Search Results (95)

Climate change significantly affects human physiology and contributes to increased morbidity and mortality, with heat stress representing one of the most severe consequences of thermal imbalance. The aim of this study was to analyze morphological changes to leukocytes on the peripheral blood smears of Wistar rats exposed to hyperthermia using the geometric morphometrics method. A total of forty Wistar albino rats were divided into three experimental groups according to water temperature exposure (37 °C, 41 °C, and 44 °C). Peripheral blood smears were prepared, stained, and digitally recorded using Motic Images Plus 2.0 software, after which selected images were analyzed using geometric morphometric programs (tpsDig, tpsUtil, and MorphoJ) to evaluate leukocyte shape variations. Comparative analysis demonstrated statistically significant morphological changes in polymorphonuclear cell shapes between the control group (37 °C) and rats exposed to 41 °C (p = 0.009). Significant differences were also identified in mononuclear cell morphology between the antemortem and postmortem groups (p = 0.00307). The findings indicate that exposure to elevated temperatures induces measurable alterations in white blood cell morphology, confirming that hyperthermia produces significant structural changes in polymorphonuclear cells and mononuclear cells detectable through geometric morphometric analysis. Full article

Accurate and efficient classification of hematological malignancies from peripheral blood smear (PBS) images remains challenging due to the scarcity of annotated datasets, staining variability, and subtle morphological differences among blood cancer subtypes. To address these limitations, this study proposes an Advanced Lightweight Deep Learning (ALDL) framework for the multi-class classification of Acute Lymphoblastic Leukemia (ALL) across four clinically significant stages: Benign, Pro-B, Pre-B, and Early Pre-B. The framework integrates EfficientNetV2-S with Convolutional Block Attention Modules (CBAM) to enhance spatial and channel-wise feature refinement. At the same time, Focal Loss is employed to mitigate class imbalance by prioritizing hard-to-classify samples. A robust preprocessing pipeline, including CLAHE contrast enhancement, Reinhard stain normalization, and data augmentation, improves feature visibility and dataset generalization. Lesion segmentation is performed using RGB-based thresholding and watershed overlay, followed by lesion-level cropping to ensure consistency across inputs. Experimental evaluations on the ALL-DB dataset demonstrate the superior performance of the proposed method, achieving an average accuracy of 96.11%, an F1-score of 95.99%, and an AUC of 0.9875. Comparative analyses against MobileNetV3, ResNet50, DenseNet121, VGG16, and InceptionV3 confirm that the proposed segmentation-guided EfficientNetV2-S + CBAM + Focal Loss framework consistently outperforms conventional CNN architectures across both 70:30 and 60:40 train–test splits. Furthermore, a detailed investigation of color spaces (RGB, HSV, LAB, and HED) indicates that RGB yields the most reliable segmentation and classification results. At the same time, HED enhances lesion visualization at the expense of higher computational cost. The proposed ALDL framework demonstrates strong potential for real-world application as a computer-aided diagnostic (CAD) system for early leukemia detection, offering improved diagnostic reliability, reduced error rates, and practical scalability for clinical environments. Full article

Background: Accurate and early detection of hematological disorders from microscopic peripheral blood smear images remains a technically challenging task due to inherent imaging limitations, including noise contamination, low contrast, staining variability, and significant cellular overlap. Conventional deep learning-based object detection frameworks often exhibit limited robustness under such conditions and demonstrate reduced sensitivity to small-scale morphological structures, particularly platelets and abnormal cell variants. Methods: To address these challenges, this study proposes a hybrid detection framework that integrates a fuzzy logic-driven image preprocessing module with the YOLOv11 object detection architecture. The proposed preprocessing pipeline employs adaptive fuzzy membership functions to normalize pixel intensity distributions, suppress high-frequency noise, and enhance edge-defined cellular boundaries. This transformation produces a structurally optimized feature representation, improving downstream feature extraction and localization performance. The proposed framework was evaluated on a curated dataset of 3000 annotated microscopic blood smear images spanning five hematological classes. Results: Experimental results show that the fuzzy logic module improves mAP@0.5 by +3.4% and mAP@0.5:0.95 by +3.6%, confirming its effectiveness in enhancing both classification and localization accuracy. Conclusions: These findings demonstrate the robustness and practical applicability of the proposed hybrid approach under challenging imaging conditions. Full article

