Peripheral Blood Smear Analysis Research Articles

Establishment of human acute monocytic leukemia model with systemic infiltration in NPG mice.

A model construction of systemic acute leukemia is challenging. Herein, we established a systemic leukemia mouse model using highly immunodeficient NPG mice without any immunosuppressive treatments. NPG mice received tail intravenous injection of SHI-1 cells at the concentration of 1×107 cells (group A) or 5×107 cells (group B) and randomly sacrificed each seven days post-inoculation. Tumor development was monitored using nested-PCR, peripheral blood-smear analysis, flow cytometry, pathological examinations, and immunohistochemistry. The median survival of mice in groups A and B were 33.0 and 30.0 days, respectively. Blast cells in peripheral blood appeared on day 14 in group B, and on day 21 in group A. In addition, SHI-1 cell specific MLL-AF6 mRNA was detected in both spleen and bone marrow on day 14 post-inoculation. 21 days after inoculation, we observed human CD45+CD33+ cells with an SH-1-immunophenotype in the peripheral blood, spleen, and bone marrow, as well as solid neoplasms in multiple organs. Moreover, the histologically infiltrated leukemic cells expressed CD45. In conclusion, the current study demonstrated the normal growth of SHI-1 cells in the NPG mice without immunosuppression, which caused systemic leukemia similar to that observed in acute leukemia patients. We developed an efficient and reproducible model to study leukemia pathogenesis and progression.

CAE-ResVGG FusionNet: A Feature Extraction Framework Integrating Convolutional Autoencoders and Transfer Learning for Immature White Blood Cells in Acute Myeloid Leukemia

Acute myeloid leukemia (AML) is a highly aggressive cancer form that affects myeloid cells, leading to the excessive growth of immature white blood cells (WBCs) in both bone marrow and peripheral blood. Timely AML detection is crucial for effective treatment and patient well-being. Currently, AML diagnosis relies on the manual recognition of immature WBCs through peripheral blood smear analysis, which is time-consuming, prone to errors, and subject to inter-observers' variation. This study aimed to develop a computer-aided diagnostic framework for AML, called "CAE-ResVGG FusionNet", that precisely identifies and classifies immature WBCs into their respective subtypes. The proposed framework leverages an integrated approach, by combining a convolutional autoencoder (CAE) with finely tuned adaptations of the VGG19 and ResNet50 architectures to extract features from CAE-derived embeddings. The process begins with a binary classification model distinguishing between mature and immature WBCs followed by a multiclassifier further classifying immature cells into four subtypes: myeloblasts, monoblasts, erythroblasts, and promyelocytes. The CAE-ResVGG FusionNet workflow comprises four primary stages, including data preprocessing, feature extraction, classification, and validation. The preprocessing phase involves applying data augmentation methods using geometric transformations and synthetic image generation using the CAE to address imbalance in the WBC distribution. Feature extraction involves image embedding and transfer learning, where CAE-derived image representations are used by a custom integrated model of VGG19 and ResNet50 pretrained models. The classification phase employs a weighted ensemble approach that leverages VGG19 and ResNet50, where the optimal weighting parameters are selected using a grid search. The model performance was assessed during the validation phase using the overall accuracy, precision, and sensitivity, while the area under the receiver characteristic curve (AUC) was used to evaluate the model's discriminatory capability. The proposed framework exhibited notable results, achieving an average accuracy of 99.9%, sensitivity of 91.7%, and precision of 98.8%. The model demonstrated exceptional discriminatory ability, as evidenced by an AUC of 99.6%. Significantly, the proposed system outperformed previous methods, indicating its superior diagnostic ability.

