Digital imaging/morphology is the next chapter in hematology

Feb. 22, 2018

Digital imaging/morphology makes use of digital images and software algorithms to classify hematological cells, such as leukocytes and red blood cells. For a subset of leukocytes, digital system classification correlates well with the manual microscope method, the gold standard. Digital imaging thereby leads to a faster, more efficient, and more standardized way of performing a morphological analysis of a peripheral blood smear. Future possible applications include the morphological analysis of other cell categories such as red blood cells and thrombocytes and digital analysis of other materials such as bone marrow samples.

Furthermore, digital imaging can be used as an excellent learning tool. Independently organized quality surveys should be implemented by manufacturers of digital microscopy systems to ensure quality requirements. Integration of digital imaging with basic cell counter results could lead to a faster detection and higher sensitivity and specificity in the detection of hematological malignancies.

Morphological analysis of the peripheral blood smear (PBS) is an essential element of hematological diagnostics.1 Traditionally, the analysis of a PBS has been performed by using the manual microscope method. This method, however, is labor-intensive, requires continuous training of personnel, and is subject to relatively large inter-observer variability.2-4 The development of digital microscope systems, capable of using digital images of leukocytes, erythrocytes, and thrombocytes for classification, has been ongoing for more than a decade.4,5

For reasons of clarity, this review will discuss digital imaging by use of a digital microscope developed by the company Cellavision. Sysmex Corporation has generated a similar digital microscope, integrated in a hematology track incorporating both a cell-counter and a slide-maker stainer.26 Other companies have generated digital microscopy systems,6,7,27 especially in the field of pathology.8 However, these systems are still in the experimental phase with regard to implementation in routine (hematological) diagnostics and are currently more used for diagnostic remote and scholar use. In essence, they are not now used as pathology filters in the diagnostic work-up. Some systems have, however, found a central place in the routine hematological peripheral blood smear screening.

The digital workflow in detail

The digital microscope (DM) makes use of a digital camera, which is capable of generating high-resolution images of leukocytes, red blood cells, and thrombocytes. The systems are equipped with software capable of not only detecting these cells, but also subsequently classifying them in the correct cell class. This software application was developed using an artificial neural network, and it considers a large number of features, such as size, roundness, and size and shape of the nucleus for the morphological classification of leukocytes. The number of cells counted by the system can be set by the operator, and the DM will present the results in both absolute numbers and percentages. The classification results can then be judged by an experienced morphological research technician. The expert will validate the results and send them to the laboratory information system (LIS) and hospital information system (HIS). The classification by the system without manual intervention will be defined as pre-classification throughout this article. The subsequent possible re-classification by a trained morphological expert will be defined as post-classification.

Before digital microscopy systems can be implemented in daily hematological routine with regard to PBS analysis, these systems should be validated thoroughly. Currently, the manual microscope method is considered the standard. To date, various papers have described accuracy- and precision-studies of digital imaging when compared to manual assessment. It has been shown that digital microscopy shows good correlation with the standard with regard to the five-part differential: segmented, eosinophilic, and basophilic granulocytes;
lymphocytes; and monocytes. Nucleated red blood cells (NRBC) also displayed a good correlation.9-11

Moreover, digital imaging leads to reproducible results when comparing the results of independently operated digital microscope systems of the same type and brand.12 Pre-classification of immature granulocytes and myeloid progenitor cells showed inadequate correlation with the manual method, requiring manual supervision to ensure proper results. Therefore the mathematical algorithm to classify these classes should be further improved. However, one could argue that in a clinical situation the sole description of left-shift is sufficient for diagnostics and does not necessarily need specific subclassification of individual myeloid progenitor cells. Combining this with state-of-the art immature granulocyte functions on cell counters could help with this issue.

Lymphocyte pathology

Correct subclassification of specific lineage subset pathology, e.g., follicular lymphoma (FCL) or mantle cell lymphoma (MCL) in the case of abnormal malignant lymphocyte classes present, is currently also still lacking. However, recent advances have been made in this specific area. Alferez et al have developed algorithms to discriminate hairy cells and chronic lymphocytic leukemia (CLL) cells from normal lymphocytes using digital imaging analysis.13 It seems likely that further improvement of these algorithms will facilitate the detection and classification of pathological cells in the nearby future.

