Fragmented red blood cells automated measurement is a useful parameter to exclude schistocytes on the blood film

1 Million Segmented Red Blood Cells With 240 K Classified in 9 Shapes and 47 K Patches of 25 Manual Blood Smears

Around 20% of complete blood count samples necessitate visual review using light microscopes or digital pathology scanners. There is currently no technological alternative to the visual examination of red blood cells (RBCs) morphology/shapes. True/non-artifact teardrop-shaped RBCs and schistocytes/fragmented RBCs are commonly associated with serious medical conditions that could be fatal, increased ovalocytes are associated with almost all types of anemias. 25 distinct blood smears, each from a different patient, were manually prepared, stained, and then sorted into four groups. Each group underwent imaging using different cameras integrated into light microscopes with 40X microscopic lenses resulting in total 47 K + field images/patches. Two hematologists processed cell-by-cell to provide one million + segmented RBCs with their XYWH coordinates and classified 240 K + RBCs into nine shapes. This dataset (Elsafty_RBCs_for_AI) enables the development/testing of deep learning-based (DL) automation of RBCs morphology/shapes examination, including specific normalization of blood smear stains (different from histopathology stains), detection/counting, segmentation, and classification. Two codes are provided (Elsafty_Codes_for_AI), one for semi-automated image processing and another for training/testing of a DL-based image classifier.

Computer vision quantitation of erythrocyte shape abnormalities provides diagnostic, prognostic, and mechanistic insight

Examination of red blood cell (RBC) morphology in peripheral blood smears can help diagnose hematologic diseases, even in resource-limited settings, but this analysis remains subjective and semiquantitative with low throughput. Prior attempts to develop automated tools have been hampered by their poor reproducibility and limited clinical validation. Here, we present a novel, open-source machine-learning approach (denoted as RBC-diff) to quantify abnormal RBCs in peripheral smear images and generate an RBC morphology differential. RBC-diff cell counts showed high accuracy for single-cell classification (mean AUC, 0.93) and quantitation across smears (mean R2, 0.76 compared with experts, interexperts R2, 0.75). RBC-diff counts were concordant with the clinical morphology grading for 300 000+ images and recovered the expected pathophysiologic signals in diverse clinical cohorts. Criteria using RBC-diff counts distinguished thrombotic thrombocytopenic purpura and hemolytic uremic syndrome from other thrombotic microangiopathies, providing greater specificity than clinical morphology grading (72% vs 41%; P < .001) while maintaining high sensitivity (94% to 100%). Elevated RBC-diff schistocyte counts were associated with increased 6-month all-cause mortality in a cohort of 58 950 inpatients (9.5% mortality for schist. >1%, vs 4.7% for schist; <0.5%; P < .001) after controlling for comorbidities, demographics, clinical morphology grading, and blood count indices. RBC-diff also enabled the estimation of single-cell volume-morphology distributions, providing insight into the influence of morphology on routine blood count measures. Our codebase and expert-annotated images are included here to spur further advancement. These results illustrate that computer vision can enable rapid and accurate quantitation of RBC morphology, which may provide value in both clinical and research contexts.

Hematology and Machine Learning

BACKGROUND

Substantial improvements in computational power and machine learning (ML) algorithm development have vastly increased the limits of what autonomous machines are capable of. Since its beginnings in the 19th century, laboratory hematology has absorbed waves of progress yielding improvements in both of accuracy and efficiency. The next wave of change in laboratory hematology will be the result of the ML revolution that has already touched many corners of healthcare and society at large.

CONTENT

This review will describe the manifestations of ML and artificial intelligence (AI) already utilized in the clinical hematology laboratory. This will be followed by a topical summary of the innovative and investigational applications of this technology in each of the major subdomains within laboratory hematology.

SUMMARY

Application of this technology to laboratory hematology will increase standardization and efficiency by reducing laboratory staff involvement in automatable activities. This will unleash time and resources for focus on more meaningful activities such as the complexities of patient care, research and development, and process improvement.