Clinical Approach to Advanced Mantle Cell Lymphoma: A Detailed Case Analysis

Mantle cell lymphoma (MCL) is a rare and aggressive subtype of non-Hodgkin lymphoma (NHL) originating from cells in the mantle zone. Herein, we present a case report of a 49-year-old male patient diagnosed with stage VI MCL, illustrating various diagnostic methods and procedures utilized in his evaluation. The patient presented with progressively enlarging cervical lymph nodes, fatigue, weight loss, anorexia, chronic diarrhea, abdominal pain, and rectal bleeding. Clinical examination revealed cutaneomucosal pallor, tachycardia, expiratory polypnea, bilateral jugulocarotid adenopathies, and splenomegaly. Laboratory investigations showed normocytic normochromic anemia, hyperleukocytosis, lymphocytic predominance, and thrombocytopenia. Peripheral blood smear analysis indicated a lymphoproliferative disorder, confirmed by flow cytometry revealing monotypic lymphoid cells. Bone marrow biopsy showed hypoplastic marrow with atypical cells. Immunohistochemistry confirmed mantle cell lymphoma localization. Subsequent thoraco-abdomino-pelvic CT scan revealed mediastinal and abdominal adenopathy with splenomegaly, leading to a diagnosis of stage IV MCL. The case highlights the importance of early and comprehensive diagnostic approaches in MCL management.

Deep learning-assisted smartphone-based quantitative microscopy for label-free peripheral blood smear analysis.

Hematologists evaluate alterations in blood cell enumeration and morphology to confirm peripheral blood smear findings through manual microscopic examination. However, routine peripheral blood smear analysis is both time-consuming and labor-intensive. Here, we propose using smartphone-based autofluorescence microscopy (Smart-AM) for imaging label-free blood smears at subcellular resolution with automatic hematological analysis. Smart-AM enables rapid and label-free visualization of morphological features of normal and abnormal blood cells (including leukocytes, erythrocytes, and thrombocytes). Moreover, assisted with deep-learning algorithms, this technique can automatically detect and classify different leukocytes with high accuracy, and transform the autofluorescence images into virtual Giemsa-stained images which show clear cellular features. The proposed technique is portable, cost-effective, and user-friendly, making it significant for broad point-of-care applications.

Crowdsourced human-based computational approach for tagging peripheral blood smear sample images from Sickle Cell Disease patients using non-expert users

In this paper, we present a human-based computation approach for the analysis of peripheral blood smear (PBS) images images in patients with Sickle Cell Disease (SCD). We used the Mechanical Turk microtask market to crowdsource the labeling of PBS images. We then use the expert-tagged erythrocytesIDB dataset to assess the accuracy and reliability of our proposal. Our results showed that when a robust consensus is achieved among the Mechanical Turk workers, probability of error is very low, based on comparison with expert analysis. This suggests that our proposed approach can be used to annotate datasets of PBS images, which can then be used to train automated methods for the diagnosis of SCD. In future work, we plan to explore the potential integration of our findings with outcomes obtained through automated methodologies. This could lead to the development of more accurate and reliable methods for the diagnosis of SCD.

Comparative study of sickling test, solubility test, and hemoglobin electrophoresis in sickle cell anemia

Abstract Background: Madhya Pradesh, a state in India, bears the highest number of sickle cell anemia (SCA) cases, particularly among its tribal communities. The diagnosis of suspected SCA cases involves utilizing several methods. The sickling test operates on the principle of hemoglobin S (HbS) polymerization upon deoxygenation. By contrast, the solubility test involves the reduction of HbS using sodium hydrosulfite, followed by precipitation of lysed red blood cells. Hemoglobin (Hb) electrophoresis identifies Hb variants based on their migration in an electric field. Our objective was to assess the efficacy of sickling and solubility tests as screening tools for detecting SCA, comparing them against capillary Hb electrophoresis, which is considered the gold standard. Materials and Methods: All individuals suspected of having SCA between 2022 and 2023 were enrolled in the study. Clinical information, peripheral blood smear analysis, sickling test, solubility test, and capillary Hb electrophoresis were conducted, and the results were compared. Results: Of 250 cases assessed, Hb electrophoresis identified 225 cases of SCA, resulting in a sickle cell disease to sickle cell trait (SCT) ratio of 1:1.36 and a male-to-female ratio of 1:1.33. The highest number of cases were observed in the age group from 21 to 30 years. Generalized weakness (77%) and abdominal pain (52%) were the most frequently reported symptoms. The sickling test demonstrated a sensitivity, specificity, and diagnostic accuracy of 91.5%, 72%, and 89%, respectively, compared with Hb electrophoresis. The solubility test yielded values of 76.5%, 68%, and 75% for sensitivity, specificity, and diagnostic accuracy, while peripheral smear analysis showed 36%, 25%, and 42%, respectively. Conclusion: The sickling test displayed superior sensitivity and diagnostic accuracy compared with the solubility test, with no significant disparity in specificity between these two methods. Notably, the solubility test exhibited a higher incidence of false-negative results for SCT. Therefore, the sickling test is the preferred screening method for SCA.

