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.

Automatic normalized digital color staining in the recognition of abnormal blood cells using generative adversarial networks.

BACKGROUND AND OBJECTIVES: Combining knowledge of clinical pathologists and deep learning models is a growing trend in morphological analysis of cells circulating in blood to add objectivity, accuracy, and speed in diagnosing hematological and non-hematological diseases. However, the variability in staining protocols across different laboratories can affect the color of images and performance of automatic recognition models. The objective of this work is to develop, train and evaluate a new system for the normalization of color staining of peripheral blood cell images, so that it transforms images from different centers to map the color staining of a reference center (RC) while preserving the structural morphological features. METHODS: The system has two modules, GAN1 and GAN2. GAN1 uses the PIX2PIX technique to fade original color images to an adaptive gray, while GAN2 transforms them into RGB normalized images. Both GANs have a similar structure, where the generator is a U-NET convolutional neural network with ResNet and the discriminator is a classifier with ResNet34 structure. Digitally stained images were evaluated using GAN metrics and histograms to assess the ability to modify color without altering cell morphology. The system was also evaluated as a pre-processing tool before cells undergo a classification process. For this purpose, a CNN classifier was designed for three classes: abnormal lymphocytes, blasts and reactive lymphocytes. RESULTS: Training of all GANs and the classifier was performed using RC images, while evaluations were conducted using images from four other centers. Classification tests were performed before and after applying the stain normalization system. The overall accuracy reached a similar value around 96% in both cases for the RC images, indicating the neutrality of the normalization model for the reference images. On the contrary, it was a significant improvement in the classification performance when applying the stain normalization to the other centers. Reactive lymphocytes were the most sensitive to stain normalization, with true positive rates (TPR) increasing from 46.3% - 66% for the original images to 81.2% - 97.2% after digital staining. Abnormal lymphocytes TPR ranged from 31.9% - 95.7% with original images to 83% - 100% with digitally stained images. Blast class showed TPR ranges of 90.3% - 94.4% and 94.4% - 100%, for original and stained images, respectively. CONCLUSIONS: The proposed GAN-based normalization staining approach improves the performance of classifiers with multicenter data sets by generating digitally stained images with a quality similar to the original images and adaptability to a reference staining standard. The system requires low computation cost and can help improve the performance of automatic recognition models in clinical settings.

Kimura disease as an uncommon cause of persistent hypereosinophilia: a diagnostic challenge.

Kimura disease (KD) is an unusual inflammatory disease of unknown etiology. Despite being described many years ago, KD might cause diagnostic difficulty or be confused with other conditions. Here, we present a 33-year-old Filipino woman who was referred to our hospital for evaluation of persistent eosinophilia and intense pruritus. Blood analysis and peripheral blood smear review showed high eosinophil counts (3.8 x109/L, 40%) that did not show morphological abnormalities. Besides, high serum IgE concentration was detected (33,528 kU/L). Serological tests were positive for Toxocara canis and treatment with albendazol was initiated. Nevertheless, increased eosinophil counts were still present after several months, alongside with high serum IgE concentrations and intense pruritus. During her follow-up, an inguinal adenopathy was detected. The biopsy revealed lymphoid hyperplasia with reactive germinal centers and massive eosinophil infiltration. Proteinaceous deposits of eosinophilic material were also observed. All these findings, together with peripheral blood eosinophilia and high IgE concentrations, confirmed the diagnosis of KD. The diagnosis of KD should be considered in the differential diagnosis of long-standing unexplained eosinophilia in association with high IgE concentrations, pruritus and lymphadenopathies.

Automatic generation of artificial images of leukocytes and leukemic cells using generative adversarial networks (syntheticcellgan).

