Does morphology matter in 2017? An approach to morphologic clues in non-neoplastic blood and bone marrow disorders

Performance of the new MC-80 automated digital cell morphology analyser in detection of normal and abnormal blood cells: Comparison with the CellaVision DM9600

INTRODUCTION

Mindray MC-80 is an automated system for digital imaging of white blood cells (WBCs) and their pre-classification. The objective of this work is to analyse its performance comparing it with the CellaVision® DM9600.

METHODS

A total of 445 samples were used, 194 normal and 251 abnormal: acute leukaemia (100), myelodysplastic syndromes/myeloproliferative neoplasms (33), lymphoid neoplasms (50), plasma cell neoplasms (14), infections (49) and thrombocytopenia (5). WBC pre-classification values with the MC-80 and DM9600 were compared with (1) the microscope, (2) Mindray BC-6800Plus differentials in only normal samples, and (3) confirmed or reclassified images (post-classification). Pearson's correlation, Lin's concordance, Passing-Bablok regression, and Bland-Altman plots were used. Sensitivity, specificity, positive (PPV) and negative (NPV) predictive values for abnormal cells using the MC-80 were calculated.

RESULTS

The PPV and NPV were above 98% and 99%, for normal samples. For immature granulocytes (IG), NPV and PPV were 100% and 74.2%. When comparing the WBC differentials using the MC-80, the microscope and the BC-6800Plus, no differences were found except for basophils and IG. Our results showed good agreement between the pre- and post-classification of normal WBC, including IG, quantified by high correlation and concordance values (0.91-1). Sensitivity and specificity for blasts were 0.984 and 0.640. The MC-80 detected abnormal lymphocytes in 30% of the smears from patients with lymphoid neoplasm. Plasma cell identification was better using the DM9600. The sensitivity and specificity for erythroblast detection were 1 and 0.890.

CONCLUSION

We found that the MC-80 shows high performance for WBC differentials for both normal samples and patients with haematological diseases.

Improving anaemia diagnosis using peripheral blood smear with remote interpretation in adults living with HIV with moderate to severe anaemia: A prospective study nested within the Kilombero and Ulanga antiretroviral cohort

INTRODUCTION

In low-resource settings, anaemia is a very common condition. Identification of anaemia aetiologies remains challenging due to the lack of diagnostic tools and expertise. We aimed to improve anaemia diagnostics using peripheral blood smear (PBS) with remote interpretation in people living with HIV (PLHIV) with moderate to severe anaemia.

METHODS

We conducted a prospective study nested within the Kilombero and Ulanga Antiretroviral Cohort, including non-pregnant PLHIV aged ≥18 years presenting with moderate (haemoglobin 7.0-9.9 g/dl) or severe (<7.0 g/dl) anaemia at any visit from January 2019 to December 2020. For each participant, ten PBS images, full blood count and clinical details were shared with a haematologist for remote interpretation (enhanced care). Identification of anaemia etiologies and potential impact on treatment was compared between enhanced and standard care.

RESULTS

Among 400 PLHIV with moderate to severe anaemia, 349 (87%) were female, median age was 40 years (interquartile range (IQR) 35-46)), 65 (17%) had a body mass index <18.5 kg/m2, 215 (54%) had HIV WHO stage III/IV, 79 (20%) had a CD4 cell count <200 cells/μl and 317 (89%) had HIV viral load <100 copies/ml. Severe anaemia was diagnosed in 84 (21%). Suspected multiple aetiologies were documented more frequently by enhanced care compared to standard care 267 (67%) vs 20 (5%); p<0.001. Suspected iron deficiency was the most frequent aetiology (n = 337; 84%), followed by chronic disease (n = 199; 50%), folate/vitamin B12 deficiency (n = 78; 20%) and haemoglobinopathy (n = 83; 21%). In 272 participants (68%), enhanced care revealed additional clinically relevant findings with impact on the treatment recommendation.

CONCLUSION

Remote interpretation of PBS combined with clinical information and blood cell count results can provide insights to the suspected aetiological diagnosis of moderate and severe anaemia in rural low-resource settings and impact specific treatment.

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.

An evaluation of existing manual blood film schistocyte quantitation guidelines and a new proposed method

Schistocytosis is the morphological hallmark of the microangiopathic haemolytic anaemia of thrombotic microangiopathy (TMA). Consensus guidelines for manual schistocyte quantitation are available, but limited research has evaluated them. The 2012 International Council for Standardization in Haematology (ICSH) recommends a schistocyte quantitation of 1% as a robust cut-off for significance, with the quantitation including helmet, crescent, triangle and keratocyte poikilocytes; and microspherocytes only in the presence of helmets, crescents/triangles, and keratocytes. We aimed to evaluate the relative contribution of these different poikilocytes to schistocyte counting; compare the ICSH method with our proposed method which counts only cells most specific for red cell fragmentation (helmet, crescent and triangular schistocytes); and evaluate inter- and intra-observer agreement. Blood films were sourced from the Australian Snakebite Project, including non-envenomed and envenomed cases, with and without TMA. In blood films across the range of schistocytosis, the predominant poikilocytes present were helmets and crescents. Triangles, keratocytes and microspherocytes were typically only present when ICSH schistocyte count was >1%. With results dichotomised as <1.0% or ≥1.0%, our proposed new method versus the ICSH method showed almost perfect agreement [observed agreement 95%, Cohen's kappa (κ)=0.84, SE 0.04, 95% CI 0.76-0.92, p<0.005]. Inter-observer strength of agreement for our method was moderate (Fleiss' κ for comparisons between three non-unique microscopists κ=0.50, SE 0.05, 95% CI 0.41-0.59, p<0.005). Intra-observer reproducibility assessed in two microscopists ranged from substantial (Cohen's κ=0.71, SE 0.08, 95% CI 0.55-0.86, p<0.005) to borderline almost perfect agreement (Cohen's κ=0.81, SE 0.07, 95% CI 0.68-0.93, p<0.005). Schistocyte quantitation using our new method is simpler than the 2012 ICSH method and had almost perfect agreement. Our finding of moderate inter-observer agreement in quantitating helmet, triangle and crescent schistocytes is applicable to both the ICSH and our newly proposed method. This finding underscores the importance of clinicopathological correlation and repeated examinations in the context of a clinically suspected TMA.