Peripheral Blood Smear Analysis for Cattle with Foot and Mouth Diseases in Lembang, West Bandung

Foot and Mouth Disease (FMD) is an infectious disease that is endemic and has a significant impact on dairy farming in Indonesia. In reducing the impact caused by FMD, proper handling by veterinarians is necessary. The peripheral blood smear can be used as a data reference to give priority to the right treatment for cattle with FMD. This study aimed to describe the appearance of peripheral blood smears in cattle with FMD. The study data were obtained from 15 cattle with FMD at KPSBU Lembang, West Bandung, West Java, Indonesia. The morphological profile of the blood was examined using the peripheral blood smear method. Morphological abnormalities found in the peripheral blood smear of red blood cells were anisocytosis (microcytosis and macrocytosis), poikilocytosis (achanthocytosis and echinocytosis), and hypochromasia. Different morphological abnormalities of leukocytes can be caused by anorexia due to FMD secondary to lack of nutritional intake. To determine an effective and efficient treatment, it is recommended that veterinarians refer to the results of this study.

Blood Cell Revolution: Unveiling 11 Distinct Types with ‘Naturalize’ Augmentation

Artificial intelligence (AI) has emerged as a cutting-edge tool, simultaneously accelerating, securing, and enhancing the diagnosis and treatment of patients. An exemplification of this capability is evident in the analysis of peripheral blood smears (PBS). In university medical centers, hematologists routinely examine hundreds of PBS slides daily to validate or correct outcomes produced by advanced hematology analyzers assessing samples from potentially problematic patients. This process may logically lead to erroneous PBC readings, posing risks to patient health. AI functions as a transformative tool, significantly improving the accuracy and precision of readings and diagnoses. This study reshapes the parameters of blood cell classification, harnessing the capabilities of AI and broadening the scope from 5 to 11 specific blood cell categories with the challenging 11-class PBC dataset. This transformation facilitates a more profound exploration of blood cell diversity, surpassing prior constraints in medical image analysis. Our approach combines state-of-the-art deep learning techniques, including pre-trained ConvNets, ViTb16 models, and custom CNN architectures. We employ transfer learning, fine-tuning, and ensemble strategies, such as CBAM and Averaging ensembles, to achieve unprecedented accuracy and interpretability. Our fully fine-tuned EfficientNetV2 B0 model sets a new standard, with a macro-average precision, recall, and F1-score of 91%, 90%, and 90%, respectively, and an average accuracy of 93%. This breakthrough underscores the transformative potential of 11-class blood cell classification for more precise medical diagnoses. Moreover, our groundbreaking “Naturalize” augmentation technique produces remarkable results. The 2K-PBC dataset generated with “Naturalize” boasts a macro-average precision, recall, and F1-score of 97%, along with an average accuracy of 96% when leveraging the fully fine-tuned EfficientNetV2 B0 model. This innovation not only elevates classification performance but also addresses data scarcity and bias in medical deep learning. Our research marks a paradigm shift in blood cell classification, enabling more nuanced and insightful medical analyses. The “Naturalize” technique’s impact extends beyond blood cell classification, emphasizing the vital role of diverse and comprehensive datasets in advancing healthcare applications through deep learning.