Combining imaging flow cytometry and machine learning for high-throughput schistocyte quantification: A SVM classifier development and external validation cohort

Background

Schistocyte counts are a cornerstone of the diagnosis of thrombotic microangiopathy syndrome (TMA). Their manual quantification is complex and alternative automated methods suffer from pitfalls that limit their use. We report a method combining imaging flow cytometry (IFC) and artificial intelligence for the direct label-free and operator-independent quantification of schistocytes in whole blood.

Methods

We used 135,045 IFC images from blood acquisition among 14 patients to extract 188 features with IDEAS® software and 128 features from a convolutional neural network (CNN) with Keras framework in order to train a support vector machine (SVM) blood elements’ classifier used for schistocytes quantification.

Finding

Keras features showed better accuracy (94.03%, CI: 93.75-94.31%) than ideas features (91.54%, CI: 91.21-91.87%) in recognising whole-blood elements, and together they showed the best accuracy (95.64%, CI: 95.39-95.88%). We obtained an excellent correlation (0.93, CI: 0.90-0.96) between three haematologists and our method on a cohort of 102 patient samples. All patients with schistocytosis (>1% schistocytes) were detected with excellent specificity (91.3%, CI: 82.0-96.7%) and sensitivity (100%, CI: 89.4-100.0%). We confirmed these results with a similar specificity (91.1%, CI: 78.8-97.5%) and sensitivity (100%, CI: 88.1-100.0%) on a validation cohort (n=74) analysed in an independent healthcare centre. Simultaneous analysis of 16 samples in both study centres showed a very good correlation between the 2 imaging flow cytometers (Y=1.001x).

Interpretation

We demonstrate that IFC can represent a reliable tool for operator-independent schistocyte quantification with no pre-analytical processing which is of most importance in emergency situations such as TMA.

Funding

None.

2021 update of the 2012 ICSH Recommendations for identification, diagnostic value, and quantitation of schistocytes: Impact and revisions

In 2012, the International Council for Standardization in Hematology (ICSH) published recommendations for the identification, quantitation, and diagnostic value of schistocytes. In the present review, the impact of these recommendations is evaluated. This work is based on citations in peer-reviewed papers published since 2012. The first 2012 ICSH Recommendations have also been revised to incorporate newly published data in the literature and current best laboratory practice. Recommended reference ranges have been proposed for healthy adults and full-term neonates of 1% or less schistocytes. More than 1% of morphologically identified schistocytes on the blood film are considered suspicious for thrombotic microangiopathy. For preterm infants, a normal level of 5% or less is recommended. The fragment red cell count (FRC) generated by some automated hematological analyzers provides a valuable screening tool for the presence of schistocytes. Specifically, the absence of FRCs can be used as a valuable parameter to exclude the presence of schistocytes on the blood film. The validity and usefulness of microscope schistocytes and automated FRCs, respectively, are discussed in the context of the laboratory diagnostic tests used for thrombotic microangiopathies.

Full-field hemocytometry. Forty years of progress seen through Clinical and Laboratory Hematology and the International Journal of Laboratory Hematology

The extraordinary advances in clinical hematology, biology, and oncology in the last decades would not have been possible without discovering how to identify and count the cells circulating in the blood. For centuries, scientists have used slides, counting chambers (hemocytometers), and diluting and staining solutions for this task. Then, automated hemocytometry began. This science, now linked to the daily routine of laboratory hematology, has completed an overwhelming path over a few decades. Our laboratories today operate with versatile multiparameter systems, ranging from complex single-channel instruments to bulky continuous flow machines. In terms of clinical information obtained from a simple routine blood test, the full exploitation of their potential depends on the operators' imagination and courage. A comprehensive review of the scientific publications that have accompanied the development of hemocytometry from the 1950s to today would require entire volumes. More than seven hundred contributions that authors worldwide have published in Clinical and Laboratory Haematology until 2007 and then the International Journal of Laboratory Hematology are summarized. Such journals have represented and hopefully will continue to represent the privileged place of welcome for future scientific research in hemocytometry. Improved technologies, attention to quality, new reagents and electronics, information technology, and scientist talent ensure a more profound and deeper knowledge of cell properties: current laboratory devices measure and count even minor immature or pathological cell subpopulations. Full-field hemocytometry includes the analysis of nonhematic fluids, digital adds to the microscope, and the development of effective point-of-care devices.

