Hematology analyzers are essential diagnostic and monitoring tools for detecting blood diseases. Although contemporary analyzers produce only basic insights, they are often not as detailed as required under the personalized medicine paradigm. Next-Generation Hematology Analyzers (NGHAs) are revolutionary newcomers in the field, with significant advantages over regular hematology analyzers. They provide deeper insights into cellular morphology, function, and genetic profiles. This detailed information opens up possibilities for tailor-made diagnostic and therapeutic approaches in precision medicine. This review presents some revolutionary technologies that have changed hematology analyzers and provides an overview of their limitations, basic functions, and influence on clinical practice. It focuses on the integration of state-of-the-art technologies, such as microfluidics, advanced optics, artificial intelligence, flow cytometry, and digital imaging, empowering NGHAs to improve diagnostic accuracy, rapidly detect diseases, and support flexible, targeted therapy. Hints regarding point-of-care hematology testing are also provided to discuss its implications for transforming healthcare
Traditional health authority approval for oncology drugs is based on a clinical benefit endpoint, or a valid surrogate. In 1992 the FDA created the Accelerated Approval pathway to allow for earlier approval of therapies in serious conditions with an unmet medical need. This is accomplished typically by granting accelerated approval based on a surrogate endpoint that can be measured earlier than a traditional approval endpoint. Minimal residual disease (MRD) is a sensitive measure of residual cancer cells in hematology oncology after treatment, and is increasingly considered as a secondary or exploratory endpoint due to its prognostic potential for traditional clinical trial endpoints such as progression-free survival (PFS) and overall survival (OS). This work aims to evaluate MRD's surrogacy potential across several hematologic cancer indications while keeping the focus on follicular lymphoma (FL), using data from published studies. We examine individual-level and trial-level correlations extracted from previously published studies to elucidate the potential role of MRD in accelerating the drug approval process in hematology oncology trials.
This industrial Ph.D. project, carried out in collaboration between Radiometer Medical ApS and SDU Centre for Photonics Engineering at the University of Southern Denmark, explored the use of digital holographic microscopy (DHM) for the purposes of differential white blood cell counts (dWBCs) in point-of-care (PoC) devices for acute care settings. Two DHM prototypes were developed; an initial lens-based system serving as the foundation for algorithm development, and experimental validation of the approach, achieving 89.6% classification accuracy on a 3-part differential, and a subsequent lensless system for simplified design and increased field-of-view (FoV). Both prototypes employed convolutional neural networks (CNNs) for cell classification. With further optimizations, the lensless system achieved classification accuracies of 92.65% and 89.44% on the 3-part and 5-part differential, respectively. With the lensless system, the derivation of the monocyte distribution width (MDW), a biomarker for sepsis, was also demonstrated. Additionally, pixel super-resolution and multi-wavelength DHM approaches were investigated to enhance the obtained cell information. Finally, a proof-of-princi
In hematology, computational models offer significant potential to improve diagnostic accuracy, streamline workflows, and reduce the tedious work of analyzing single cells in peripheral blood or bone marrow smears. However, clinical adoption of computational models has been hampered by the lack of generalization due to large batch effects, small dataset sizes, and poor performance in transfer learning from natural images. To address these challenges, we introduce DinoBloom, the first foundation model for single cell images in hematology, utilizing a tailored DINOv2 pipeline. Our model is built upon an extensive collection of 13 diverse, publicly available datasets of peripheral blood and bone marrow smears, the most substantial open-source cohort in hematology so far, comprising over 380,000 white blood cell images. To assess its generalization capability, we evaluate it on an external dataset with a challenging domain shift. We show that our model outperforms existing medical and non-medical vision models in (i) linear probing and k-nearest neighbor evaluations for cell-type classification on blood and bone marrow smears and (ii) weakly supervised multiple instance learning for ac
Sparse autoencoders (SAEs) emerged as a promising tool for mechanistic interpretability of transformer-based foundation models. Very recently, SAEs were also adopted for the visual domain, enabling the discovery of visual concepts and their patch-wise attribution to tokens in the transformer model. While a growing number of foundation models emerged for medical imaging, tools for explaining their inferences are still lacking. In this work, we show the applicability of SAEs for hematology. We propose CytoSAE, a sparse autoencoder which is trained on over 40,000 peripheral blood single-cell images. CytoSAE generalizes to diverse and out-of-domain datasets, including bone marrow cytology, where it identifies morphologically relevant concepts which we validated with medical experts. Furthermore, we demonstrate scenarios in which CytoSAE can generate patient-specific and disease-specific concepts, enabling the detection of pathognomonic cells and localized cellular abnormalities at the patch level. We quantified the effect of concepts on a patient-level AML subtype classification task and show that CytoSAE concepts reach performance comparable to the state-of-the-art, while offering exp
Deep learning is popularly used for analyzing pathology images, but variations in image properties can limit the effectiveness of the models. The study aims to develop a method that transfers the variability present in the training set to unseen images, improving the model's ability to make accurate inferences. YOLOv5 was trained on peripheral blood and bone marrow sample images and Neural Color Transfer techniques were used to incorporate invariance. The results showed significant improvement in detecting WBCs from untrained samples after normalization, highlighting the potential of deep learning-based normalization techniques for inference robustness.
