Search Results (23,541)

This review evaluates the emerging role of circulating tumour cells (CTCs) as clinically meaningful, minimally invasive biomarkers for oral squamous cell carcinoma (OSCC). Despite advances in management, OSCC continues to demonstrate high morbidity and mortality, largely due to late diagnosis and the absence of validated biomarkers for early detection or real-time monitoring. Conventional diagnostic tools, tissue biopsy, and imaging provide only static snapshots and fail to capture tumour heterogeneity or evolving biological behaviour. CTCs offer a novel and significant opportunity to address these limitations. Key findings from recent studies highlight that CTC enumeration correlates with tumour burden, nodal metastasis, recurrence, and overall prognosis. Molecular and phenotypic characterisation further reveals dynamic traits such as epithelial–mesenchymal transition, stemness, and therapy resistance, providing insights into metastatic potential and treatment failure. Technological advances, including immunocytochemistry, microfluidic capture platforms, PCR-based assays, and next-generation sequencing, have enhanced the sensitivity and specificity of CTC detection and enabled detailed multi-omic profiling. Collectively, evidence suggests that integrating CTC analysis into OSCC clinical workflows could improve early detection, refine risk stratification, personalise therapeutic strategies, and support longitudinal monitoring of disease dynamics. As research progresses, CTC-based diagnostics represent a promising frontier in shifting OSCC management toward more precise, adaptive, and biologically informed care. Full article

The increasing interest in the development and integration of navigation and positioning services across a wide range of receivers has exposed them to various security threats, including GNSS jamming and spoofing attacks. Early detection of jamming and spoofing interference is crucial to mitigating these threats and preventing service degradation. This research introduces an interference detection technique leveraging an AI algorithm applied to GNSS data utilizing various methods to enhance detection accuracy and efficiency. The objective was to use modern sensors and AI to develop an effective tool that detects, characterizes, and localizes interference, thereby reducing associated risks. These sensors and algorithms enable continuous GNSS interference monitoring and support real-time Decision-making. A server plays a crucial role in managing the entire system. Its primary function is to process data collected from various sensors referred to as nodes (e.g., static, rover, drone, and space) and from (public) GNSS networks as well as to perform localization using rotating-antenna nodes. Within the interference detection module, various methods were implemented at different points in the software receiver architecture. Each method’s certainty in identifying an interference source depends on its design and capabilities, with outcomes—whether positive or negative—being subject to potential accuracy or errors. To enhance the Decision-making process, an AI-based Decision-making block has been introduced to determine the presence of interference at a given epoch. The proposed interference monitoring methods were evaluated through experiments using GNSS signals under clean, jamming, and spoofing scenarios. The results demonstrate the techniques’ applicability across diverse scenarios, achieving high performance in interference detection, characterization, and localization. Full article

