-
Nature Communications Jul 2023Many hematological diseases are characterized by altered abundance and morphology of blood cells and their progenitors. Myelodysplastic syndromes (MDS), for example, are...
Many hematological diseases are characterized by altered abundance and morphology of blood cells and their progenitors. Myelodysplastic syndromes (MDS), for example, are a group of blood cancers characterised by cytopenias, dysplasia of hematopoietic cells and blast expansion. Examination of peripheral blood slides (PBS) in MDS often reveals changes such as abnormal granulocyte lobulation or granularity and altered red blood cell (RBC) morphology; however, some of these features are shared with conditions such as haematinic deficiency anemias. Definitive diagnosis of MDS requires expert cytomorphology analysis of bone marrow smears and complementary information such as blood counts, karyotype and molecular genetics testing. Here, we present Haemorasis, a computational method that detects and characterizes white blood cells (WBC) and RBC in PBS. Applied to over 300 individuals with different conditions (SF3B1-mutant and SF3B1-wildtype MDS, megaloblastic anemia, and iron deficiency anemia), Haemorasis detected over half a million WBC and millions of RBC and characterized their morphology. These large sets of cell morphologies can be used in diagnosis and disease subtyping, while identifying novel associations between computational morphotypes and disease. We find that hypolobulated neutrophils and large RBC are characteristic of SF3B1-mutant MDS. Additionally, while prevalent in both iron deficiency and megaloblastic anemia, hyperlobulated neutrophils are larger in the latter. By integrating cytomorphological features using machine learning, Haemorasis was able to distinguish SF3B1-mutant MDS from other MDS using cytomorphology and blood counts alone, with high predictive performance. We validate our findings externally, showing that they generalize to other centers and scanners. Collectively, our work reveals the potential for the large-scale incorporation of automated cytomorphology into routine diagnostic workflows.
Topics: Humans; Myelodysplastic Syndromes; Anemia; Anemia, Megaloblastic; Blood Cells; Neutrophils
PubMed: 37474506
DOI: 10.1038/s41467-023-39676-y -
Acta Histochemica Aug 2022Measurements of Morphometric Parameters of the Blood Cells (MPBC) are key for the diagnosis of both mental and metabolic diseases. Several manual approaches or...
Measurements of Morphometric Parameters of the Blood Cells (MPBC) are key for the diagnosis of both mental and metabolic diseases. Several manual approaches or computational methodologies are useful to provide reliable clinical diagnosis. The sample processing and data analysis is relevant, however the sample handling on the pre-analytical phase remains scarcely evaluated. The main goal of this study was to favor the preservation of blood smear using a histological resin. This strategy lead us two practical approaches, give a detailed morphometric description of white blood cells and establish reference intervals in male Wistar rats, which are scarcely reported. Blood smears from male Wistar rats (n = 120) and adult men were collected at room temperature. The integrity of Wright-stained cells was evaluated by an in silico image analysis from rat and human blood smear preserved with a toluene-based synthetic resin mounting medium. A single sample of human blood was used as a control of procedure. The reference intervals was established by cell counting. Based on the results of segmentation algorithm followed by an automatic thresholding analysis, the incorporation of resin favor the conservation of cell blood populations, and lead to identify morphologic features such as nucleus/cytoplasmic shape, granules presence and DNA appearance in nucleus of white blood cells. The use of a histological resin could favor a fast and efficient sample handling in silico MPBC measurements both in the species studied as in wild animals.
Topics: Algorithms; Animals; Humans; Image Processing, Computer-Assisted; Leukocytes; Male; Rats; Rats, Wistar; Specimen Handling
PubMed: 35716583
DOI: 10.1016/j.acthis.2022.151917 -
Ear, Nose, & Throat Journal 2017Our aim was to find out the association between nasal smear eosinophil count and allergic rhinitis (AR) and to determine a cutoff value that is significant for a...