BACKGROUND AND OBJECTIVES: Visual analysis of cell morphology has an important role in the diagnosis of hematological diseases. Morphological cell recognition is a challenge that requires experience and in-depth review by clinical pathologists. Within the new trend of introducing computer-aided diagnostic tools in laboratory medicine, models based on deep learning are being developed for the automatic identification of different types of cells in peripheral blood. In general, well-annotated large image sets are needed to train the models to reach a desired classification performance. This is especially relevant when it comes to discerning between cell images in which morphological differences are subtle and when it comes to low prevalent diseases with the consequent difficulty in collecting cell images. The objective of this work is to develop, train and validate SyntheticCellGAN (SCG), a new system for the automatic generation of artificial images of white blood cells, maintaining morphological characteristics very close to real cells found in practice in clinical laboratories. METHODS: SCG is designed with two sequential generative adversarial networks. First, a Wasserstein structure is used to transform random noise vectors into low resolution images of basic mononuclear cells. Second, the concept of image-to-image translation is used to build specific models that transform the basic images into high-resolution final images with the realistic morphology of each cell type target: 1) the five groups of normal leukocytes (lymphocytes, monocytes, eosinophils, neutrophils and basophils); 2) atypical promyelocytes and hairy cells, which are two relevant cell types of complex morphology with low abundance in blood smears. RESULTS: The images of the SCG system are evaluated with four experimental tests. In the first test we evaluated the generated images with quantitative metrics for GANs. In the second test, morphological verification of the artificial images is performed by expert clinical pathologists with 100% accuracy. In the third test, two classifiers based on convolutional neural networks (CNN) previously trained with images of real cells are used. Two sets of artificial images of the SCG system are classified with an accuracy of 95.36% and 94%, respectively. In the fourth test, three CNN classifiers are trained with artificial images of the SCG system. Real cells are identified with an accuracy ranging from 87.7% to 100%. CONCLUSIONS: The SCG system has proven effective in creating images of all normal leukocytes and two low-prevalence cell classes associated with diseases such as acute promyelocyte leukemia and hairy cell leukemia. Once trained, the system requires low computational cost and can help augment high-quality image datasets to improve automatic recognition model training for clinical laboratory practice.

Serous body fluid evaluation using the new automated haematology analyser Mindray BC-6800Plus.

OBJECTIVES: Cellular analysis of body fluids (BF) has clinical relevance in several medical conditions. The objective of this study is twofold: (1) evaluate the analytical performance of the BF mode of Mindray BC-6800 Plus compared to manual counts under microscopy and (2) analyse if the high-fluorescent cell counts provided by the analyser (HF-BF) are useful to detect malignancy. METHODS: A total of 285 BF was analysed: 250 corresponding to patients without neoplasia and 35 to patients with malignant diseases. Manual differential counts were performed in BF with ≥250 cells/µL. Percentages and absolute counts were obtained on the BC-6800Plus for total nucleated cells (TC-BF), mononuclear, polymorphonuclear and HF-BF. Statistical analysis was performed using Mann-Whitney U-test, Spearman's correlation, Passing-Bablok regression, Bland-Altman graph and ROC curve. RESULTS: To compare manual and automatic total cell counts, samples were divided in three groups: <250, 250-1,000 and >1,000 cells/µL. Correlation was good in all cases (r=0.72, 0.73 and 0.92, respectively) without significant differences between both methods (p=0.65, 0.39 and 0.30, respectively). The concordance between methods showed values of 90%. Considering malignant samples, median HF-BF values showed significant higher values (102 cells/µL) with respect to non-malignant (4 cells/µL) (p<0.001). The cut-off value of 8.5 HF-BF/µL was able to discriminate samples containing malignant cells showing sensitivity and specificity values of 89 and 71%, respectively. Considering both, HF-BF and TC-BF values, sensitivity and specificity values were 100 and 53%, respectively. CONCLUSIONS: This study reveals that the Mindray BC-6800Plus offers an accurate and acceptable performance, showing results consistent with the manual method. It is recommended to consider both HF-BF and TC-BF values for the screening of the microscopic evaluation to ensure the detection of all malignant samples.

A Deep Learning Approach for the Morphological Recognition of Reactive Lymphocytes in Patients with COVID-19 Infection.

Laboratory medicine plays a fundamental role in the detection, diagnosis and management of COVID-19 infection. Recent observations of the morphology of cells circulating in blood found the presence of particular reactive lymphocytes (COVID-19 RL) in some of the infected patients and demonstrated that it was an indicator of a better prognosis of the disease. Visual morphological analysis is time consuming, requires smear review by expert clinical pathologists, and is prone to subjectivity. This paper presents a convolutional neural network system designed for automatic recognition of COVID-19 RL. It is based on the Xception71 structure and is trained using images of blood cells from real infected patients. An experimental study is carried out with a group of 92 individuals. The input for the system is a set of images selected by the clinical pathologist from the blood smear of a patient. The output is the prediction whether the patient belongs to the group associated with better prognosis of the disease. A threshold is obtained for the classification system to predict that the smear belongs to this group. With this threshold, the experimental test shows excellent performance metrics: 98.3% sensitivity and precision, 97.1% specificity, and 97.8% accuracy. The system does not require costly calculations and can potentially be integrated into clinical practice to assist clinical pathologists in a more objective smear review for early prognosis.