Background/Objectives: The incidence of pediatric pathological scars (PPS) has been gradually increasing due to various causes, highlighting the need for accurate scar assessment to monitor disease progression and therapeutic efficacy. Vancouver Scar Scale (VSS) and other scar evaluation systems are relatively subjective evaluation methods that rely on physicians’ or patients’ own judgment. By contrast, when comparing different scar scale evaluation methods, a three-dimensional (3D) camera and dermoscopy may provide relatively objective measurable parameters to avoid possible subjective bias created by the observers. This study aimed to compare the utility of traditional VSS evaluation with that of 3D cameras and dermoscopy in PPS evaluation. Methods: A total of 35 pediatric patients (aged 0–18 years) with PPS were involved, and their scars were assessed via the VSS, dermoscopy, and the Antera 3D^® system. In addition, a subset of 18 patients (36 scar regions) was also evaluated for therapeutic efficacy after 3–6 months of treatment. Briefly, VSS scores were blindly evaluated by two independent dermatologists under standardized conditions. Quantitative assessment was also performed using dermoscopy and the Antera 3D^® system. The former quantified chromatic parameters (pigmentation: L*, vascularity: a*, green value); the latter captured multispectral 3D images to analyze volume, pigmentation, and erythema. Data are presented as means ± standard deviation and analyzed using paired-sample t tests (one-tailed), the Wilcoxon signed-rank test, and standardized response means (SRMs) to assess therapeutic sensitivity, while baseline variability was evaluated using the standard deviation and coefficient of variation (CV). Results: The results showed that Antera 3D^® detected significant reductions in pigmentation (p < 0.01, SRM = −0.46), vascularity (p < 0.001, SRM = −0.59), and volume (p < 0.0001, SRM = −0.83), while dermoscopy indicated similar moderate improvements in vascularity (Green value: p < 0.001, SRM = 0.57; a*: p < 0.0001, SRM = −0.68) and pigmentation (L*: p < 0.0001, SRM = 0.48) after treatments. VSS showed significant gains in pliability (p < 0.0001, SRM = −1.13), height (p < 0.01, SRM = −0.54), and overall impression (p < 0.0001, SRM = −0.86), but minimal changes in pigmentation (p > 0.05, SRM = 0) or vascularity (p > 0.05, SRM = −0.21). At baseline, Antera 3D^® showed the greatest variability in pigmentation (CV 43.41%) and volume (CV 91.21%), followed by VSS in vascularity (CV 52.95%), pliability (CV 34.05%), and overall impression (CV 31.76%). Dermoscopy presented the lowest variability, indicating limited discriminative power. Conclusions: In conclusion, Antera 3D^® offers an objective, sensitive, and spatially precise approach for PPS assessment and may provide additional quantitative information for evaluating subtle and early changes alongside traditional scar assessment scales. Its integration into clinical practice will enhance treatment monitoring and support more accurate timing of therapeutic interventions. Full article

Early and precise detection of plant diseases is essential for safeguarding crop yield and ensuring sustainable agricultural practices. In this study, we propose the Modified RefineNet with Attention based Fusion (MoRefNet-AF), a Modified RefineNet architecture enhanced with attention-based fusion for multi-class classification of corn (maize) and Pepper leaf diseases. Unlike the original RefineNet, which was segmentation-oriented and computationally heavy, MoRefNet-AF is redesigned for lightweight and discriminative classification. The modifications include replacing standard convolutions with depthwise separable convolutions for efficiency, adopting the Mish activation function for smoother gradient flow, redesigning the multi-resolution fusion module with concatenation and shared convolution for richer cross-scale integration, and incorporating Squeeze-and-Excitation (SE) blocks for adaptive channel recalibration. Additionally, Chained Residual Pooling (CRP) with atrous convolutions enhances contextual representation, while global average pooling with dense layers improves classification readiness. When evaluated on a curated six-class dataset combining PlantVillage and Mendeley leaf disease repositories, MoRefNet-AF achieved 99.88% accuracy, 99.74% precision, 99.73% recall, 99.95% F1-score, and 99.73% specificity. These results outperform strong baselines including ResNet152V2, DenseNet201, EfficientNet-B0, and ConvNeXt-Tiny, while maintaining only 0.3 M parameters. With its compact design and TensorFlow Lite (v2.13) compatibility, MoRefNet-AF offers a robust, lightweight, and real-time deployable solution for precision agriculture and smart plant disease monitoring. Full article