Our aim was to find out the association between nasal smear eosinophil count and allergic rhinitis (AR) and to determine a cutoff value that is significant for a diagnosis of AR. We also wanted to determine whether this count is related to the predominant symptoms, duration, or type and severity of AR, or to the presence of coexisting asthma. We selected 100 patients with a clinical diagnosis of allergic rhinitis across all age groups and an equal number of age- and sex-matched controls for the study. Their nasal smear eosinophil counts were recorded in terms of the number of eosinophils per high-power field (HPF). All patients were then clinically assessed for asthma and underwent spirometry. The data were recorded and appropriate statistical analysis done. The difference in the mean eosinophil counts of patients with AR and controls was found to be statistically significant (p = 0.000). A nasal smear eosinophil count of >0.3 per HPF had a 100% specificity and a 100% positive predictive value for AR. Asthma was associated with allergic rhinitis in 40% of patients; an association was not found between nasal smear eosinophil count and the symptoms, duration, type, and severity of allergic rhinitis or coexistent asthma. We conclude that an eosinophil count of >0.3 per HPF in nasal smears is a highly specific criterion for the diagnosis of AR. However, nasal smear eosinophil counts are poor indicators of the degree, duration, or type of upper or associated lower airway inflammation due to allergy.
Topics: Adolescent; Adult; Child; Child, Preschool; Eosinophils; Female; Humans; Infant; Infant, Newborn; Leukocyte Count; Male; Middle Aged; Nose; Predictive Value of Tests; Reference Values; Rhinitis, Allergic; Sensitivity and Specificity; Severity of Illness Index; Young Adult
PubMed: 29121381
DOI: 10.1177/0145561317096010-1105 -
ACS Applied Materials & Interfaces May 2021An accurate microscopical analysis of blood smears requires a reproducible and convenient method of staining. Solution-based staining procedures can be cumbersome....
An accurate microscopical analysis of blood smears requires a reproducible and convenient method of staining. Solution-based staining procedures can be cumbersome. Especially in low- and middle-income countries, the lack of skilled technicians and adequate laboratory facilities, as well as insufficient water and reagent quality, often become confounding factors. To overcome these obstacles, we developed a new cell staining method based on sequential stamping of agarose gel patches that contain eosin, methylene blue/oxidized methylene blue, Azure B, and buffer, respectively. Our method, termed "hydrogel staining", provides a simple, reproducible, solution-free, and inexpensive approach to stain blood cells. We have optimized incubation times to achieve the optimal transfer of dyes to fixed blood cells on a glass slide, with outcomes comparable to conventional solution-based methods for white blood cells and malaria-infected red blood cells. This hydrogel staining method does not require special skills to produce excellent quality stained blood film slides. The new method could enhance the accuracy of microscopical examination of blood smears, especially in resource-limited settings.
Topics: Blood Cells; Humans; Hydrogels; Malaria; Reproducibility of Results; Staining and Labeling
PubMed: 33870697
DOI: 10.1021/acsami.0c22521 -
Blood Reviews Nov 2023Chronic lymphocytic leukemia (CLL) is a B cell neoplasm characterized by the accumulation of aberrant monoclonal B lymphocytes. CLL is the predominant type of leukemia... (Review)
Review
Chronic lymphocytic leukemia (CLL) is a B cell neoplasm characterized by the accumulation of aberrant monoclonal B lymphocytes. CLL is the predominant type of leukemia in Western countries, accounting for 25% of cases. Although many patients remain asymptomatic, a subset may exhibit typical lymphoma symptoms, acquired immunodeficiency disorders, or autoimmune complications. Diagnosis involves blood tests showing increased lymphocytes and further examination using peripheral blood smear and flow cytometry to confirm the disease. With the significant advancements in machine learning (ML) and artificial intelligence (AI) in recent years, numerous models and algorithms have been proposed to support the diagnosis and classification of CLL. In this review, we discuss the benefits and drawbacks of recent applications of ML algorithms in the diagnosis and evaluation of patients diagnosed with CLL.