Background/Objectives: Acute promyelocytic leukemia (APL) is a high-risk subtype of acute myeloid leukemia and requires rapid diagnosis to avoid early mortality. Current clinical diagnostic and genetic tests are time-consuming, expensive, and complex. Notably, all these tests depend on bone marrow aspiration and are intensely invasive, resulting in poor patient compliance. This study aimed to develop a rapid, explainable, and accurate auxiliary tool for cell-level detection of abnormal promyelocytes in peripheral blood smears, which can serve as a key clue for suspecting APL. Methods: We developed a multi-stage deep learning (DL) model that automatically read images of peripheral blood smears (PBSs), accurately segmented cells, and identified abnormal promyelocytes using only image data. We retrospectively reviewed a total of 114 bone marrow smears (42 APL patients and 72 non-APL patients) and 158 PBSs (30 APL patients and 128 non-APL patients) at the Fifth Affiliated Hospital of Harbin Medical University and collected 223,123 cell images for training. Then, the efficacy of EfficientDet in APL screening was evaluated with an additional 150 PBSs (50 from APL patients and 100 from non-APL patients) and finally compared with manual microscopy. Results: EfficientDet exhibited superior overall screening performance compared with pathologists in the identification of abnormal promyelocytes. Conclusions: Our findings suggest that the DL approach we describe herein is promising as a practical tool for abnormal promyelocyte detection and early APL screening, raising attention to suspected cases of APL for expert evaluation and further reducing diagnostic delays. Full article

Background: Sickle cell disease (SCD) is a prevalent hereditary hemoglobinopathy associated with substantial morbidity, particularly in regions with limited access to advanced laboratory diagnostics. Conventional diagnostic workflows, including manual peripheral blood smear examination and biochemical or molecular assays, are resource-intensive, time-consuming, and subject to observer variability. Recent advances in artificial intelligence (AI) enable automated analysis of blood smear images and offer a scalable alternative for SCD screening. Methods: This study presents a controlled benchmark of CNNs, Vision Transformers, hierarchical Transformers, and hybrid CNN–Transformer architectures for image-level SCD classification using a publicly available peripheral blood smear dataset. Eleven ImageNet-pretrained models were fine-tuned under identical conditions using an explicit leakage-safe evaluation protocol, incorporating duplicate-aware, group-based data splitting and repeated splits to assess robustness. Performance was evaluated using accuracy and macro-averaged precision, recall, and F1-score, complemented by bootstrap confidence intervals, paired statistical testing, error-type analysis, and explainable AI (XAI). Results: Across repeated group-aware splits, CNN-based and hybrid architectures demonstrated more stable and consistently higher performance than transformer-only models. MaxViT-Tiny and DenseNet121 ranked highest overall, while pure ViTs showed reduced effectiveness under data-constrained conditions. Error analysis revealed a dominance of false-positive predictions, reflecting intrinsic morphological ambiguity in challenging samples. XAI visualizations suggest that CNNs focus on localized red blood cell morphology, whereas hybrid models integrate both local and contextual cues. Conclusions: Under limited-data conditions, convolutional inductive bias remains critical for robust blood-smear-based SCD classification. CNN and hybrid CNN–Transformer models offer interpretable and reliable performance, supporting their potential role as decision-support tools in screening-oriented research settings. Full article

Background and Clinical Significance: Malaria remains a significant public health issue in Latin America, where Plasmodium vivax predominates but P. falciparum continues to circulate. Mixed-species infections are uncommon and can pose diagnostic challenges, particularly when parasite densities differ markedly, increasing the risk of underdetecting P. falciparum with conventional methods. Case report: We report a 9-year-old boy from an endemic area with a six-day febrile syndrome. Thick smear and peripheral blood film microscopy, complemented by rapid diagnostic tests for pan-Plasmodium and HRP2 antigens, confirmed a mixed infection with P. vivax (5500 parasites/µL) and P. falciparum (562 parasites/µL). The patient was hemodynamically stable, without severe malaria criteria, and laboratory values were within normal limits. Following confirmation of normal glucose-6-phosphate dehydrogenase activity, treatment with artemether–lumefantrine was initiated, followed by primaquine for hypnozoite eradication. Clinical evolution was favorable, with progressive defervescence, treatment tolerance, and documented parasite clearance. Conclusions: This case illustrates the risk of underestimating P. falciparum in mixed infections with disparate parasitemias and highlights the value of integrated diagnostic approaches in resource-limited endemic settings. It also underscores surveillance limitations that can misclassify mixed infections, potentially affecting epidemiological estimates and treatment strategies. Timely recognition and comprehensive diagnostic evaluation are essential to ensure appropriate antimalarial therapy, prevent complications, and inform public health interventions in regions where both species coexist. Full article