Background: Parkinson’s disease (PD) is characterized by progressive degeneration of dopaminergic neurons in the substantia nigra pars compacta, accompanied by neuromelanin loss. Neuromelanin-sensitive magnetic resonance imaging (NM-MRI) enables in vivo visualization of these changes; however, its diagnostic and clinical utility remains incompletely defined. This study evaluated the feasibility, reliability, and biological sensitivity of semi-automated NM-MRI–based substantia nigra volumetry in PD. Methods: In this prospective case–control study, 50 participants (25 PD patients and 25 healthy controls) underwent 3T NM-sensitive MRI using a high-resolution T1-weighted spin-echo sequence. Semi-automated segmentation of hyperintense substantia nigra regions was performed using Mango v3.5.1, with intracranial volume normalization derived from FreeSurfer v7.3. Four participants were excluded due to motion artifacts, yielding a final cohort of 46 subjects. Clinical assessment included the Unified Parkinson’s Disease Rating Scale (UPDRS) Part III and Hoehn and Yahr (H&Y) staging. Group comparisons, receiver operating characteristic (ROC) analysis, and reliability testing using intraclass correlation coefficients (ICC) were performed. Results: Corrected substantia nigra volume was significantly reduced in PD patients compared with controls (18% reduction; p = 0.039, Mann–Whitney U test). Semi-automated measurements demonstrated excellent agreement with manual segmentation (ICC = 0.945). ROC analysis showed moderate discriminative performance for corrected volume (AUC = 0.700; sensitivity 68.4%, specificity 74.1%). No significant correlation was observed between corrected substantia nigra volume and UPDRS-III motor scores, while a trend toward lower SNc volume was observed with advancing H&Y stage. Conclusions: Semi-automated NM-MRI volumetry detects biologically meaningful substantia nigra volume loss in early-stage Parkinson’s disease with high measurement reliability. However, diagnostic performance was moderate and insufficient for standalone clinical diagnosis or motor severity prediction. These findings support the role of NM-MRI as a complementary imaging marker within multimodal diagnostic and research frameworks rather than as an independent diagnostic tool. Full article

Background: Retinal and optic nerve disorders are a leading cause of irreversible visual impairment worldwide. Advances in molecular genetics—including next-generation sequencing, genome-wide association studies, and gene-based therapeutic technologies—have reshaped understanding of both inherited and complex retinal diseases. However, translating genetic discovery into sustained clinical benefit remains biologically and practically constrained. Methods: A structured literature search was conducted using PubMed and Scopus to identify relevant studies published between 2015 and 2025. The search focused on molecular genetics, epigenetic modulation, mitochondrial biology, and translational applications in inherited retinal dystrophies and selected complex retinal diseases, prioritizing high-impact original research and systematic reviews addressing diagnostic innovation and therapeutic development. Results: Inherited retinal dystrophies represent the most advanced model of precision ophthalmology, with diagnostic yields approaching 70–80% in well-characterized cohorts. Gene augmentation and genome-editing strategies have demonstrated proof-of-concept efficacy, yet clinical benefit depends on residual cellular viability, delivery efficiency, and durability of expression. Emerging platforms include AAV-mediated gene transfer, in vivo CRISPR-based editing, RNA-directed splice modulation, and mitochondrial-targeted approaches. Persistent barriers include unresolved non-coding and structural variants, variant interpretation uncertainty, and endpoint selection in clinical trials. In contrast, complex retinal diseases such as glaucoma, age-related macular degeneration, and pathological myopia reflect polygenic susceptibility interacting with environmental and aging-related factors. Although polygenic risk scores refine probabilistic prediction, their utility is limited by ancestry bias and incomplete predictive performance. Epigenetic and mitochondrial mechanisms further modulate disease expression but remain largely non-actionable in routine practice. Conclusions: Retinal genetics has progressed from gene discovery to early therapeutic implementation. Future advances will depend on improved variant detection, functional validation, biomarker-guided staging, and integration of genomics with imaging and longitudinal modeling to achieve durable and equitable precision ophthalmology. Full article

Background/Objectives: Non-classical congenital adrenal hyperplasia (NCCAH) due to 21-hydroxylase deficiency represents the mildest form of congenital adrenal hyperplasia and is frequently diagnosed only after the onset of clinical signs in childhood. Newborn screening programs for CAH are primarily designed to detect classical forms and show limited sensitivity for NCCAH. The clinical significance of neonatal 17-hydroxyprogesterone (17-OHP) values below recall thresholds remains incompletely defined. Methods: We retrospectively analyzed clinical, auxological, hormonal, and genetic data from pediatric patients diagnosed with NCCAH between 2018 and 2023 at a tertiary referral center. Neonatal screening 17-OHP concentrations, basal and ACTH-stimulated 17-OHP levels at diagnosis, bone age advancement, pubertal status, and hydrocortisone treatment were evaluated. Correlations between hormonal parameters, age at onset, and treatment dose were assessed. Results: Thirty-five patients (30 females) were included, with a mean age at clinical onset of 7.52 ± 0.36 years for females and 6.25 ± 0.29 years for males. Premature pubarche was the most frequent presenting sign (94.3%), and central precocious puberty was diagnosed in 31.4% of cases. The mean neonatal screening 17-OHP level was 4.53 ± 0.7 ng/mL; only two patients exceeded the screening recall cut-off. At diagnosis, mean basal and ACTH-stimulated 17-OHP levels were 15.1 ± 3.35 and 55.2 ± 11.3 ng/mL, respectively. Age at clinical onset was inversely correlated with both basal and stimulated 17-OHP levels, while hydrocortisone dose correlated positively with biochemical severity. Bone age advancement was observed in all patients. Conclusions: Most children with NCCAH display mildly elevated neonatal 17-OHP values that do not trigger screening recall. Higher biochemical severity is associated with earlier clinical presentation and higher glucocorticoid requirements. Neonatal 17-OHP concentrations, even when below cut-off values, may represent an early indicator of disease severity and warrant further investigation. Full article