Blast cells

Several studies showed high sensitivity scores for the detection of blast cells in the PBS using digital imaging.10,11 Unfortunately this was accompanied by relatively low specificity scores in the pre-classification, rendering the definitive result still subject to experienced manual observer validation.11 However, the high sensitivity makes digital imaging extremely suitable as a screening tool for the presence of blast cells in a PBS. This is, for instance, very useful in myelodysplastic syndrome (MDS) and acute myeloid leukemia (AML) patient follow-up during therapy treatment, and our laboratory has been using this specific feature with satisfying results for several years now.


With regard to thrombocyte count, digital imaging has been shown to correlate well with both manual and cell counter results.14 The analysis of platelet morphology (e.g. granularity) using digital imaging is, however, still a work in progress. This development might prove clinically relevant. For example, we know that essential thrombocytosis (ET, MPN) patients can display morphological aberrant thrombocytes in the absence of an absolute elevated thrombocyte count (currently the cut-off point for the diagnosis ET is >450 x 109/L as one of the major criteria).

Red blood cell morphology

Recent advances have also been made in the field of red blood cell morphology using digital imaging. The advanced RBC module generates between 2,000 and 4,000 individual images of red blood cells. The systems subsequently classify the cells on the basis of various morphological algorithms, comparable to the method for five-part leukocyte classification.

The first steps toward standardization of the morphological analysis of the RBC lineage by use of digital imaging have recently been made. Recent studies using a morphological red blood cell module show lower within-run, between-run, and between-observer coefficients of variation when counting schistocytes compared to the coefficients observed for manual assessment. Both the study of Hervent et al and Egele et al show that digital imaging overestimates the percentage of schistocytes in the pre-classification, resulting in a high sensitivity.15,16 The subsequent low specificity, however, underlines the need for post-classification/manual supervision.

Overestimation is also seen in the pre-classification of teardrop cells, for instance seen in myeloproliferative diseases (i.e. myelofibrosis).17 Detection of inclusions has also been shown to be possible with digital imaging. A study by Racsa et al demonstrates that digital imaging has the potential to detect intracellular parasites in routine screening of blood smears for RBC morphology.18 Howell-Jolly bodies can also be detected by the systems, and Revol et al recently even used digital imaging machines to quantify Howell-Jolly body-like inclusions in neutrophils as a possible predictor in ganciclovir toxicity.19 Moreover, digital microscopy of red blood cells has been successfully used as a screening tool for the diagnosis of hereditary hemolytic anemia.28

These latter, specific applications of digital imaging, however, are currently not FDA-approved, and the underlying detection and decision algorithms need further improvement before these modules can be implemented safely in routine diagnostics.

Integration in daily practice

The introduction of digital microscopes implemented in total lab automation tracks (i.e., coupled with cell-counter and slide-maker stainers) paves the way for the implementation of clinical decision modules by coupling cell counter results with digital imaging results.5 This will undoubtedly lead to a higher sensitivity and specificity in the detection and classification of hematological diseases. Several requirements will have to be met, however, before we reach this state of development. One of these requirements is continuous 24/7 proper sample preparation.

Good quality slide/sample preparation plays a pivotal role in good detection and subsequent classification of both leukocytes and red blood cells using digital imaging. For instance, the digital imaging systems have difficulty separating neutrophilic granulocytes from basophilic granulocytes when the staining is of insufficient quality and gets too dark. Manual prepared slides are of insufficient quality to allow for a good and reproducible classification. Semi-automated and fully-automated slide preparation and staining systems (either May Grünwald Giemsa or Wright staining) are the preferred methods of choice.

To summarize, digital imaging seems to work for several cell classes in classifying both leukocytes and red blood cells in peripheral blood smears. The automated analysis of body fluids has also been investigated.20 Results from both cerebrospinal fluids and other body fluids (including abdominal fluids/ascites and CAPD) show good and clinically acceptable accuracy when comparing automated morphological analysis using digital imaging with the manual method. Even the pre-classification is good for most body fluid categories. A big drawback for the automated digital analysis of body fluids, however, is the lack of recognition of certain defined categories. For instance, the system is currently incapable of detecting and classifying mesothelial cells, and possible tumor cells present are frequently found in the category “other” (subcategory present in body fluid module). Another disadvantage is the analysis time; automated digital analysis of body fluids still requires significant manual correction and therefore takes longer than a full classification done manually. Improvement of the current digital body fluid applications is needed before this module can be fully integrated in the routine body fluid diagnostic process.