Background and Objectives: Neutrophil extracellular traps (NETs) have been linked to hypercoagulability, immunothrombosis, and organ injury in COVID-19. Digital morphology of peripheral blood smears enables the identification of NET-compatible appearances (NET-like) in circulation, and associations between NET-like derived indices and clinical outcomes have been reported. However, evidence at hospital admission that relates smear NET-like burden to systemic inflammation and clinical severity remains limited. We therefore aimed to compare the burden of NET-like structures on admission smears according to disease severity and systemic inflammatory markers. Materials and Methods: We included 50 consecutively enrolled adults hospitalized for COVID-19; samples were obtained within 24 h of admission. Severity was defined by the World Health Organization Clinical Progression Scale and grouped as moderate or severe. C-reactive protein (CRP), ferritin, and complete blood counts were measured; the neutrophil-to-lymphocyte ratio (NLR) and platelet-to-lymphocyte ratio (PLR) were calculated. Digital morphology assessed 200 leukocytes per patient; the presence of morphological abnormalities, including NET-like events per patient, was recorded. We additionally quantified NET-like events per 100 white blood cells (NET-like/100 WBC) and the neutrophil extracellular trap–segmented neutrophil ratio (NNSR). Results: At admission, CRP, ferritin, NLR, and PLR of patients were above method-specific reference intervals. NET-like events were identified in 66% of patients. NET-like/100 WBC correlated positively with NLR (r = 0.312; p < 0.05). Patients with severe COVID-19 had higher NET-like/100 WBC than those with moderate disease (5.8 ± 7.34 vs. 14.14 ± 15.12; p = 0.0294). Conclusions: Digital morphological identification of NET-like structures on peripheral blood smears is frequent at admission and is associated with systemic inflammatory burden and with greater COVID-19 severity. These findings support the potential complementary value of reporting NET-like events for initial risk stratification in the clinical laboratory. Full article

Background/Objectives: Conventional workflows, peripheral blood smears, and bone marrow assessment supplemented by LDI-PCR, molecular cytogenetics, and array-CGH, are expert-driven in the face of biological and imaging variability. Methods: We propose an AI pipeline that integrates convolutional neural networks (CNNs) and transfer learning-based models with two explainable AI (XAI) approaches, LIME and Grad-Cam, to deliver both high diagnostic accuracy and transparent rationale. Seven public sources were curated into a unified benchmark (66,550 images) covering ALL, AML, CLL, CML, and healthy controls; images were standardized, ROI-cropped, and split with stratification (80/10/10). We fine-tuned multiple backbones (DenseNet-121, MobileNetV2, VGG16, InceptionV3, ResNet50, Xception, and a custom CNN) and evaluated the accuracy and F1-score, benchmarking against the recent literature. Results: On the five-class task (ALL/AML/CLL/CML/Healthy), MobileNetV2 achieved 97.9% accuracy/F1, with DenseNet-121 reaching 97.66% F1. On ALL subtypes (Benign, Early, Pre, Pro) and across tasks, DenseNet121 and MobileNetV2 were the most reliable, achieving state-of-the-art accuracy with the strongest, nucleus-centric explanations. Conclusions: XAI analyses (LIME, Grad-CAM) consistently localized leukemic nuclei and other cell-intrinsic morphology, aligning saliency with clinical cues and model performance. Compared with baselines, our approach matched or exceeded accuracy while providing stronger, corroborated interpretability on a substantially larger and more diverse dataset. Full article