Background: Early childhood caries (ECC) is one of the most common chronic diseases in children and remains unevenly distributed across populations. It is associated with pain, impaired function, and long-term health consequences. Although advances have been made in understanding its aetiology and prevention, important gaps in evidence limit progress in prevention, early detection, and equitable care. Objective: To examine current evidence on ECC and identify key research gaps across biological, behavioral, social, and health system domains. Methods: This narrative review draws on peer-reviewed literature addressing ECC epidemiology, pathogenesis, risk factors, diagnosis, management, and service delivery. The literature was examined to identify areas where evidence is limited, inconsistent, or insufficient to inform clinical practice and public health policy. Results: Research on ECC remains uneven across levels. Longitudinal evidence linking microbiome dynamics, host susceptibility, and lesion progression is limited, restricting causal understanding. Genetic and epigenetic contributions are incompletely defined, particularly in diverse populations. Although socioeconomic gradients are well established, integrative models connecting structural determinants with biological mechanisms are scarce. Emerging diagnostic tools, including biomarkers and artificial intelligence, lack robust evidence demonstrating improved clinical or behavioral outcomes. Implementation research addressing scalability, cost-effectiveness, and equity impact is underdeveloped, especially in low-resource settings. Long-term systemic and developmental consequences of ECC remain insufficiently characterized. Conclusions: Addressing ECC requires integrated and equity-oriented research frameworks that bridge biological, social, diagnostic, and implementation domains. Clarifying these gaps is essential to inform coherent prevention strategies and reduce persistent disparities in child oral health. Full article

Gas kick events in drilling operations are characterized by strong coupling dynamics, subtle early-stage evolution, and severe class imbalance, which limit the effectiveness of conventional feature-independent monitoring methods. To address these challenges, this paper proposes a structure-aware intelligent monitoring framework for early gas kick detection. First, multivariate drilling parameters are modeled as an interacting graph, and a graph neural network (GNN) is introduced to capture relational dependencies and anomaly propagation behaviors at the structural level. Second, to mitigate abnormal sample scarcity and enhance temporal discriminability, a representation enhancement strategy integrating conditional tabular generative adversarial networks (CTGAN) and shapelet-based temporal patterns is developed. Finally, a multi-level interpretability mechanism combining graph attention analysis and SHAP attribution is constructed to provide transparent insights into both structural interactions and feature contributions. Experiments conducted on real drilling datasets demonstrate that the proposed GNN baseline achieves the highest accuracy (0.7302) among various machine learning and deep learning models. With representation enhancement, the GNN+CTGAN+Shapelet model further improves accuracy to 0.7507 and F1-score to 0.7347, validating the effectiveness of the enhancement strategy. Interpretability results reveal that the model decisions are primarily driven by flow-rate and standpipe-pressure-related temporal evolution patterns, which are consistent with drilling engineering knowledge. Overall, the proposed framework provides a structurally consistent, robust, and interpretable solution for intelligent gas kick monitoring in modern drilling operations. Full article

