objects and digitally recorded 49 measured cellular features for each identified case. The measurement data of these objects were analyzed by the See5 decision tree (DT) algorithm to ascertain whether they were true-positive detections.

Objective Assessment of Cancer Biomarkers Using Semi‐Rare Event Detection

“…The system presented here is capable of dealing with such specimens, rendering it useful for analysis of biomarkers which are either not fully specific for abnormal cells or biomarkers which show nonspecific background staining. Two previous studies [13,15] employing cell features for rare event detection aimed at differentiating between true and false positive events, rather than locating the most informative positive events. In cases with many positive events, the system described in the present paper focuses on positive cells and cell clusters exhibiting the most extensive and/or intense staining pattern.…”