Topics: Humans; Leukemia, Lymphocytic, Chronic, B-Cell; Artificial Intelligence; B-Lymphocytes; Lymphoma; Machine Learning
PubMed: 37758527
DOI: 10.1016/j.blre.2023.101134 -
Scientific Reports Nov 2022Treatment of blood smears with Wright's stain is one of the most helpful tools in detecting white blood cell abnormalities. However, to diagnose leukocyte disorders, a...
Treatment of blood smears with Wright's stain is one of the most helpful tools in detecting white blood cell abnormalities. However, to diagnose leukocyte disorders, a clinical pathologist must perform a tedious, manual process of locating and identifying individual cells. Furthermore, the staining procedure requires considerable preparation time and clinical infrastructure, which is incompatible with point-of-care diagnosis. Thus, rapid and automated evaluations of unlabeled blood smears are highly desirable. In this study, we used color spatial light interference microcopy (cSLIM), a highly sensitive quantitative phase imaging (QPI) technique, coupled with deep learning tools, to localize, classify and segment white blood cells (WBCs) in blood smears. The concept of combining QPI label-free data with AI for the purpose of extracting cellular specificity has recently been introduced in the context of fluorescence imaging as phase imaging with computational specificity (PICS). We employed AI models to first translate SLIM images into brightfield micrographs, then ran parallel tasks of locating and labelling cells using EfficientNet, which is an object detection model. Next, WBC binary masks were created using U-net, a convolutional neural network that performs precise segmentation. After training on digitally stained brightfield images of blood smears with WBCs, we achieved a mean average precision of 75% for localizing and classifying neutrophils, eosinophils, lymphocytes, and monocytes, and an average pixel-wise majority-voting F1 score of 80% for determining the cell class from semantic segmentation maps. Therefore, PICS renders and analyzes synthetically stained blood smears rapidly, at a reduced cost of sample preparation, providing quantitative clinical information.
Topics: Neural Networks, Computer; Leukocytes; Microscopy; Lymphocytes; Monocytes
PubMed: 36414631
DOI: 10.1038/s41598-022-21250-z -
Veterinary Clinical Pathology Mar 2018Hematologic and serum biochemical reference values obtained from captive or free-ranging wildlife populations may not be comparable as there can be significant...
BACKGROUND
Hematologic and serum biochemical reference values obtained from captive or free-ranging wildlife populations may not be comparable as there can be significant variations due to preanalytic and analytic differences, including methods of capture and restraint, overall management in captivity including diet and composition of animal groups, and analytic methods being used. Hematology and serum biochemistry have never been studied in captive or free-ranging populations of Sechuran foxes (Lycalopex sechurae).
OBJECTIVES
The purposes of the study were to determine hematologic and serum biochemical RI in Sechuran foxes and to explore differences in these variables related to sex and overall life circumstances.
METHODS
Blood samples were obtained from 15 free-ranging and 15 captive Sechuran foxes. Hematology variables were assessed by blood smear examination and automated analyzer methodology. Serum biochemical analysis was performed by automated analyzer methodology. Descriptive statistics were calculated for each variable. Data obtained from free-ranging and captive groups were statistically compared and RIs were calculated.
RESULTS
Captive Sechuran foxes had significantly (P < .05) higher MCH, MCHC, and eosinophil counts and significantly lower band neutrophil counts than free-ranging foxes. Free-ranging Sechuran foxes had significantly (P < .05) higher serum lipase and globulins and significantly lower albumin, total bilirubin, and indirect bilirubin than captive foxes.
CONCLUSIONS
These findings suggest that there are hematologic and serum biochemical differences between captive and free-ranging Sechuran fox populations. Hence, such differences should be considered when using these variables to assess the health status of this species.