Introduction: Cystic fibrosis (CF) frequently presents prenatally with meconium ileus (MI), a condition associated with significant neonatal morbidity and long-term gastrointestinal complications. The advent of highly effective CFTR modulators, particularly elexacaftor/tezacaftor/ivacaftor (ETI), during pregnancy remains off-label, and their role as in utero therapy for affected fetuses of carrier mothers is still emerging. Methods: We conducted a narrative literature review using PubMed, Embase, and Scopus to identify published reports of in utero CFTR modulator therapy for MI between 2022 and 2026. Seven relevant studies were identified and qualitatively synthesized. Their findings were interpreted in comparison with the present case. Results: We describe the first Italian case of prenatal ETI therapy for fetal CF. At 32 weeks’ gestation, ultrasound (US) findings were suggestive of evolving MI. Both parents were carriers of F508del CFTR and subsequent testing confirmed fetal homozygosity. Following urgent multidisciplinary consultation and ethics committee approval, maternal ETI therapy was initiated at 33 weeks’ gestation. After 21 days of treatment, follow-up fetal US demonstrated improvement in bowel dilatation and hyperchogenity. The infant was delivered at 36 + 2, passed meconium spontaneously, and required no surgical intervention. Pharmacokinetic assessment showed substantial transplacental transfer of all three ETI components, with cord-to-maternal plasma ratios of 0.34 (elexacaftor), 2.48 (tezacaftor), and 0.58 (ivacaftor), and detectable concentrations in amniotic fluid. Postnatally, sweat chloride was elevated, and pancreatic function transitioned from initially preserved to pancreatic insufficiency within the first month of life. Conclusions: This case and literature review suggest that prenatal CFTR modulation may influence the early trajectory of CF, potentially by preventing MI and potentially delaying the progression to pancreatic insufficiency and potentially reducing later gastrointestinal complications. While evidence remains limited, these findings highlight a potential therapeutic window during fetal life and underscore the need for prospective data collection, structured registries, and harmonized clinical guidance in this evolving field. Full article

Some diseases affecting the oral mucosa can be life-threatening and/or associated with life-threatening complications. Conventional diagnostic methods for most oral mucosal diseases are usually employed at a fully established disease state. All these peculiarities usually result in late diagnosis, poor prognosis, poor treatment outcomes, and reduced overall survival rates, hence the need for novel methods for the early detection of these disease conditions. Small extracellular vesicle (sEV)-based diagnosis carries great potential for early diagnosis of oral mucosal diseases, as sEVs reflect the physiological status of their parent cells. sEVs are also widely distributed in body fluids, which helps overcome the problem of inaccessibility in sample or specimen collection in some cases. Furthermore, the composition of sEVs can be used as diagnostic biomarkers for several disease conditions, including oral mucosal diseases. This review critically examines the emerging role of sEVs-derived biomarkers from saliva and blood in the diagnosis of some oral mucosal diseases, such as hand, foot, and mouth disease (HFMD), oral lichen planus (OLP), oral leukoplakia (OL), and oral squamous cell carcinoma (OSCC). It also discusses the need for the validation and standardization of the potential sEV-derived diagnostic biomarkers of these oral mucosal diseases for clinical application. Full article

West Nile virus (WNV) is a mosquito-borne flavivirus of growing importance for both human and equine health in Europe. Horses are highly susceptible to neurological disease and, because they share ecological exposure with humans, they represent valuable sentinels for detecting local viral circulation within a One Health framework. However, diagnosis of WNV infection in equines is complicated by the short and low-level viraemia, which limits the sensitivity of molecular assays, and by serological cross-reactivity with related flaviviruses and the confounding effects of vaccination. In this narrative review, we summarise the current diagnostic tools for WNV in horses, including direct detection methods (RT-qPCR, virus isolation, antigen detection) and indirect serological approaches (IgM and IgG ELISA, virus neutralisation tests), and discuss their practical performance and constraints in clinical and surveillance settings. We further examine equine surveillance systems, passive clinical reporting, active serosurveys and sentinel cohorts, and their integration with vector, avian and environmental monitoring. Key challenges include methodological heterogeneity, limited access to confirmatory testing and variable cross-sector data sharing. Finally, we outline future directions, highlighting the need for harmonised laboratory protocols, innovative field-deployable diagnostics, genomic surveillance and integrated, multi-source monitoring systems to strengthen early warning capacity and improve preparedness for WNV outbreaks in equine populations. Full article