Myeloproliferative neoplasms (MPNs) are a heterogeneous group of diseases originating from hematopoietic stem cell transformation, characterized by the clonal proliferation of hematopoietic progenitors. A specific subset includes myeloid/lymphoid neoplasms with eosinophilia and tyrosine kinase (TK) gene fusions, particularly involving PDGFR A or B, which are sensitive to TK inhibitor treatment. We report a case of a 21-year-old patient with a myeloproliferative/myelodysplastic neoplasm, presenting with hyperleukocytosis, anemia, thrombocytopenia, and elevated LDH. The peripheral blood smear showed hypogranular neutrophils, eosinophils, basophils, and myeloid precursors. The absence of BCR::ABL1 and mutations in JAK2, CALR, and MPL excluded common MPNs. Cytogenetic analysis revealed a rearrangement between chromosomes 5 and 14. FISH analysis confirmed an inverted insertion from chromosome 5 to chromosome 14, involving the PDGFRB gene. WGS and RNAseq identified a fusion between PDGFRB and CCDC88C, causing the constitutive activation of PDGFRB. The fusion gene was confirmed by sequencing. This allowed for targeted therapy with a tyrosine kinase inhibitor (TKI), leading to molecular remission monitored by RT-qPCR. This case highlights how a multidisciplinary approach can identify atypical transcripts in MPN, guiding targeted therapy with TK inhibitors, thus resulting in effective treatment and molecular remission. Full article

We report the first confirmed case of persistent microfilaremia in a human host infected with Dirofilaria repens. A 54-year-old woman from an endemic area in Croatia presented with peripheral eosinophilia and dermatological symptoms. Over four months, microfilariae were repeatedly detected in her blood using thick smears and Knott’s test, and the diagnosis was molecularly confirmed via COI gene sequencing and detection of Wolbachia endosymbionts. This case provides compelling evidence that D. repens can sustain a complete or near-complete life cycle in humans under specific conditions. Our findings have significant implications for clinical diagnostics, One Health surveillance, and public health interventions. Full article

Background: Erythroblasts have recently been identified as host cells for malarial parasites, revealing a previously underappreciated host–parasite interaction. However, their extremely low abundance in peripheral blood has hindered progress, especially in elucidating the biological significance of parasitized erythroblasts (pEBs) in vivo. Methods: Here, we visualized pEBs in a murine model and established a method to increase their number in peripheral blood by immunizing mice with live Plasmodium yoelii 17XNL, followed by challenge with P. berghei ANKA. Results: Immunized mice were protected from cerebral malaria and survived longer, during which pEBs appeared in circulation and were detected using Giemsa-stained smears. All blood-stage parasite forms were identified within pEBs, including enucleating erythroblasts. Conclusions: This model enables in vivo/ex vivo analysis of pEB biology without bone marrow/spleen isolation, thus lowering technical/ethical barriers for the field. Full article

Background/Objectives: We wished to raise awareness of Hereditary Spherocytosis (HS) as a potential cause of early and significant hemolytic newborn jaundice. Methods: We utilized three recent cases from our experience to discuss hyperbilirubinemia etiologies to be considered when a baby has hemolytic hyperbilirubinemia, including HS, and presented a review of the literature about this disorder including presentation and evaluation in the neonate. Results: We found that ABO hemolytic disease of the newborn (HDN) is often considered as the etiology for presumed hemolytic hyperbilirubinemia even when the direct antiglobulin test (DAT) is negative. When there is a mother-baby ABO mismatch and baby’sDAT is negative, another etiology should be sought. HS should be considered in these cases as the prevalence of HS is as frequent as 1 in 2000 in certain populations, it is the third most common hemolytic disorder after ABO isoimmunization and G6PD deficiency, and it is the most common cause of non-immune hemolytic hyperbilirubinemia in neonates with kernicterus. The indices to look for in the complete blood count that are suggestive for HS are MCHC > 36.5–37 g/dL, an MCHC:MCV ratio (HS Index) > 0.36, and increased RDW. The lack of spherocytes on the newborn peripheral blood smear, family history, initial anemia, and reticulocytosis do not eliminate the diagnosis of HS. Conclusions: HS is common and should be included in the differential diagnosis for hemolytic hyperbilirubinemia. Red blood cell indices can suggest the diagnosis of HS, and eosin 5’ maleimide (EMA) testing can be used to make the diagnosis. If DAT-negative ABO HDN is the leading diagnosis for hyperbilirbinemia, a different etiology should urgently be sought. Full article