Metallic plating systems composed of titanium and its alloys remain the standard treatment for craniofacial bony fixation but may require secondary removal due to infection, implant migration, or discomfort. Thus, biodegradable metallic implants may eliminate complications and secondary procedures while maintaining structural integrity. Our previous work demonstrated the fabrication of immiscible Fe-AZ31 composites via additive manufacturing with improved degradation kinetics over pure Iron. This study aimed to evaluate the in vitro and in vivo biocompatibility of Fe-AZ31 composites for potential craniofacial fixation applications. Pure iron (Fe), Mg alloy (AZ31) and Fe-AZ31 samples were fabricated for extract-based cytotoxicity testing using HFF-1 fibroblasts, L929 fibroblasts and hFOB osteoblasts. Metal extracts were prepared at a 3 cm^2/mL surface-to-volume ratio in complete media at 37C and cell viability was measured by live/dead assay after 24 and 72h exposure. For in vivo evaluation, Fe-AZ31, Fe, and Ti plates were implanted subcutaneously in wild type mice for 6 weeks, 3 and 6 months. Implant degradation, histologic response, hematology, and serum biochemistry were assessed
White blood cell (WBC) classification is fundamental for hematology applications such as infection assessment, leukemia screening, and treatment monitoring. However, real-world WBC datasets present substantial appearance variations caused by staining and scanning conditions, as well as severe class imbalance in which common cell types dominate while rare but clinically important categories are underrepresented. To address these challenges, we propose a stain-normalized, decoupled training framework that first learns transferable representations using instance-balanced sampling, and then rebalances the classifier with class-aware sampling and a hybrid loss combining effective-number weighting and focal modulation. In inference stage, we further enhance robustness by ensembling various trained backbones with test-time augmentation. Our approach achieved the top rank on the leaderboard of the WBCBench 2026: Robust White Blood Cell Classification Challenge at ISBI 2026.
Although the circulatory system functions as a continuous source of physiological data, contemporary diagnostics remain bound to intermittent, time-delayed assessments. To resolve this, we present a framework for ubiquitous hematological profiling driven by Integrated Sensing and Communication (ISAC). We demonstrate how electromagnetic signals can be exploited to monitor blood in real-time, effectively converting them into diagnostic tools. We analyze the biological foundations of blood, review existing Complete Blood Count (CBC) and sensing technologies, and detail a novel pipeline for continuous blood monitoring. Furthermore, we discuss the potential applications of deploying these devices to enable real-time CBC and biomarker detection, ultimately revolutionizing how we predict, detect, and manage individual and public health.