Digital images were already being used for scholarly purposes long before the introduction of digital microscopy systems. With the introduction of such systems, the application of digital imaging in educational settings has grown tremendously. Cell atlases and even mobile apps have been generated to teach students the various normal and pathological cell classes that can be found in both PBS and body fluids. Pictures of classified or pre-classified cells can be sent to colleagues all over the world for a second opinion or to share rarely seen diseases. One can even imagine that imaging modules that are capable of pre-classification could send their pre-classification results to a central location for post-classification. This would be very helpful for hospital locations with low-volume PBS amounts which struggle to maintain morphological expertise.

Quality survey issues in digital imaging

Whether it is manual microscopy or digital imaging, good-quality slide preparation and staining is and will remain essential. Digital images already raised the possibility for quality surveys a long time before digital imaging systems capable of pre-classifying cells classes were generated, implemented, and commercialized.21-23 Also, commercial use of such quality surveys has become apparent.23 The quality module usually makes use of a digitalized slide that can be uploaded via the internet. Technicians can subsequently classify the leukocytes, RBCs, and thrombocytes. Next the results are compared to a gold standard, which is usually the clinical chemist or pathologist. Scores can then be used to identify potential training possibilities for individual laboratorians. The hemato-morphology field would greatly benefit from an independent, quality-controlled digital slide institution to fully implement digital quality surveys as a standard routine requisite. Therefore, commercial organizations should join hands with local established quality institutions in morphology to bring digital quality control to the next level.

Integration of digital imaging with routine cell counter results

The next step in hematology will be the implementation of digital imaging results with routine cell counter results. Several companies have already embraced this idea.5,24 Patients could greatly benefit from integration, especially in the detection of pathology that requires immediate medical intervention. For example, the diagnosis of thrombotic thrombocytopenic purpura (TTP) requires fast detection and subsequent treatment.25 A clinical diagnostic module would involve fast detection of (hemolytic) anemia in combination with a thrombocytopenia on a cell counter. On the basis of these parameters and possible cell counter flaggings for fragmented red blood cells, a slide would be generated. This could then be automatically analyzed for the presence of schistocytes/fragmentocytes by digital imaging. Current pre-classification cut-off values could be used to warn laboratory personnel in case of exceedance. So, for instance, a hemoglobin value of 9 g/dl in a 35-year old female with a thrombocyte count of 25 x 109/L in combination with a pre-classification result of 10 percent schistocytes should be presented by the system as a high-priority differential.

This is only one example of the many possibilities these systems could provide. The detection of most hematological malignancies, whether MDS/AML or MPN, would benefit from structural integration of cell counter results with digital imaging. Diagnostic machines such as hematological cell counters and digital microscopes should be used as pathology filters to filter out diseases and discriminate patients from non-patients. Subsequent additional diagnostics, such as flow cytometry, molecular, and cytogenetic testing (on peripheral blood or bone-marrow samples) can then be used to finalize the diagnosis. Interestingly some companies are already trying to perform automated digital analysis of bone marrow samples using digital imaging.27

Routine cell counters have proved themselves to be robust and reliable diagnostic tools in detecting hematological pathology. Digital imaging systems will undoubtedly do the same in the upcoming years.