Schistocyte quantitation, thrombotic microangiopathy and acute kidney injury in Australian snakebite coagulopathy [ASP28]

INTRODUCTION

The major systemic manifestation of hemotoxicity in human snakebite envenoming is venom-induced consumption coagulopathy (VICC). A subset of patients with VICC develop thrombotic microangiopathy (TMA), in which acute kidney injury (AKI) occurs. We aimed to investigate the association between schistocytosis in snakebite patients with VICC and AKI, compared to non-envenomed patients.

METHODS

Serial blood films collected from a prospective cohort of snakebite patients (Australian Snakebite Project) were examined. Cases were classified a priori as non-envenomed snakebites (normal controls), envenomed without VICC, partial VICC without AKI, complete VICC without AKI, and VICC with AKI based on defined clinical and laboratory criteria. The percentage of schistocytes between groups was compared and correlated by Kendall's tau b test.

RESULTS

Seven hundred and eighty blood films from 234 snakebite cases were analyzed. There was a statistically significant correlation (τ = .69, SE .03, P < .001) for schistocytosis between the ordered groups of non-envenomed snakebites, envenomed without VICC, partial VICC without AKI, complete VICC without AKI, and VICC with AKI groups. Patients with VICC and AKI had a platelet nadir median of 42 × 10⁹ /L (interquartile range [IQR] :25-130 × 10⁹ /L), hemoglobin nadir of median 107 g/L (IQR 66-122 g/L), and maximum LDH median of 1128 U/L (IQR 474-3255 U/L). A 1.0% threshold for schistocytosis yielded 90% sensitivity (95% CI: 67%-98%) and 71% specificity (95% CI: 62%-79%) for predicting AKI in patients with VICC.

CONCLUSION

Schistocyte quantitation has good diagnostic utility in snakebite patients with VICC. A definition of snakebite TMA as MAHA with ≥1.0% schistocytes and thrombocytopenia, would appear to be appropriate.

The ADVIA2120i parameter Revised %MICRO is a surrogate marker of schistocyte formation after hematopoietic stem cell transplantation

Objectives : Hematopoietic stem cell transplantation (HSCT)-associated thrombotic microangiopathy (TA-TMA) is an important early post-treatment condition. This study evaluated the Revised %MICRO, a parameter obtained from the ADVIA 2120i automated blood cell counter, as a surrogate marker of the schistocyte ratio. We hypothesized that individual differences between the %MICRO value and schistocyte ratio would remain constant. Design and Methods: EDTA-2K-treated peripheral blood samples were collected from 19 patients who underwent allogeneic HSCT from April 2014 to September 2018. First, the baseline difference, X, was calculated using a sample from the first day after HSCT as X = %MICRO (first day) - schistocyte ratio (first day). Next, the Revised %MICRO for each subsequent day was calculated as Revised %MICRO = %MICRO - X. We evaluated correlations of the schistocyte ratio with the calculated %MICRO and Revised %MICRO and the RBC fragment, RBC distribution width, %MICRO and Revised %MICRO data obtained from the ADVIA 2120i. Results : The mean schistocyte percentage and Revised %MICRO were both 0.4% ± 0.6. RBC fragments correlated weakly with the %MICRO and schistocyte ratio, respectively (r = 0.162 and r = 0.771, respectively), whereas the Revised %MICRO correlated strongly with the schistocyte ratio (r = 0.893). Conclusion : The Revised %MICRO appears to be a good surrogate of the schistocyte ratio in a clinical setting. J. Med. Invest. 67 : 250-254, August, 2020.