White blood cell (WBC) classification plays a vital role in hematology for diagnosing various medical conditions. However, it faces significant challenges due to domain shifts caused by variations in sample sources (e.g., blood or bone marrow) and differing imaging conditions across hospitals. Traditional deep learning models often suffer from catastrophic forgetting in such dynamic environments, while foundation models, though generally robust, experience performance degradation when the distribution of inference data differs from that of the training data. To address these challenges, we propose a generative replay-based Continual Learning (CL) strategy designed to prevent forgetting in foundation models for WBC classification. Our method employs lightweight generators to mimic past data with a synthetic latent representation to enable privacy-preserving replay. To showcase the effectiveness, we carry out extensive experiments with a total of four datasets with different task ordering and four backbone models including ResNet50, RetCCL, CTransPath, and UNI. Experimental results demonstrate that conventional fine-tuning methods degrade performance on previously learned tasks and s
Red blood cell (RBC) deformation is the consequence of several diseases, including sickle cell anemia, which causes recurring episodes of pain and severe pronounced anemia. Monitoring patients with these diseases involves the observation of peripheral blood samples under a microscope, a time-consuming procedure. Moreover, a specialist is required to perform this technique, and owing to the subjective nature of the observation of isolated RBCs, the error rate is high. In this paper, we propose an automated method for differentially enumerating RBCs that uses peripheral blood smear image analysis. In this method, the objects of interest in the image are segmented using a Chan-Vese active contour model. An analysis is then performed to classify the RBCs, also called erythrocytes, as normal or elongated or having other deformations, using the basic shape analysis descriptors: circular shape factor (CSF) and elliptical shape factor (ESF). To analyze cells that become partially occluded in a cluster during sample preparation, an elliptical adjustment is performed to allow the analysis of erythrocytes with discoidal and elongated shapes. The images of patient blood samples used in the stu
Red blood cells (RBCs) are essential to human health, and their precise morphological analysis is important for diagnosing hematological disorders. Despite the promise of foundation models in medical diagnostics, comprehensive AI solutions for RBC analysis remain scarce. We present RedDino, a self-supervised foundation model designed for RBC image analysis. RedDino uses an RBC-specific adaptation of the DINOv2 self-supervised learning framework and is trained on a curated dataset of 1.25 million RBC images from diverse acquisition modalities and sources. Extensive evaluations show that RedDino outperforms existing state-of-the-art models on RBC shape classification. Through assessments including linear probing and nearest neighbor classification, we confirm its strong feature representations and generalization ability. Our main contributions are: (1) a foundation model tailored for RBC analysis, (2) ablation studies exploring DINOv2 configurations for RBC modeling, and (3) a detailed evaluation of generalization performance. RedDino addresses key challenges in computational hematology by capturing nuanced morphological features, advancing the development of reliable diagnostic tool
The hematology analytics used for detection and classification of small blood components is a significant challenge. In particular, when objects exists as small pixel-sized entities in a large context of similar objects. Deep learning approaches using supervised models with pre-trained weights, such as residual networks and vision transformers have demonstrated success for many applications. Unfortunately, when applied to images outside the domain of learned representations, these methods often result with less than acceptable performance. A strategy to overcome this can be achieved by using self-supervised models, where representations are learned and weights are then applied for downstream applications. Recently, masked autoencoders have proven to be effective to obtain representations that captures global context information. By masking regions of an image and having the model learn to reconstruct both the masked and non-masked regions, weights can be used for various applications. However, if the sizes of the objects in images are less than the size of the mask, the global context information is lost, making it almost impossible to reconstruct the image. In this study, we inves
Peripheral blood smears remain a cornerstone in the diagnosis of hematological neoplasms, offering rapid and valuable insights that inform subsequent diagnostic steps. However, since neoplastic transformations typically arise in the bone marrow, they may not manifest as detectable aberrations in peripheral blood, presenting a diagnostic challenge. In this paper, we introduce cAItomorph, an explainable transformer-based AI model, trained to classify hematological malignancies based on peripheral blood cytomorphology. Our data comprises peripheral blood single-cell images from 6115 patients with diagnoses confirmed by cytomorphology, cytogenetics, molecular genetics, and immunophenotyping from bone marrow samples, and 495 healthy controls, eight coarse classes. cAItomorph leverages the DinoBloom hematology foundation model and aggregates image encodings via a transformer-based architecture into a single vector. It achieves an overall accuracy of 0.72 in eight disease classification, with F1 scores of 0.76 for acute leukemia, 0.80 for myeloproliferative neoplasms and 0.94 for healthy cases. The overall accuracy increases to 0.87 in top-2 predictions. cAItomorph achieves high sensitivi
