Differential counting of blood leukocytes using automated microscopy and a decision support system based on artificial neural networks - evaluation of DiffMaster^TM Octavia

Abstract

The morphological appearance of blood cells has an established association to clinical conditions. A novel system, DiffMaster Octavia for differential counting of blood leukocytes, has been evaluated. The system consisted of a microscope, 3-chip color charge coupled device (CCD) camera, automated motorized stage holder, electronic hardware for motor and light control and software for automatic cell location and image processing for preclassification of blood cells using artificial neural networks. The DiffMaster test method, was evaluated on 322 routine blood samples (400 cells per sample) using manual microscopy as reference method. The results showed a correlation of determination (r(2)) of 0.8-0.98 for the normal cell classes and blast cells. The DiffMaster correctly preclassified 89% of all leukocytes with a good reproducibility. After verification of the cell classes, the agreement between the test and reference method was 91% whether the sample was abnormal or normal. The clinical sensitivity was 98% and specificity 82%. The sensitivity to identify blast cells was slightly higher with the DiffMaster than manual microscopy. Similar levels of short-term imprecision for the two methods were found for all cell classes. In conclusion this study shows that the DiffMaster can provide a decision support system which, together with a qualified morphologist, can generate leukocyte differential count reports of high quality.

Automation and validation of a rapid method to assess neutrophil and monocyte activation by routine fluorescence flow cytometry in vitro

“…In this study we adapted the system to accurately determine research parameters reflecting and describing the relative position of M, PMN and total leukocytes based on fluorescence intensity of intracellular NA and protein material, side scatter for granularity and impedance count for volume or shape change depending on total lipid membrane amount. All findings were compared with and correlated to established methods like microscopic morphological cell diagnostic by pattern recognition (27), cytokine production and release (TNF-a and IL-8) and intracellular myeloperoxidase concentration in order to establish the method as a standardized and reproducible routine procedure, to understand the functional state and activity of M and PMN, the defense cells of the human innate immune system. The interpretation of the functional state or activation of M and PMN by simple means of analyser research parameters has been investigated by in vitro experiments with easily obtainable, EDTA anticoagulated whole blood samples.…”

“…The 200-cell leukocyte differential count was performed by standardized automated image analysis (27) with preclassification (DiffMaster DM 96 from CellaVision AB, Sweden). After automated preclassification of segmented neutrophils, monocytes, lymphocytes, eosinophils and basophils white blood cells were manually classified into activated cell type categories ( Fig.…”

Total nucleated cell differential for blood and bone marrow using a single tube in a five‐color flow cytometer

“…In general, the performance of the automatic classification declines with increasing abnormality/immaturity of the cells. The DiffMaster TM Octavia has been validated against conventional microscopy by an extended evaluation of 322 routine specimens following the NCCLS-H20A protocol (10).…”

Interlaboratory Reproducibility of Blood Morphology Using the Digital Microscope

“…7 It was previously shown that a DM system, using several advanced mathematical algorithms, is capable of correct classification of leukocytes in peripheral blood and body fluid samples in relation to manual microscopic assessment of the five main peripheral blood cell categories. [3][4][5][8][9][10] An overall accuracy of 92.0% was found when the preclassification results of the DM96 (Cellavision, Lund, Sweden) were compared to those of manual assessment. 3,11 It has been shown that the classification performance of this particular system is as reliable as manual classification by …”