Deep Learning Models for the Diagnosis of Acute Lymphoblastic Leukemia from Bone Marrow Images : A Comprehensive Literature Review

Introduction: Acute lymphoblastic leukemia (ALL) is an aggressive blood cancer that begins in the bone marrow. It is the most common childhood cancer and requires early and accurate diagnosis for optimal treatment outcomes. Through automated image analysis of peripheral blood smears and bone marrow biopsies, artificial intelligence (AI), particularly Deep Learning (DL), have opened new avenues for improving ALL diagnosis. While bone marrow testing is the gold standard for ALL confirmation, AI applications in diagnosing ALL from bone marrow images have received less attention in the literature than peripheral blood smears. This review aims to assess the current state of AI in ALL diagnosis using bone marrow aspirates and biopsies, with a focus on Deep Learning (DL) models such as Convolutional Neural Networks (CNNs). Methods: A comprehensive literature search, conducted on June 11th, 2023, covered major medical databases, including PubMed/MEDLINE, Scopus, Embase, and Web of Science. Relevant keywords like “acute lymphoblastic leukemia,” “deep learning,” and “neural network” were employed, without time frame restrictions. Articles were included if they assessed the metrics of AI applications for ALL diagnosis in bone marrow aspirates. Articles were excluded if they: (1) had different outcomes, (2) were reviews, (3) were abstracts only, or (4) only reported peripheral blood smear metrics. Results: The search yielded 496 articles. After eliminating duplicates (282), title and abstract screening on the Rayyan platform excluded 204 records, leaving 214 articles eligible for full-text screening. Ten relevant articles were ultimately included in the review. Diverse approaches were presented to enhance diagnostic accuracy and efficiency. One study achieved 100% accuracy in classifying leukemic cells using a unique Convolutional Leaky RELU with CatBoost and XGBoost (CLR-CXG) design. Another study employed transfer learning with CNNs, obtaining 95.3% accuracy for AML, ALL, and CML classification with DenseNet121. Furthermore, the novel “i-Net” model demonstrated 99.18% validation accuracy for white blood cancer segmentation and classification. Adaptive Multi-objective CAT algorithms achieved 99.45% accuracy in detecting bone marrow cancer cells. An AI-based system using deep learning exhibited 97.2% accuracy in diagnosing ALL, while a robust fuzzy logic algorithm combined with a radial basis function neural network achieved 82.93% accuracy in diagnosing ALL in developing countries. Additionally, AI technologies based on computer microscopy demonstrated 95% and 97.5% accuracy in diagnosing ALL and minimal residual disease, respectively. A computer-aided system achieved 97.78% accuracy in classifying ALL subtypes. Conclusion: The potential of AI-driven approaches, particularly deep learning models like CNNs, in improving ALL diagnosis from bone marrow images is highlighted in this review. Because of their superior sensitivity and specificity over peripheral blood smears, bone marrow samples are the gold standard for ALL confirmation. The morphological and cellular properties of bone marrow samples provide important information for disease classification and monitoring. While DL and CNNs have shown promise in diagnosing ALL from peripheral blood smears, their use in bone marrow samples has yet to be investigated deeply. More research and external validation are required to fully realize AI's potential in ALL diagnosis from bone marrow specimens.

A Comprehensive Microscopy and Peripheral Blood Smear Curriculum for Hematology Fellows