Digital hematopathology requires cell-level analysis across diverse disease categories, including malignant disorders (e.g., leukemia), infectious conditions (e.g., malaria), and non-malignant red blood cell disorders (e.g., sickle cell disease). Whether single-task, vision-language, WSI-optimized, or single-cell hematology models, these approaches share a key limitation, they cannot provide unified, multi-task, multi-modal reasoning across the complexities of digital hematopathology. To overcome these limitations, we propose Uni-Hema, a multi-task, unified model for digital hematopathology integrating detection, classification, segmentation, morphology prediction, and reasoning across multiple diseases. Uni-Hema leverages 46 publicly available datasets, encompassing over 700K images and 21K question-answer pairs, and is built upon Hema-Former, a multimodal module that bridges visual and textual representations at the hierarchy level for the different tasks (detection, classification, segmentation, morphology, mask language modeling and visual question answer) at different granularity. Extensive experiments demonstrate that Uni-Hema achieves comparable or superior performance to tr
The rapid advancement of large language models(LLMs) has prompted significant interest in their potential applications in medical domains. This paper presents a comprehensive benchmark evaluation of 27 state-of-the-art LLMs on Chinese medical examination questions, encompassing seven medical specialties across two professional levels. We introduce a robust evaluation framework that assesses model performance on 2,800 carefully curated questions from cardiovascular, gastroenterology, hematology, infectious diseases, nephrology, neurology, and respiratory medicine domains. Our dataset distinguishes between attending physician and senior physician difficulty levels, providing nuanced insights into model capabilities across varying complexity. Our empirical analysis reveals substantial performance variations among models, with Mixtral-8x7B achieving the highest overall accuracy of 74.25%, followed by DeepSeek-R1-671B at 64.07%. Notably, we observe no consistent correlation between model size and performance, as evidenced by the strong performance of smaller mixture-of-experts architectures. The evaluation demonstrates significant performance gaps between medical specialties, with model
A Whole Slide Image (WSI) is a high-resolution digital image created by scanning an entire glass slide containing a biological specimen, such as tissue sections or cell samples, at multiple magnifications. These images are digitally viewable, analyzable, and shareable, and are widely used for Artificial Intelligence (AI) algorithm development. WSIs play an important role in pathology for disease diagnosis and oncology for cancer research, but are also applied in neurology, veterinary medicine, hematology, microbiology, dermatology, pharmacology, toxicology, immunology, and forensic science. When assembling cohorts for AI training or validation, it is essential to know the content of a WSI. However, no standard currently exists for this metadata, and such a selection has largely relied on manual inspection, which is not suitable for large collections with millions of objects. We propose a general framework to generate 2D index maps (tissue maps) that describe the morphological content of WSIs using common syntax and semantics to achieve interoperability between catalogs. The tissue maps are structured in three layers: source, tissue type, and pathological alterations. Each layer ass
Understanding disease relationships through blood biomarkers offers a pathway toward data driven taxonomy and precision medicine. We constructed a digital blood twin from 103 disease signatures comprising longitudinal hematological and biochemical analytes. Profiles were standardized into a unified disease analyte matrix, and pairwise Pearson correlations were computed to assess similarity. Hierarchical clustering revealed robust grouping of hematopoietic disorders, while metabolic, endocrine, and respiratory diseases were more heterogeneous, reflecting weaker cohesion. To evaluate structure, the tree was cut at a stringent threshold, yielding 16 groups. Enrichment of the largest heterogeneous cluster (Cluster 9) showed convergence on cytokine-signaling pathways, indicating shared immunological and inflammatory mechanisms across clinical boundaries. Dimensionality reduction with PCA and UMAP corroborated these results, consistently separating hematological diseases. Random Forest feature selection identified neutrophils, mean corpuscular volume, red blood cell count, and platelets as the most discriminative analytes, reinforcing hematopoietic markers as key drivers. Collectively, t
Fungal infections, such as Coccidioidomycosis, Aspergillosis, and Histoplasmosis, represent a growing public health concern in the United States. The rising incidence of these mycoses is linked to climate shifts, demographic changes, and social determinants of health. However, the actual burden of these infections is often underestimated by traditional surveillance methods. Therefore, this study aims to characterize these infections within the All of Us Research Program and evaluate the quality of clinical and health data related to fungal infections. We constructed three fungi cohorts of Coccidioidomycosis (n=1,173), Aspergillosis (n=687), and Histoplasmosis (n=345) among over 400,000 participants using electronic health record data. We analyzed geographic and sociodemographic distributions and performed a data quality assessment on ten key laboratory biomarkers to evaluate data completeness, unit conformance, and measurement concordance within a 90-day window of diagnosis. Our analysis confirmed known epidemiological patterns, including the geographic distributions of Coccidioidomycosis in the Southwest and Histoplasmosis in the Midwest. Fungal infections disproportionately affec
Clinical ML workflows are often fragmented and inefficient: triage, task selection, and model deployment are handled by a patchwork of task-specific networks. These pipelines are rarely aligned with data-science practice, reducing efficiency and increasing operational cost. They also lack data-driven model identification (from imaging/tabular inputs) and standardized delivery of model outputs. We present a framework that employs a single vision-language model (VLM) in two complementary, modular roles. First (Solution 1): the VLM acts as an aware model-card matcher that routes an incoming image to the appropriate specialist model via a three-stage workflow (modality -> primary abnormality -> model-card ID). Reliability is improved by (i) stage-wise prompts enabling early termination via "None"/"Other" and (ii) a calibrated top-2 answer selector with a stage-wise cutoff. This raises routing accuracy by +9 and +11 percentage points on the training and held-out splits, respectively, compared with a baseline router, and improves held-out calibration (lower Expected Calibration Error, ECE). Second (Solution 2): we fine-tune the same VLM on specialty-specific datasets so that one mo