Usefulness of automated fragmented red blood cell percentage in the diagnosis of paediatric haemolytic uraemic syndrome

INTRODUCTION

Presence of schistocytes in peripheral blood smear supporting haemolysis is important for diagnosis and decision-making in paediatric haemolytic uraemic syndrome (HUS). High observer dependency and requirement of expertise for peripheral smear evaluation propels us to think of other modalities to overcome these issues. We envisage that newer techniques like automated fragmented red blood cell percentage (FRC %), whose role has been described in transplant associated HUS and thrombotic thrombocytopenic purpura, can serve the purpose.

METHODS

Twenty-eight children with HUS after excluding secondary causes were enrolled in this study. Blood samples were analysed for FRC% at admission, using SYSMEX XN-1000 (Japan) haematology analyser, and simultaneously, schistocytes in peripheral smear were reported by a single expert haematopathologist.

RESULTS

Median age was 56 months ranging from 2 to 140 months. FRC% was elevated in 85.8% (n-24/28) with a mean of 4.56 ± 3.1%. FRC% had a sensitivity of 95.4% (C.I: 77.16% to 99.88%) in children who had FRC% >1.49% with an accuracy of 85.71% (C.I: 67.33% to 95.97%). However, specificity was only 50% (C.I: 11.81% to 88.19%) with a positive likelihood ratio of 1.91. Receiver-operator curve showed an AUC value of 0.841.

CONCLUSION

We suggest automated FRC% as a rapid and highly sensitive index for screening of paediatric HUS; however, a peripheral blood film examination is a must in cases with count >2% to avoid false positives as the index has low specificity.

Comparison between optical microscopy and the Sysmex XN-3000 for schistocyte determination in patients suspected of having schistocytosis

Background and aims

Diagnosis of thrombotic microangiopathy (TMA) relies on microscopic schistocyte determination by an experienced microscopist. In addition, schistocytes can be found in non‐TMA–related disorders such as thalassaemia. We aimed to compare the accuracy of the automated haematology analyser Sysmex XN‐3000 for schistocyte detection, to that of the microscopy approach, in patients suspected of having schistocytosis.

Methods

Consecutive blood samples were collected between April 2016 and March 2017 at Siriraj Hospital, Mahidol University, Bangkok, Thailand. Specimens were collected from adults with suspected TMA or with thalassaemia trait and/or disease. All blood samples were examined by both microscopy and the analyser. Samples were considered to be positive for schistocytes (ie, schistocytosis) if they had a schistocyte count ≥1% by microscopy. The analyser's ability to determine schistocytosis was assessed by receiver operating characteristic (ROC) curve. Sensitivity, specificity, positive (PPV), and negative predictive value (NPV) of an appropriate cut‐off point were calculated, with manual microscopy as the standard. Quantitative agreement in schistocyte counts between the two approaches was assessed using 95% limits of agreement, Bland‐Altman plots, intraclass correlation coefficient, and concordance correlation coefficient.

Results

Ninety‐seven blood samples (62 suspected TMA and 35 thalassaemia) were collected. ROC curve analysis of the analyser for determining schistocytosis showed an area under the curve of 0.803 (95% confidence interval, 0.689‐0.917, P < 0.001). A cut‐off point of 0.6% yielded 86.1% sensitivity, 77.8% specificity, 94.4% PPV, and 56.0% NPV. The automated schistocyte count did not quantitatively agree with schistocyte counts by microscopy, neither in all blood specimens (mean of difference: −1.09; 95% limits of agreement, −11.9 to 9.7) nor in the subgroups (TMA, −0.88; 95% limits of agreement, −6.60 to 4.84; thalassaemia, −2.4; 95% limits of agreement, −14.10 to 9.30). The differences in the estimation of fragmented red blood cells between the methods tended to increase at higher schistocyte counts.

Conclusion

Sysmex XN‐3000 can be used for qualitative measurement of schistocytosis, but should not be used as a quantitative tool for schistocyte counting. Improvements are needed before this analyser's schistocyte detection feature can be recommended for use in clinical practice.

Neonates with suspected microangiopathic disorders: performance of standard manual schistocyte enumeration vs. the automated fragmented red cell count

OBJECTIVES

To enhance the diagnosis of schistocyte-producing conditions, we compared routine manual schistocyte enumeration with automated fragmented red cell counts (FRCs).