Topics: Animals; Animals, Wild; Animals, Zoo; Blood Chemical Analysis; Female; Foxes; Hematology; Male; Peru; Reference Values
PubMed: 29364544
DOI: 10.1111/vcp.12568 -
Blood Coagulation & Fibrinolysis : An... Sep 2022Current diagnosis of primary immune thrombocytopenia (ITP) is presumptive, centered on excluding other causes of thrombocytopenia. The diagnosis of ITP is challenging...
Current diagnosis of primary immune thrombocytopenia (ITP) is presumptive, centered on excluding other causes of thrombocytopenia. The diagnosis of ITP is challenging because of the wide range of potential inherited and acquired causes of thrombocytopenia. The treatment of ITP is empiric with steroids, high-dose immunoglobulin, immunosuppressants and thrombopoietin agonists with potential side effects. We searched Medline and Cochrane databases, reviewed the study data and analyzed the individual diagnostic tests for their evidence-based role in the diagnosis of ITP. We then analyzed the strength of the scientific evidence for each diagnostic test in the diagnosis of ITP and identified gaps in the diagnostic accuracy. The diagnostic challenges in ITP include: insufficient evidence for the individual test for diagnosis of ITP, no standardized protocol/guideline for diagnosis, hurdles in accessing the available resources and failure to correlate the clinical data while reviewing the blood smear. We did not identify a diagnostic test that clinicians can use to confirm the diagnosis of ITP. In the absence of a diagnostic test of proven value in ITP, the clinician is best served by a comprehensive history and physical examination, complete blood count and review of the peripheral blood smear in evaluating thrombocytopenia.
Topics: Humans; Purpura, Thrombocytopenic, Idiopathic; Thrombocytopenia; Thrombopoietin
PubMed: 35867940
DOI: 10.1097/MBC.0000000000001144 -
American Family Physician Aug 2001Purpura is the result of hemorrhage into the skin or mucosal membrane. It may represent a relatively benign condition or herald the presence of a serious underlying... (Review)
Review
Purpura is the result of hemorrhage into the skin or mucosal membrane. It may represent a relatively benign condition or herald the presence of a serious underlying disorder. Purpura may be secondary to thrombocytopenia, platelet dysfunction, coagulation factor deficiency or vascular defect. Investigation to confirm a diagnosis or to seek reassurance is important. Frequently, the diagnosis can be established on the basis of a careful history and physical examination, and a few key laboratory tests. Indicated tests include a complete blood cell count with platelet count, a peripheral blood smear, and prothrombin and activated partial thromboplastin times.
Topics: Algorithms; Blood Coagulation; Blood Coagulation Disorders; Child; Diagnosis, Differential; Humans; IgA Vasculitis; Leukemia; Lupus Erythematosus, Systemic; Purpura; Purpura, Thrombocytopenic, Idiopathic; Uremia
PubMed: 11515831
DOI: No ID Found -
International Journal of Laboratory... May 2018This review focuses on how image processing and machine learning can be useful for the morphological characterization and automatic recognition of cell images captured... (Review)
Review
INTRODUCTION
This review focuses on how image processing and machine learning can be useful for the morphological characterization and automatic recognition of cell images captured from peripheral blood smears.
METHODS
The basics of the 3 core elements (segmentation, quantitative features, and classification) are outlined, and recent literature is discussed. Although red blood cells are a significant part of this context, this study focuses on malignant lymphoid cells and blast cells.
RESULTS
There is no doubt that these technologies may help the cytologist to perform efficient, objective, and fast morphological analysis of blood cells. They may also help in the interpretation of some morphological features and may serve as learning and survey tools.
CONCLUSION
Although research is still needed, it is important to define screening strategies to exploit the potential of image-based automatic recognition systems integrated in the daily routine of laboratories along with other analysis methodologies.
Topics: Blast Crisis; Blood Cells; Clinical Laboratory Techniques; Humans; Image Processing, Computer-Assisted; Lymphocytes; Machine Learning
PubMed: 29741258
DOI: 10.1111/ijlh.12818