Background: Peripheral blood smear (PBS) analysis is an essential skill for the practicing hematologist and allows for the timely diagnosis of a variety of hematologic disorders. In most cases, PBS analysis can be performed faster than advanced laboratory tests, allowing for the prompt treatment of life-threatening diseases, such as acute promyelocytic leukemia and thrombotic microangiopathies. For these reasons, the Accreditation Council for Graduate Medical Education requires that hematology fellows achieve competency in PBS interpretation in order to graduate. However, most hematology training programs lack a structured PBS curriculum and formalized method of skills assessment. Consensus recommendations were recently developed by a multi-institutional focus group as to the ideal structure and components of PBS curricula within hematology training programs (Chase et al., Blood Advances, 2023). Herein, we report our initial experience implementing a longitudinal PBS curriculum for hematology fellows based on these consensus guidelines and demonstrate the effectiveness of this curriculum using a novel assessment tool. Methods: We developed a longitudinal PBS curriculum for hematology fellows at the University of Wisconsin-Madison. The curriculum included an introductory course for first-year fellows on the use of a microscope, slide handling, and PBS review using a hands-on and collaborative approach (Figure 1A). The introductory course included five two-hour sessions spanning the first two months of fellowship. The first three sessions were led by a faculty member and senior fellow and included training on how to use the microscope as well as identification of normal blood cell morphology and blood cell morphologies and hematologic diagnoses deemed high-priority by consensus recommendations using a slide library. For the final two sessions, the fellows were provided with a set of unknowns and asked to work as a group to identify the pathologic findings and underlying diagnosis. The introductory course was supplemented with ongoing experience and education on PBS interpretation through hematology consult, ward, and clinic rotations throughout fellowship under the direction of hematology faculty skilled in PBS analysis. A novel assessment tool was distributed to participants before and after the introductory course in order to assess the effectiveness of the curriculum. The assessment tool was a ten-question image-based questionnaire in which fellows were prompted to identify high-priority morphologies or hematologic diagnoses after being provided with a clinical vignette and associated PBS for review. Results: To date, four hematology fellows have participated in the PBS curriculum. Prior to the introductory course, no participants expressed feeling very or extremely confident in analyzing and interpreting PBS. After the introductory course, 25% of participants expressed feeling very confident in analyzing and interpreting PBS, whereas the remaining 75% felt somewhat confident. 75% of participants strongly agreed that the course improved their ability to use a microscope, and 100% of participants strongly agreed that the course improved their ability to analyze and interpret PBS. Participation in the course led to improved ability of participants to identify high-priority blood cell morphologies and diagnoses as determined by the assessment tool (Figure 1B, 8.25/10 pre-course compared to 9/10 post-course). Conclusions: Our longitudinal PBS curriculum was perceived positively by hematology fellows and led to improved confidence and independence in using a microscope and PBS interpretation. Additionally, participation in the introductory course improved identification of high-priority PBS morphologic abnormalities and hematologic diagnoses. Our curriculum and assessment tool serve as proof of concept that can now be improved upon and potentially adopted on a larger scale to promote competency in PBS interpretation among hematology trainees.

Mutant p53 Drives the Development of Myelodysplastic Syndromes Via Dysregulating Pre-mRNA Splicing in Hematopoietic Stem and Progenitor Cells

Despite the clinical importance of TP53 mutations, to date there have been no studies on the functional impact of TP53 mutations on the initiation and progression of MDS. We found that heterozygous p53 mutant mice ( p53R248W/+) show extended survival and died within 15-20 months after birth. p53 mutant mice had hypercellular bone marrow and displayed cytopenia, thrombocytopenia, and anemia. Approximately 60% of p53R248W/+ mice developed MDS based upon pathological analysis of bone marrow (BM) and peripheral blood smears, while the remaining p53R248W/+ mice developed lymphoma and sarcoma. We further showed that mutant p53-driven MDS are transplantable. Thus, we have generated a mouse model of MDS that has some features of human MDS with TP53 mutations. To understand how mutant p53 drives MDS development, we performed RNA-seq studies to compare gene expression in hematopoietic stem and progenitor cells (HSPCs). GSEA analysis revealed that spliceosome genes were significantly downregulated in middle-aged p53 R248W/+ HSPCs compared to age-matched p53 +/+ HSPCs. We confirmed that the expression of splicing factors, such as Prpf3 and Prpf4, was significantly downregulated in middle-aged p53 R248W/+ HSPCs. We conducted alternative splicing analysis utilizing MISO (Mixture of Isoforms) algorithm to identify differences in exon inclusion ratio between WT and mutant HSPCs. We observed differential splicing of all classes of alternative splicing events, including Cassette Exons (CE), Competing 5′ and 3′ splice sites (A5' or A3'SS), Mutually Exclusive Exons (MXE), and Retained Introns (RI) in p53 R248W/+ cells compared to that of the WT HSPCs. Notably, we found that murine p53 mutant HSPCs exhibited aberrant splicing of key regulators of NFκBactivation, such as USP15. USP15 overexpression promotes NFκB expression through inhibiting its ubiquitination, whereas NFκB promotes USP15 expression. p53 mutant HSPCs tend to skip exon 7 and express high levels of short isoform of Usp15. The short isoform of Usp15, but not the long isoform of Usp15, activates NFκB in HSPCs, manifested by increased phosphorylation of p65. To determine the impact of mutant p53 on pre-mRNA splicing in human HSPCs, we ectopically expressed GFP or p53 R248W in human cord blood CD34 + cells and performed RNA-seq in transduced cells (GFP +). Human HSPCs expressing mutant p53 displayed alterations in pre-mRNA splicing compared to HSPCs expressing GFP. We found that human HSPCs expressing mutant p53 display aberrant splicing in key regulator of NFκB such as IKBKE (Inhibitor of nuclear factor kappa-B kinase subunit epsilon). Human HSPCs expressing mutant p53 tend to include exon 7 and express high levels of long isoform of IKBKE. The long isoform of IKBKE, but not the short isoform of IKBKE, activates NFκB in human HSPCs. Many proinflammatory cytokine genes are NFκB targets and we observed increased levels of pro-inflammatory cytokines, including IL-1β and IL-6, in the BM of middle-aged p53 mutant mice. Notably, we observed increased levels of IL-1β and IL-6 in the BM of MDS or AML patients with TP53 mutations. TP53 mutations co-occur with splicing factor mutations in MDS. To determine whether TP53 and SRSF2 mutations cooperate in pathogenesis of MDS, we have generated p53 R248W/+SRSF2 P95H/+ mice. We found that the survival of recipient mice repopulated with p53 R248W/+SRSF2 P95H/+ BM cells was significantly decreased compared to recipients repopulated with WT, p53 R248W/+, or SRSF2 P95H/+ BM cells. All recipient mice repopulated with p53 R248W/+SRSF2 P95H/+ BM cells died within 6 months and developed MDS or leukemia. Thus, we demonstrate that TP53 and SRSF2 mutations cooperate in MDS or leukemia development. In summary, we discovered that mutant p53 dysregulates pre-mRNA splicing in key regulators of inflammatory response during aging, thereby generating a chronic inflammatory microenvironment to drive MDS pathogenesis.