STUDY DESIGN

In neonates "suspected" of having sepsis, NEC, or DIC we compared manual schistocyte estimates vs. automated FRC counts. When the two disagreed, we used a "gold standard" from a  ≥ 1000 RBC differential. We also assessed the diagnostic accuracy of the FRC count in diagnosing sepsis, NEC, or DIC.

RESULTS

We collected 270 CBCs from 90 neonates. The methods agreed in 63% (95% CI 55%-70%) of the CBCs. Among the 37% where they disagreed, the FRC count was more accurate in 100% (95% CI 88-100%). An elevated FRC count was specific for sepsis, and was sensitive and specific for necrotizing enterocolitis and DIC.

CONCLUSIONS

Automated FRC counts have advantages over routine manual evaluation, larger sample size, lower expense, and superior accuracy in diagnosing schistocyte-producing conditions.

The Clinical Significance of Schistocytes: A Prospective Evaluation of the International Council for Standardization in Hematology Schistocyte Guidelines

Objective:

The presence of ≥1% schistocytes on a peripheral blood smear (PBS) is an important criterion for the diagnosis of thrombotic microangiopathy (TMA). The reporting of schistocytes has been standardized by the International Council for Standardization in Hematology (ICSH). Despite the availability of guidelines, however, the assessment of schistocytes remains subjective. More recently, the automated fragmented red cell (FRC) parameter has been evaluated. However, local studies are not available.

Materials and Methods:

A prospective study was performed at the Charlotte Maxeke Johannesburg Academic Hospital in order to evaluate the ICSH recommendations for schistocyte measurement in 146 PBSs with schistocytes. Schistocytes were evaluated by microscopy and ADVIA 2120 automated hematology analyzers.

Results:

Schistocytes were frequently observed in patients with TMA (n=76), infection (n=20), hematologic malignancy (n=10), renal failure (n=5), and hemoglobinopathy (n=15), and in neonates (n=11). Schistocytes were ≥1% in all PBSs with TMA (n=76) with a mean of 3.44±1.84. Schistocytes of ≥1% were also observed in cases of renal failure and hemoglobinopathy, and in neonates. In these conditions, schistocytes were mainly observed in conjunction with moderate red blood cell changes. The agreement between two morphologists gave a correlation coefficient of 0.63 [confidence interval (CI): 0.52-0.75], while the correlation coefficient between the average of the morphologists and the FRC percentage was -1.97 (CI: -1.60 to -2.34). The ADVIA 2120 underestimated the schistocyte count in patients with TMA.

Conclusion:

Observer bias can be decreased by implementing the standardized procedures recommended by the ICSH. However, estimation of schistocytes by the ADVIA 2120 analyzer requires further evaluation as a screening tool. A higher threshold for schistocytes in thrombotic thrombocytopenic purpura is recommended to distinguish this hematological emergency from other conditions associated with ≥1% schistocytes.

Verification and standardization of blood cell counters for routine clinical laboratory tests

The use of automated blood cell counters (automated hematology analyzers) for diagnostic purposes is inextricably linked to clinical laboratories. However, the need for uniformity among the various methods and parameters is increasing and standardization of the automated analyzers is therefore crucial. Standardization not only involves procedures based on reference methods but it also involves validation, verification, quality assurance, and quality control, and it includes the involvement of several participants. This article discusses the expert guidelines and provides an overview of issues involved in complete blood count parameter reference methods and standardization of reporting units.

Red cell indices in classification and treatment of anemias: from M.M. Wintrobes's original 1934 classification to the third millennium

PURPOSE OF REVIEW

Measurements of red cell volume, hemoglobin (Hb) concentration and Hb content continue to play a crucial role in the differential diagnosis of anemias 80 years after the publication of Wintrobe's seminal work. Modern hematology analyzers provide additional data on the heterogeneity of these parameters (distribution width) and quantify similar parameters of reticulocytes as well. Red cell and reticulocyte cellular indices are widely used in the diagnosis and monitoring of hematological diseases.