Background/Objectives: Platelet counts can be affected by storage conditions, potentially leading to pseudothrombocytopenia. The present study aimed to investigate temperature-dependent changes in platelet counts and morphology in whole blood samples anticoagulated with heparin or EDTA. We also examined the molecular mechanism of cold-induced aggregation via integrin GPIIb/IIIa–fibrinogen interaction using established bioinformatics technologies (docking simulation). Methods: Peripheral blood was collected from healthy volunteers (n = 6) and treated with either heparin or EDTA. The samples were stored at 4 °C, room temperature, or incubated at 37 °C. Platelet counts were measured using an automated hematology analyzer. The morphology of various blood cells in smears was assessed using the May-Grünwald Giemsa staining method. Docking simulations using an available software (HADDOCK 2.4) were performed to evaluate integrin–fibrinogen binding at different temperatures. Results: In automated blood cell counting, platelet counts in heparinized blood were significantly decreased under low-temperature conditions (4 °C), but this decrease was restored to levels comparable to those at room temperature upon warming to 37 °C (p < 0.05). No significant changes were observed in EDTA-treated samples. Microscopical findings showed platelet aggregation only in heparinized samples at 4 °C, with normal morphology restored upon warming (37 °C). Docking simulations estimated stronger integrin GPIIb/IIIa–fibrinogen binding at 4 °C than at 37 °C (p = 0.0286), suggesting temperature-dependent enhancement of molecular interactions. Conclusions: These findings indicate that heparin can induce reversible platelet aggregation at low temperatures in whole blood samples, leading to pseudothrombocytopenia. This phenomenon may be mediated by increased integrin GPIIb/IIIa–fibrinogen binding. Full article

Background/Objectives: Acute Lymphoblastic Leukemia (ALL) poses significant diagnostic challenges due to its ambiguous symptoms and the limitations of conventional methods like bone marrow biopsies and flow cytometry, which are invasive, costly, and time-intensive. Methods: This study introduces Neuro-Bridge-X, a novel neuro-symbolic hybrid model designed for automated, explainable ALL diagnosis using peripheral blood smear (PBS) images. Leveraging two comprehensive datasets, ALL Image (3256 images from 89 patients) and C-NMC (15,135 images from 118 patients), the model integrates deep morphological feature extraction, vision transformer-based contextual encoding, fuzzy logic-inspired reasoning, and adaptive explainability. To address class imbalance, advanced data augmentation techniques were applied, ensuring equitable representation across benign and leukemic classes. The proposed framework was evaluated through 5-fold cross-validation and fixed train-test splits, employing Nadam, SGD, and Fractional RAdam optimizers. Results: Results demonstrate exceptional performance, with SGD achieving near-perfect accuracy (1.0000 on ALL, 0.9715 on C-NMC) and robust generalization, while Fractional RAdam closely followed (0.9975 on ALL, 0.9656 on C-NMC). Nadam, however, exhibited inconsistent convergence, particularly on C-NMC (0.5002 accuracy). A Meta-XAI controller enhances interpretability by dynamically selecting optimal explanation strategies (Grad-CAM, SHAP, Integrated Gradients, LIME), ensuring clinically relevant insights into model decisions. Conclusions: Visualizations confirm that SGD and RAdam models focus on morphologically critical features, such as leukocyte nuclei, while Nadam struggles with spurious attributions. Neuro-Bridge-X offers a scalable, interpretable solution for ALL diagnosis, with potential to enhance clinical workflows and diagnostic precision in oncology. Full article

Background/Objectives: Digital morphology analysers have been developed to overcome the limitations of manual microscopy. This study aimed to evaluate the performance of the DC-1 on leukaemia samples, determining if it is a suitable for the identification of leukaemia in low-throughput or remote laboratories. To the best of our knowledge, there is no current published literature evaluating the performance of the DC-1 with leukaemia samples. Methods: This study utilised 88 leukaemia peripheral blood smears donated from various anonymous hospitals and medical laboratories in collaboration with RMIT university. DC-1 pre-classification was compared with post-classification using Cohen’s kappa, sensitivity, and specificity calculations. Pre- and post-classification was compared with manual microscopy using Passing–Bablok regression, Pearson’s r correlation, and Bland–Altman analysis. Results: DC-1 pre-classification results showed a moderate agreement with post-classification (k = 0.52), a very high specificity for most leukocytes (>94%) and variable sensitivity (21–86%). Pre- and post-classification displayed a higher accuracy and correlation with manual results for segmented neutrophils and lymphocytes, compared to other leukocyte classes. Additionally, there was an improvement in the post-classification of immature granulocytes, band neutrophils, and blast cells compared to pre-classification. Conclusions: The results indicate that the DC-1 displayed a better performance for the classification of segmented neutrophils and lymphocytes compared to other cell classes, indicating that the DC-1 is more acceptable for use in infection or normal samples, as opposed to leukaemia. The gold standard therefore remains with the morphologist who can distinguish leukaemia samples. Full article