A SURVEY ON VARIOUS APPROACHES FOR SEGMENTATION AND CLASSIFICATION OF WHITE BLOOD CELLS

Traditionally, White Blood Cell identification is performed by experienced pathologists manually. Peripheral blood smear analysis is a laboratory procedure that helps in diagnosis of various pathological disorders such as malaria, anemia, leukemia, etc. This process is performed at a microscopic level and therefore is required to be precise. Manually performing microscopic evaluation is a challenging task. This task can be automated with the help of computer-aided systems. This work discusses various methods being used in a variety of cellular image segmentation and classification tasks with the field of the survey being concentrated on leukocyte segmentation and classification.

Computational analysis of peripheral blood smears detects disease-associated cytomorphologies

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.

A comparative study of red cell histogram along with CBC parameters and peripheral blood smear in various anemias

: The red blood cell (RBC) parameters generated by cell counters can aid in morphological categorization of anemia, the significance of microscopic analysis of peripheral blood smears (PBSs) cannot be overlooked when it comes to interpreting the underlying cause of anemia. Therefore, both RBC parameters and microscopic examination of PBSs are essential for a comprehensive assessment of anemia.This study aimed to evaluate and compare the results obtained through two different methods: examination of peripheral blood smears (PBS) and automated cell counter generated parameters. The objective was to identify any differences or similarities in the diagnostic outcomes produced by each method. Over the course of one year, from December 2020 to November 2021, a hospital-based, prospective study was conducted. The study aimed to evaluate and compare the PBS findings and RBC parameters and histograms generated by a cell counter in 1000 anemic patients.In a sample of 1000 cases, we compared the typing of anemia using an automated analyzer and peripheral smear examination. Out of these cases, 690 showed consistent typing results between the two methods, while 310 showed discordant typing. The automated analyzer diagnosed majority of cases 70.1% as microcytic anemia and Normocytic, dimorphic, and macrocytic cases were found in 13.5%, 7.8%, and 4.3% of cases, respectively. Additionally, a normal histogram was observed in 17.6% of cases.We have concluded that while the automated analyzer is useful in reducing the overall workload through its graphical representation of anemia typing, it should always be confirmed through microscopy. The automated analyzer is a helpful tool, it should not be relied upon solely for accurate anemia typing. Microscopy remains an essential method for confirming the results of automated analysis.