Quantitative features to assist in the diagnostic assessment of chronic lymphocytic leukemia progression†.

The use of artificial intelligence methods in the image-based diagnostic assessment of hematological diseases is a growing trend in recent years. In these methods, the selection of quantitative features that describe cytological characteristics plays a key role. They are expected to add objectivity and consistency among observers to the geometric, color, or texture variables that pathologists usually interpret from visual inspection. In a recent paper in The Journal of Pathology, El Hussein, Chen et al proposed an algorithmic procedure to assist pathologists in the diagnostic evaluation of chronic lymphocytic leukemia (CLL) progression using whole-slide image analysis of tissue samples. The core of the procedure was a set of quantitative descriptors (biomarkers) calculated from the segmentation of cell nuclei, which was performed using a convolutional neural network. These biomarkers were based on clinical practice and easily calculated with reproducible tools. They were used as input to a machine learning algorithm that provided classification in one of the stages of CLL progression. Works like this can contribute to the integration into the workflow of clinical laboratories of automated diagnostic systems based on the morphological analysis of histological slides and blood smears. © 2021 The Pathological Society of Great Britain and Ireland.

Atypical lymphoid cells circulating in blood in COVID-19 infection: morphology, immunophenotype and prognosis value.

AIMS: Atypical lymphocytes circulating in blood have been reported in COVID-19 patients. This study aims to (1) analyse if patients with reactive lymphocytes (COVID-19 RL) show clinical or biological characteristics related to outcome; (2) develop an automatic system to recognise them in an objective way and (3) study their immunophenotype. METHODS: Clinical and laboratory findings in 36 COVID-19 patients were compared between those showing COVID-19 RL in blood (18) and those without (18). Blood samples were analysed in Advia2120i and stained with May Grünwald-Giemsa. Digital images were acquired in CellaVisionDM96. Convolutional neural networks (CNNs) were used to accurately recognise COVID-19 RL. Immunophenotypic study was performed throughflow cytometry. RESULTS: Neutrophils, D-dimer, procalcitonin, glomerular filtration rate and total protein values were higher in patients without COVID-19 RL (p<0.05) and four of these patients died. Haemoglobin and lymphocyte counts were higher (p<0.02) and no patients died in the group showing COVID-19 RL. COVID-19 RL showed a distinct deep blue cytoplasm with nucleus mostly in eccentric position. Through two sequential CNNs, they were automatically distinguished from normal lymphocytes and classical RL with sensitivity, specificity and overall accuracy values of 90.5%, 99.4% and 98.7%, respectively. Immunophenotypic analysis revealed COVID-19 RL are mostly activated effector memory CD4 and CD8 T cells. CONCLUSION: We found that COVID-19 RL are related to a better evolution and prognosis. They can be detected by morphology in the smear review, being the computerised approach proposed useful to enhance a more objective recognition. Their presence suggests an abundant production of virus-specific T cells, thus explaining the better outcome of patients showing these cells circulating in blood.

Automatic identification of malaria and other red blood cell inclusions using convolutional neural networks.

Malaria is a serious disease responsible for thousands of deaths each year. Many efforts have been made to aid in the diagnosis of malaria using machine learning techniques, but to date, the presence of other elements that may interfere with the recognition of malaria has not been considered. We have developed the first deep learning model using convolutional neural networks capable of differentiating malaria-infected red blood cells from not only normal erythrocytes but also erythrocytes with other types of inclusions. 6415 images of red blood cells were segmented from digital images of 53 peripheral blood smears using thresholding and watershed transformation techniques. These images were used to train a VGG-16 architecture using transfer learning. Using an independent test set of 23 smears, this model was 99.5% accurate in classifying malaria parasites and other red blood cell inclusions. This model also exhibited sensitivity and specificity values of 100% and 91.7%, respectively, classifying a complete smear as infected or not infected. Our model represents a promising advance for automation in the identification of malaria-infected patients. The differentiation between malaria parasites and other red blood cell inclusions demonstrates the potential utility of our model in a real work environment.