Masson Pine (Pinus massoniana), an important afforestation species in southern China, is severely threatened by pine wilt disease caused by pine wood nematode (Bursaphelenchus xylophilus, PWN). To differentiate mortality induced by B. xylophilus from that caused by abiotic environmental factors, hyperspectral imaging and needle chlorophyll content were measured and analyzed for the early detection physiological changes in Masson pine seedlings under various environmental stressors. Four-year-old Masson pine seedlings were subjected to PWN inoculation, mechanical injury, drought, and waterlogging treatments. Hyperspectral reflectance and needle chlorophyll content of Masson pine were measured concurrently at 7-day intervals. The results showed that hyperspectral imaging responses varied among the stressors. Both PWN and waterlogging stress induced rapid mortality, with spectral changes observed as early as the 3rd week and reaching statistical significance by the 5th week. Under PWN infection, hyperspectral reflectance increased markedly in the 405–580 nm range, accompanied by a pronounced blue-shift of the red edge position (680–750 nm), while needle chlorophyll content declined sharply from approximately 0.8 mg g⁻¹ to 0.48 mg g⁻¹. Waterlogging stress produced a uniform increase in reflectance within the 500–580 nm range, with the hyperspectral curve gradually flattening, and needle chlorophyll content decreasing from 0.75 mg g⁻¹ to 0.6 mg g⁻¹. Conversely, drought-stressed seedlings exhibited only minor hyperspectral changes and maintained relatively stable chlorophyll levels, demonstrating the inherent drought tolerance of Masson pine. The RF and XGBoost models performed best in fitting the entire process of pine wood nematode infection and waterlogging stress, with all R² values greater than 0.69. The distinct hyperspectral imaging patterns under nematode infection and water-related stresses provide a reliable basis for early diagnosis and monitoring pine wilt disease in Masson pine stands. Full article

Tree ensembles—Random Forests (RFs) and Gradient Boosting Machines (GBMs)—often stabilize before all trees are evaluated. We study early stopping as a nonparametric change-point problem on prediction increments. The P²-STOP method family monitors a robust interquartile-range (IQR) scale of prediction increments online and stops when a relative-scale criterion is met. The default variant uses a rolling-window exact-quantile estimator ($O\left(w\right)$ memory), which provides a clean finite-sample stopping guarantee; a full-prefix P² streaming approximation ($O\left(1\right)$ memory) is available as a memory-light alternative. The stopping rule applies to both RFs and GBMs without model-specific distributional assumptions. On four RF benchmarks (MNIST, Covertype, HIGGS, and Credit Card Fraud), P²-STOP achieves 44.8% mean work reduction (range: 0.7–71.7%) with an accuracy change from $-0.53$ to $+0.02$ percentage points versus full-ensemble inference. On XGBoost ($T=500$), work reduction is dataset-dependent (41.4% on Covertype up to 89.0% on Credit Card), with corresponding accuracy trade-offs. Under random-tree contamination conditions (5%, 15%, and 25%), performance remains stable, whereas IQR-versus-standard-deviation baseline differences are mixed rather than uniformly dominant. Designed for compiled inference engines (e.g., C++/Numba), P²-STOP translates theoretical work reduction into consistent wall-clock speedups ($4.14\times$–$4.82\times$ versus compiled full RF on MNIST/Covertype/HIGGS for $T=500$). Native Python implementations serve purely as logical baselines due to loop overhead, while Credit Card exhibits the expected slowdown when work reduction is near zero. All comparisons use five seeds with 95% confidence intervals and seed-level paired tests. With only five seeds, inferential power is limited, and p-values should be interpreted cautiously. Relative to the Dirichlet RF baseline, our contribution is not larger RF-specific work reduction; it is a robust nonparametric IQR-scale stopping criterion, cast as a change-point/sequential-inference problem, that works as a post hoc wrapper across RF and GBM settings. 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