An interactive e-learning module on peripheral blood smear analysis is an effective option for teaching pathology trainees.

This study compares the effectiveness of an interactive e-learning module with a traditional text-based method for teaching peripheral blood smear analysis. Pathology trainees at Accreditation Council for Graduate Medical Education residency programs were asked to participate. Participants completed a multiple-choice test on peripheral blood smear findings. Trainees were randomized into completing an e-learning module or a PDF reading exercise with the same educational content. Respondents rated their experience and completed a postintervention test composed of the same questions. In total, 28 participants completed the study; 21 improved their score in the posttest (mean, 21.6 correct answers) compared with the pretest (19.8; P < .001). This improvement was seen in both the PDF (n = 19) and interactive (n = 9) groups, with no difference in performance between the 2 groups. Trainees with less clinical hematopathology experience showed a trend of having the largest performance improvement. Most participants completed the exercise within 1 hour, rated the exercise as easy to navigate, were engaged, and reported learning new information about peripheral blood smear analysis. All participants indicated that they would likely complete a similar exercise in the future. This study suggests that e-learning is an effective tool for hematopathology education and equivalent to traditional narrative-based methods. This module could easily be incorporated into a curriculum.

Accurate stratification between VEXAS syndrome and differential diagnoses by deep learning analysis of peripheral blood smears.

VEXAS syndrome is a newly described autoinflammatory disease associated with UBA1 somatic mutations and vacuolization of myeloid precursors. This disease possesses an increasingly broad spectrum, leading to an increase in the number of suspected cases. Its diagnosis via bone-marrow aspiration and UBA1-gene sequencing is time-consuming and expensive. This study aimed at analyzing peripheral leukocytes using deep learning approaches to predict VEXAS syndrome in comparison to differential diagnoses. We compared leukocyte images from blood smears of three groups: participants with VEXAS syndrome (identified UBA1 mutation) (VEXAS); participants with features strongly suggestive of VEXAS syndrome but without UBA1 mutation (UBA1-WT); participants with a myelodysplastic syndrome and without clinical suspicion of VEXAS syndrome (MDS). To compare images of circulating leukocytes, we applied a two-step procedure. First, we used self-supervised contrastive learning to train convolutional neural networks to translate leukocyte images into lower-dimensional encodings. Then, we employed support vector machine to predict patients' condition based on those leukocyte encodings. The VEXAS, UBA1-WT, and MDS groups included 3, 3, and 6 patients respectively. Analysis of 33,757 images of neutrophils and monocytes enabled us to distinguish VEXAS patients from both UBA1-WT and MDS patients, with mean ROC-AUCs ranging from 0.87 to 0.95. Image analysis of blood smears via deep learning accurately distinguished neutrophils and monocytes drawn from patients with VEXAS syndrome from those of patients with similar clinical and/or biological features but without UBA1 mutation. Our findings offer a promising pathway to better screening for this disease.

Qualitative Abnormalities of Peripheral Blood Smear Images Using Deep Learning Techniques

In recent years, Peripheral blood smear is a generic analysis to assess the person’s health status. Manual testing of Peripheral blood smear images are difficult, time-consuming and is subject to human intervention and visual error. This method encouraged for researchers to present algorithms and techniques to perform the peripheral blood smear analysis with the help of computer-assisted and decision-making techniques. Existing CAD based methods are lacks in attaining the accurate detection of abnormalities present in the images. In order to mitigate this issue Deep Convolution Neural Network (DCNN) based automatic classification technique is introduced with the classification of eight groups of peripheral blood cells such as basophil, eosinophil, lymphocyte, monocyte, neutrophil, erythroblast, platelet, myocyte, promyocyte and metamyocyte. The proposed DCNN model employs transfer learning approach and additionally it carries three stages such as pre-processing, feature extraction and classification. Initially the pre-processing steps are incorporated to eliminate noisy contents present in the image by using Histogram Equalization (HE). It is enclosed to improve an image contrast. In order to distinguish the dissimilar class and segmentation approach is carried out with the help of Fuzzy C-Means (FCM) model whereas its centroid point optimality method with Slap Swarm based optimization strategy. Moreover some specific set of Gray Level Co-occurrence Matrix (GLCM) features of the segmented images are extracted to augment the performance of proposed detection algorithm. Finally the extracted features are recorded by DCNN and the proposed classifier has the capability to extract their own features. Based on this the diverse set of classes are classified and distinguished from qualitative abnormalities found in the image.