A new convolutional neural network predictive model for the automatic recognition of hypogranulated neutrophils in myelodysplastic syndromes.

BACKGROUND: Dysplastic neutrophils commonly show at least 2/3 reduction of the content of cytoplasmic granules by morphologic examination. Recognition of less granulated dysplastic neutrophils by human eyes is difficult and prone to inter-observer variability. To tackle this problem, we proposed a new deep learning model (DysplasiaNet) able to automatically recognize the presence of hypogranulated dysplastic neutrophils in peripheral blood. METHODS: Eight models were generated by varying convolutional blocks, number of layer nodes and fully connected layers. Each model was trained for 20 epochs. The five most accurate models were selected for a second stage, being trained again from scratch for 100 epochs. After training, cut-off values were calculated for a granularity score that discerns between normal and dysplastic neutrophils. Furthermore, a threshold value was obtained to quantify the minimum proportion of dysplastic neutrophils in the smear to consider that the patient might have a myelodysplastic syndrome (MDS). The final selected model was the one with the highest accuracy (95.5%). RESULTS: We performed a final proof of concept with new patients not involved in previous steps. We reported 95.5% sensitivity, 94.3% specificity, 94% precision, and a global accuracy of 94.85%. CONCLUSIONS: The primary contribution of this work is a predictive model for the automatic recognition in an objective way of hypogranulated neutrophils in peripheral blood smears. We envision the utility of the model implemented as an evaluation tool for MDS diagnosis integrated in the clinical laboratory workflow.

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.

Moving Toward and Through Trauma: Participant Experiences of Multi-Modal Motion-Assisted Memory Desensitization and Reconsolidation (3MDR).

Introduction: Military members and Veterans are at risk of developing combat-related, treatment-resistant posttraumatic stress disorder (TR-PTSD) and moral injury (MI). Conventional trauma-focused therapies (TFTs) have shown limited success. Novel interventions including Multi-modal Motion-assisted Memory Desensitization and Reconsolidation therapy (3MDR) may prove successful in treating TR-PTSD. Objective: To qualitatively study the experiences of Canadian military members and Veterans with TR-PTSD who received the 3MDR intervention. Methods: This study explored qualitative data from a larger mixed-method waitlist control trial testing the efficacy of 3MDR in military members and veterans. Qualitative data were recorded and collected from 3MDR sessions, session debriefings and follow-up interviews up to 6 months post-intervention; the data were then thematically analyzed. Results: Three themes emerged from the data: (1) the participants' experiences with 3MDR; (2) perceived outcomes of 3MDR; and (3) keys to successful 3MDR treatment. Participants expressed that 3MDR provided an immersive environment, active engagement and empowerment. The role of the therapist as a coach and "fireteam partner" supports the participants' control over their therapy. The multi-modal nature of 3MDR, combining treadmill-walking toward self-selected trauma imagery with components of multiple conventional TFTs, was key to helping participants engage with and attribute new meaning to the memory of the traumatic experience. Discussion: Preliminary thematic analysis of participant experiences of 3MDR indicate that 3MDR has potential as an effective intervention for combat-related TR-PTSD, with significant functional, well-being and relational improvements reported post-intervention. Conclusion: Military members and Veterans are at risk of developing TR-PTSD, with worse outcomes than in civilians. Further research is needed into 3MDR and its use with other trauma-affected populations.

Automated cell count in body fluids: a review.

Body fluid cell counting provides valuable information for the diagnosis and treatment of a variety of conditions. Chamber cell count and cellularity analysis by optical microscopy are considered the gold-standard method for cell counting. However, this method has a long turnaround time and limited reproducibility, and requires highly-trained personnel. In the recent decades, specific modes have been developed for the analysis of body fluids. These modes, which perform automated cell counting, are incorporated into hemocytometers and urine analyzers. These innovations have been rapidly incorporated into routine laboratory practice. At present, a variety of analyzers are available that enable automated cell counting for body fluids. Nevertheless, these analyzers have some limitations and can only be operated by highly-qualified laboratory professionals. In this review, we provide an overview of the most relevant automated cell counters currently available for body fluids, the interpretation of the parameters measured by these analyzers, their main analytical features, and the role of optical microscopy as automated cell counters gain ground.