A deep learning model (ALNet) for the diagnosis of acute leukaemia lineage using peripheral blood cell images

BACKGROUND AND OBJECTIVES

Morphological differentiation among blasts circulating in blood in acute leukaemia is challenging. Artificial intelligence decision support systems hold substantial promise as part of clinical practise in detecting haematological malignancy. This study aims to develop a deep learning-based system to predict the diagnosis of acute leukaemia using blood cell images.

METHODS

A set of 731 blood smears containing 16,450 single-cell images was analysed from 100 healthy controls, 191 patients with viral infections and 148 with acute leukaemia. Training and testing sets were arranged with 85% and 15% of these smears, respectively. To find the best architecture for acute leukaemia classification VGG16, ResNet101, DenseNet121 and SENet154 were evaluated. Fine-tuning was implemented to these pre-trained CNNs to adapt their layers to our data. Once the best architecture was chosen, a system with two modules working sequentially was configured (ALNet). The first module recognised abnormal promyelocytes among other mononuclear blood cell images, such as lymphocytes, monocytes, reactive lymphocytes and blasts. The second distinguished if blasts were myeloid or lymphoid lineage. The final strategy was to predict patients' initial diagnosis of acute leukaemia lineage using the blood smear review. ALNet was assessed with smears of the testing set.

RESULTS

ALNet provided the correct diagnostic prediction of all patients with promyelocytic and myeloid leukaemia. Sensitivity, specificity and precision values of 100%, 92.3% and 93.7%, respectively, were obtained for myeloid leukaemia. Regarding lymphoid leukaemia, a sensitivity of 89% and specificity and precision values of 100% were obtained.

CONCLUSIONS

ALNet is a predictive model designed with two serially connected convolutional networks. It is proposed to assist clinical pathologists in the diagnosis of acute leukaemia during the blood smear review. It has been proved to distinguish neoplastic (leukaemia) and non-neoplastic (infections) diseases, as well as recognise the leukaemia lineage.

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.

Automatic recognition of different types of acute leukaemia in peripheral blood by image analysis

AIMS

Morphological differentiation among different blast cell lineages is a difficult task and there is a lack of automated analysers able to recognise these abnormal cells. This study aims to develop a machine learning approach to predict the diagnosis of acute leukaemia using peripheral blood (PB) images.

METHODS

A set of 442 smears was analysed from 206 patients. It was split into a training set with 75% of these smears and a testing set with the remaining 25%. Colour clustering and mathematical morphology were used to segment cell images, which allowed the extraction of 2,867 geometric, colour and texture features. Several classification techniques were studied to obtain the most accurate classification method. Afterwards, the classifier was assessed with the images of the testing set. The final strategy was to predict the patient's diagnosis using the PB smear, and the final assessment was done with the cell images of the smears of the testing set.

RESULTS

The highest classification accuracy was achieved with the selection of 700 features with linear discriminant analysis. The overall classification accuracy for the six groups of cell types was 85.8%, while the overall classification accuracy for individual smears was 94% as compared with the true confirmed diagnosis.

CONCLUSIONS

The proposed method achieves a high diagnostic precision in the recognition of different types of blast cells among other mononuclear cells circulating in blood. It is the first encouraging step towards the idea of being a diagnostic support tool in the future.

Quantitative Cytologic Descriptors to Differentiate CLL, Sézary, Granular, and Villous Lymphocytes Through Image Analysis

OBJECTIVES

We aimed to find descriptors to identify chronic lymphocytic leukemia (CLL), Sézary, granular, and villous lymphocytes among normal and abnormal lymphocytes in peripheral blood.

METHODS

Image analysis was applied to 768 images from 15 different types of lymphoid cells and monocytes to determine four discriminant descriptors. For each descriptor, numerical scales were obtained using 627 images from 79 patients. An assessment of the four descriptors was performed using smears from 209 new patients.

RESULTS

Cyan correlation of the nucleus identified clumped chromatin, and standard deviation of the granulometric curve of the cyan of the nucleus was specific for cerebriform chromatin. Skewness of the histogram of the u component of the cytoplasm identified cytoplasmic granulation. Hairiness showed specificity for cytoplasmic villi. In the assessment, 96% of the smears were correctly classified.

CONCLUSIONS

The quantitative descriptors obtained through image analysis may contribute to the morphologic identification of the abnormal lymphoid cells considered in this article.