  1. Bain BJ. Diagnosis from the blood smear. N Engl J Med. 2005;353(5):498-507.
  2. Rumke CL. Imprecision of ratio-derived differential leukocyte counts. Blood Cells. 1985;11(2):311-314, 315.
  3. Bentley SA. Automated differential white cell counts: a critical appraisal. Baillieres Clin Haematol. 1990;3(4):851-869.
  4. Ceelie H, Dinkelaar RB, van Gelder W. Examination of peripheral blood films using automated microscopy; evaluation of Diffmaster Octavia and Cellavision DM96. J Clin Pathol. 2007;60(1):72-79.
  5. Tabe Y, Yamamoto T, Maenou I, et al. Performance evaluation of the digital cell imaging analyzer DI-60 integrated into the fully automated Sysmex XN hematology analyzer system. Clin Chem Lab Med. 2015;53(2):281-289.
  6. Yu H, Ok CY, Hesse A, et al. Evaluation of an automated digital imaging system, Nextslide Digital Review Network, for examination of peripheral blood smears. Arch Pathol Lab Med. 2012;136(6):660-667.
  7. Medica Corporation. Hematology imaging system.
  8. Higgins C. Applications and challenges of digital pathology and whole slide imaging. Biotech Histochem. 2015;90(5):341-347.
  9. Briggs C, Longair I, Slavik M, et al. Can automated blood film analysis replace the manual differential? An evaluation of the CellaVision DM96 automated image analysis system. Int J Lab Hematol. 2009;31(1):48-60.
  10. Kratz A, Bengtsson HI, Casey JE, et al. Performance evaluation of the CellaVision DM96 system: WBC differentials by automated digital image analysis supported by an artificial neural network. Am J Clin Pathol. 2005;124(5):770-781.
  11. Stouten K, Riedl JA, Levin MD, van Gelder W. Examination of peripheral blood smears: performance evaluation of a digital microscope system using a large-scale leukocyte database. Int J Lab Hematol. 2015;37(5):e137-40.
  12. Riedl JA, Stouten K, Ceelie H, Boonstra J, Levin MD, van Gelder W. Interlaboratory reproducibility of blood morphology using the digital microscope. J Lab Autom. 2015;20(6):670-675.
  13. Alferez S, Merino A, Mujica LE, Ruiz M, Bigorra L, Rodellar J. Automatic classification of atypical lymphoid B cells using digital blood image processing. Int J Lab Hematol. 2014;36(4):472-480.
  14. Gao Y, Mansoor A, Wood B, Nelson H, Higa D, Naugler C. Platelet count estimation using the CellaVision DM96 system. J Pathol Inform. 2013;4:16-3539.114207.
  15. Hervent AS, Godefroid M, Cauwelier B, Billiet J, Emmerechts J. Evaluation of schistocyte analysis by a novel automated digital cell morphology application. Int J Lab Hematol. 2015;37(5):588-596.
  16. Egelé A, van Gelder W, Riedl J. Automated detection and classification of schistocytes by a novel red blood cell module using digital imaging/microscopy. J Hematol. 2015;4(2):184-186.
  17. Egelé A, van Gelder W, Riedl J. Automated detection and classification of teardrop cells by a novel RBC module using digital imaging/microscopy. Int J Lab Hematol. 2015;37(6):e153-6.
  18. Racsa LD, Gander RM, Southern PM, et al. Detection of intracellular parasites by use of the CellaVision DM96 analyzer during routine screening of peripheral blood smears. J Clin Microbiol. 2015;53(1):167-171.
  19. Revol B, Thiebaut-Bertrand A, Carre M, Bulabois CE, Mossuz P, Mondet J. Quantification of Howell-Jolly body-like inclusions in ganciclovir toxicity using CellaVision DM96 analyser. Br J Haematol. 2016;174(4):647-639.
  20. Riedl JA, Dinkelaar RB, van Gelder W. Automated morphological analysis of cells in body fluids by the digital microscopy system DM96. J Clin Pathol. 2010;63(6):538-543.
  21. Hutchinson CV, Brereton ML, Burthem J. Digital imaging of haematological morphology. Clin Lab Haematol. 2005;27(6):357-362.
  22. Burthem J, Brereton M, Ardern J, et al. The use of digital ‘virtual slides’ in the quality assessment of haematological morphology: results of a pilot exercise involving UK NEQAS(H) participants. Br J Haematol. 2005;130(2):293-296.
  23. Cellavision proficience software.
  24. Siemens Hemalink user meeting 2014. Available at:
  25. George JN, Nester CM. Syndromes of thrombotic microangiopathy. N Engl J Med. 2014;371(7):654-666.
  26. Kim HN, Hur M, Kim H, Kim SW, Moon HW, Yun YM. Performance of automated digital cell imaging analyzer Sysmex DI-60. Clin Chem Lab Med. 2017 56(1):94-102.
  27. West Medica Austria. Vision Hema: automatic identification and pre-classification of blood cells and bone marrow cells.
  28. Huisjes R, van Solinge WW, Levin MD, van Wijk R, Riedl JA. Digital microscopy as a screening tool for the diagnosis of hereditary hemolytic anemia. Int J Lab Hematol. 2017;Nov 1.

Jurgen Riedl, PhD, is a clinical chemist and head of the diagnostic hematology department of the Albert Schweitzer hospital laboratories, part of Result Laboratories in Dordrecht, the Netherlands. He is considered an international expert on digital imaging and digital morphology.

Photo 241571148 © BiancoBlue |
Photo 75539817 © Vladimirs Prusakovs |
Dreamstime Xxl 75539817
Image by NatalyaBurova @
Coverbackgroundv1 Forstory
Photo 14015956 © Sebastian Czapnik |
Dreamstime Xxl 14015956