The Diagnostic Performance of the Cellavision DC-1 Digital Morphology Analyser on Leukaemia Samples

Background/Objectives: Digital morphology analysers have been developed to overcome the limitations of manual microscopy. This study aimed to evaluate the performance of the DC-1 on leukaemia samples, determining if it is a suitable for the identification of leukaemia in low-throughput or remote laboratories. To the best of our knowledge, there is no current published literature evaluating the performance of the DC-1 with leukaemia samples. Methods: This study utilised 88 leukaemia peripheral blood smears donated from various anonymous hospitals and medical laboratories in collaboration with RMIT university. DC-1 pre-classification was compared with post-classification using Cohen’s kappa, sensitivity, and specificity calculations. Pre- and post-classification was compared with manual microscopy using Passing–Bablok regression, Pearson’s r correlation, and Bland–Altman analysis. Results: DC-1 pre-classification results showed a moderate agreement with post-classification (k = 0.52), a very high specificity for most leukocytes (>94%) and variable sensitivity (21–86%). Pre- and post-classification displayed a higher accuracy and correlation with manual results for segmented neutrophils and lymphocytes, compared to other leukocyte classes. Additionally, there was an improvement in the post-classification of immature granulocytes, band neutrophils, and blast cells compared to pre-classification. Conclusions: The results indicate that the DC-1 displayed a better performance for the classification of segmented neutrophils and lymphocytes compared to other cell classes, indicating that the DC-1 is more acceptable for use in infection or normal samples, as opposed to leukaemia. The gold standard therefore remains with the morphologist who can distinguish leukaemia samples.