Remote Digital Microscopy Improves Hematology Laboratory Workflow by Reducing Peripheral Blood Smear Analysis Turnaround Time.

The demand for morphological diagnosis by peripheral blood smear (PBS) analysis with clearly defined turnaround times (TAT), coupled with a shortage of morphologists and increasing cost containment, is driving digitalization to the forefront of laboratory workflow. Labor-intensive manual PBS review affects weekend workflow with limited staff availability. The impact of remote analysis of PBS on the performance of hematology laboratories has not yet been assessed. Following implementation of fully remote digital microscopy within our laboratory, we measured its impact on morphology workflow efficiency, TAT, and hours saved per month. A retrospective study of the effects of remote PBS analysis on the morphology workflow in a tertiary medical center using the Scopio Labs X100 Full-Field PBS system was conducted. 10,704 PBS samples were analyzed pre-and post -implementation, over a 5-month period. Overall PBS workload, and average TAT of PBS samples over weekends and the first two weekdays were collected and evaluated. Remote weekend viewing resulted in a 15.8% reduction in the overall morphology TAT of the laboratory (p <0.03) over a 5-month period, despite similar overall workload. PBS analysis TAT on Fridays was reduced by 41.4% (p <0. 006), and by 59.1% on the first weekday (p <0.02). The additional hours incurred over the weekend were offset against a reduced need for double weekday shifts resulting in approximately 12.76 work hours saved per month. Internet links to clinically relevant cases are provided. The Scopio Labs Full-Field X100 PBS system with remote analysis capacity significantly reduced PBS TAT and improved the morphology workflow of the hematology laboratory. PBSs with significant clinical findings are now available for remote viewing by on-call clinicians located outside the medical center perimeter. Remote PBS viewing, coupled with the overall monthly cost savings, merit consideration for the implementation of full digitalization for remote PBS review.

White blood cell detection using saliency detection and CenterNet: A two-stage approach.

White blood cell (WBC) detection plays a vital role in peripheral blood smear analysis. However, cell detection remains a challenging task due to multi-cell adhesion, different staining and imaging conditions. Owing to the powerful feature extraction capability of deep learning, object detection methods based on convolutional neural networks (CNNs) have been widely applied in medical image analysis. Nevertheless, the CNN training is time-consuming and inaccuracy, especially for large-scale blood smear images, where most of the images are background. To address the problem, we propose a two-stage approach that treats WBC detection as a small salient object detection task. In the first saliency detection stage, we use the Itti's visual attention model to locate the regions of interest (ROIs), based on the proposed adaptive center-surround difference (ACSD) operator. In the second WBC detection stage, the modified CenterNet model is performed on ROI sub-images to obtain a more accurate localization and classification result of each WBC. Experimental results showed that our method exceeds the performance of several existing methods on two different data sets, and achieves a state-of-the-art mAP of over 98.8%.

Hematologic Complications in Patients Hospitalized with COVID-19 Infection.

Introduction: This review summarizes data from patients with COVID-19 requiring intensive care unit (ICU) admission. The goals of this study are to showcase some morphological anomalies found in peripheral blood smears from COVID-19 patients and to bring attention to how some hematologic abnormalities in COVID-19 that correspond to disease severity and mortality. Methods: We performed a retrospective analysis of hematologic parameters using peripheral blood smear analysis from 31 COVID-19 patients hospitalized between April 2021 and January 2022. Results: We found abnormal morphology that has not been previously reported. We also report that severe lymphopenia, neutrophilia, acute hemolysis, hematologic malignancies, and increased LDH are associated with ICU admissions, respiratory failure requiring intubation, and poor clinical outcome. Conclusion: We propose these recommendations in the management of COVID-19 patients: 1. Early diagnosis and follow-up of DIC; 2. Optimization of thromboprophylaxis regimen.