RECENT FINDINGS

Quantification of hypochromic cells is valuable in the differential diagnosis of thalassemia trait and iron deficiency, and in monitoring therapeutic response to erythropoietic stimulating agents, while hyperchromic cells are an essential diagnostic component for hereditary spherocytosis and may correlate with hemolytic parameters in sickle cell disease. Values for these parameters however depend on the technology used. Red cell clearance is associated with a reduction in both Hb content and cell volume: normal cells are likely to be removed by the time they reach a volume of 72 fl. Reticulocyte parameters such as Hb content (CHr or ret-He) or maturity index (RMI) have shown value in a variety of hematological conditions. New findings from genetic association studies have identified several potential novel genes affecting red cell indices, which are not mediated by changes in iron availability.

SUMMARY

Red cell indices continue to provide an essential support to the diagnosis and monitoring of hematological diseases.

Evaluation of ICSH schistocyte measurement guidelines in France

INTRODUCTION

The schistocytes are fragmented red blood cells mainly observed in the setting of hemolytic anemias where they remain an important criterion for the diagnosis. As the identification of these cells is still problematic, the International Council for Standardization in Hematology (ICSH) set up a consensus report in November, 2011. The French Group of Cellular Hematology (GFHC) aimed to collect the opinion of French biologists directly confronted to schistocytes measurements, about these guidelines.

METHODS

Among the 578 professionals, 169 (29%) answered to the 10 questions dealing with the identification and measurements of schistocytes as proposed by the ICSH.

RESULTS

A consensus was reached for the urgent need of such guidelines documents, especially in the current background of the European accreditation EN ISO 15189 rules. A traduction in native (French) language was warmly wished in order to facilitate the diffusion of the information. The pathologic threshold for the diagnosis of thrombotic microangiopathic anemia (TMA) (>1%) remained questionable. For half of the biologists, the new fragmented red blood cell (FRC) parameter recently provided by two manufacturers of automated blood cell counters was still doubtful for routine use.

CONCLUSION

This survey assessed the impact of international 'guidelines' on the French biological community. The will to implement validated recommendations was strong, reflecting the awareness of the biologists to standardize the laboratory investigations.

Microscopic schistocyte determination according to International Council for Standardization in Hematology recommendations in various diseases

INTRODUCTION

Recently, a consensus report for microscopic schistocyte determination was prepared by International Council for Standardization in Hematology (ICSH). ICSH focused on diagnosis of thrombocytopenic purpura (TTP)/hemolytic uremic syndrome (HUS). We aimed to reanalyze schistocytes according to ICSH recommendations, to study diseases other than TTP/HUS related to the schistocytes, and to compare the percentage of schistocytes among the various diseases.

METHODS

We retrieved all reported cases of peripheral blood (PB) smear in a single institution during 6 years. Schistocytes on 282 PB smears showing previous peripheral schistocytes and hemoglobin ≤10 g/dL were recounted according to ICSH recommendations.

RESULTS

The schistocytes were frequently observed in patients with microangiopathic hemolytic anemia (MAHA), metastatic carcinoma, sepsis, chronic renal failure, preterm infant, and infection. Only two among 34 patients categorized as MAHA were diagnosed as TTP/HUS. Schistocytes were observed with other morphological changes in 169 of 170 cases with schistocyte ≤1% and in 102 of 112 with schistocyte >1%. The median schistocyte percentages of patients with hematologic malignancy, megaloblastic anemia, acute renal failure, and preterm infant were 1.20%, 1.30%, 1.35%, and 1.70%, respectively.

CONCLUSION

Schistocytes were observed above 1% in many diseases other than TTP /HUS. Therefore, it is important to understand that schistocytes could be seen in various diseases, and in these cases, schistocytes were usually detected together with other red blood cell morphologic changes. These data support ICSH recommendation that a schistocyte count should be considered clinically meaningful if schistocytes represent the main morphological abnormality in the PB smear.