Peripheral blood morphology review and diagnostic proficiency evaluation by a new Spanish EQAS during the period 2011-2019.

INTRODUCTION: The Spanish Haematology and Haemotherapy Society organizes peripheral blood smear review scheme, focused on the evaluation of diagnostic proficiency of participants by blood cell morphology analysis. The objective was to evaluate the efficacy of this scheme as an educational tool to improve the diagnostic proficiency of the participants. METHODS: During 2011-2019, 54 peripheral blood smears, alongside with patient details such as age, sex, blood cell counts and relevant clinical information, were sent to an average of 125 ± 13 laboratories per year. A number of 44 shipments were selected to analyse whether successive surveys of the same disease may lead to an improvement in the diagnostic success rate proposed by the laboratories. Participants were asked to select the most relevant morphological abnormalities, alongside the diagnostic orientation. Agreement of participant responses with RR was evaluated. RESULTS: Spanish laboratories showed a diagnostic proficiency greater than 80% in acute myeloid leukaemia, including acute promyelocytic leukaemia, mature B-cell neoplasms (hairy cell leukaemia and splenic marginal zone lymphoma), chronic myeloid leukaemia, sickle cell disease, Bernard-Soulier syndrome and infectious mononucleosis. It was important to note the significant improvement over the time in the successive shipments of the same disease, with a 31% and 13% increase in their diagnostic orientation success rate for acute myeloid leukaemia and acute promyelocytic leukaemia cases, respectively, 15% for mantle cell lymphoma and 6% for sickle cell disease. CONCLUSIONS: The present study provides evidence that peripheral blood smear review scheme can be a valid educational tool to improve the clinical pathologist skills in blood morphology and haematological diagnosis.

A Deep Learning Approach for Segmentation of Red Blood Cell Images and Malaria Detection.

Malaria is an endemic life-threating disease caused by the unicellular protozoan parasites of the genus Plasmodium. Confirming the presence of parasites early in all malaria cases ensures species-specific antimalarial treatment, reducing the mortality rate, and points to other illnesses in negative cases. However, the gold standard remains the light microscopy of May-Grünwald-Giemsa (MGG)-stained thin and thick peripheral blood (PB) films. This is a time-consuming procedure, dependent on a pathologist's skills, meaning that healthcare providers may encounter difficulty in diagnosing malaria in places where it is not endemic. This work presents a novel three-stage pipeline to (1) segment erythrocytes, (2) crop and mask them, and (3) classify them into malaria infected or not. The first and third steps involved the design, training, validation and testing of a Segmentation Neural Network and a Convolutional Neural Network from scratch using a Graphic Processing Unit. Segmentation achieved a global accuracy of 93.72% over the test set and the specificity for malaria detection in red blood cells (RBCs) was 87.04%. This work shows the potential that deep learning has in the digital pathology field and opens the way for future improvements, as well as for broadening the use of the created networks.

A dataset of microscopic peripheral blood cell images for development of automatic recognition systems.

This article makes available a dataset that was used for the development of an automatic recognition system of peripheral blood cell images using convolutional neural networks [1]. The dataset contains a total of 17,092 images of individual normal cells, which were acquired using the analyzer CellaVision DM96 in the Core Laboratory at the Hospital Clinic of Barcelona. The dataset is organized in the following eight groups: neutrophils, eosinophils, basophils, lymphocytes, monocytes, immature granulocytes (promyelocytes, myelocytes, and metamyelocytes), erythroblasts and platelets or thrombocytes. The size of the images is 360 × 363 pixels, in format jpg, and they were annotated by expert clinical pathologists. The images were captured from individuals without infection, hematologic or oncologic disease and free of any pharmacologic treatment at the moment of blood collection. This high-quality labelled dataset may be used to train and test machine learning and deep learning models to recognize different types of normal peripheral blood cells. To our knowledge, this is the first publicly available set with large numbers of normal peripheral blood cells, so that it is expected to be a canonical dataset for model benchmarking.