Objective assessment of stored blood quality by deep learning

Morphology, repulsion, and ordering of red blood cells in viscoelastic flows under confinement

Red blood cells (RBC), the primary carriers of oxygen in the body, play a crucial role across several biomedical applications, while also being an essential model system of a deformable object in the microfluidics and soft matter fields. However, RBC behavior in viscoelastic liquids, which holds promise in enhancing microfluidic diagnostic applications, remains poorly studied. We here show that using viscoelastic polymer solutions as a suspending carrier causes changes in the clustering and shape of flowing RBC in microfluidic flows when compared to a standard Newtonian suspending liquid. Additionally, when the local RBC concentration increases to a point where hydrodynamic interactions take place, we observe the formation of equally-spaced RBC structures, resembling the viscoelasticity-driven ordered particles observed previously in the literature, thus providing the first experimental evidence of viscoelasticity-driven cell ordering. The observed RBC ordering, unaffected by polymer molecular architecture, persists as long as the surrounding medium exhibits shear-thinning, viscoelastic properties. Complementary numerical simulations reveal that viscoelasticity-induced repulsion between RBCs leads to equidistant structures, with shear-thinning modulating this effect. Our results open the way for the development of new biomedical technologies based on the use of viscoelastic liquids while also clarifying fundamental aspects related to multibody hydrodynamic interactions in viscoelastic microfluidic flows.

Information-Distilled Generative Label-Free Morphological Profiling Encodes Cellular Heterogeneity

Image-based cytometry faces challenges due to technical variations arising from different experimental batches and conditions, such as differences in instrument configurations or image acquisition protocols, impeding genuine biological interpretation of cell morphology. Existing solutions, often necessitating extensive pre-existing data knowledge or control samples across batches, have proved limited, especially with complex cell image data. To overcome this, "Cyto-Morphology Adversarial Distillation" (CytoMAD), a self-supervised multi-task learning strategy that distills biologically relevant cellular morphological information from batch variations, is introduced to enable integrated analysis across multiple data batches without complex data assumptions or extensive manual annotation. Unique to CytoMAD is its "morphology distillation", symbiotically paired with deep-learning image-contrast translation-offering additional interpretable insights into label-free cell morphology. The versatile efficacy of CytoMAD is demonstrated in augmenting the power of biophysical imaging cytometry. It allows integrated label-free classification of human lung cancer cell types and accurately recapitulates their progressive drug responses, even when trained without the drug concentration information. CytoMAD  also allows joint analysis of tumor biophysical cellular heterogeneity, linked to epithelial-mesenchymal plasticity, that standard fluorescence markers overlook. CytoMAD can substantiate the wide adoption of biophysical cytometry for cost-effective diagnosis and screening.

Imaging Flow Cytometry and Convolutional Neural Network-Based Classification Enable Discrimination of Hematopoietic and Leukemic Stem Cells in Acute Myeloid Leukemia

Acute myeloid leukemia (AML) is a heterogenous blood cancer with a dismal prognosis. It emanates from leukemic stem cells (LSCs) arising from the genetic transformation of hematopoietic stem cells (HSCs). LSCs hold prognostic value, but their molecular and immunophenotypic heterogeneity poses challenges: there is no single marker for identifying all LSCs across AML samples. We hypothesized that imaging flow cytometry (IFC) paired with artificial intelligence-driven image analysis could visually distinguish LSCs from HSCs based solely on morphology. Initially, a seven-color IFC panel was employed to immunophenotypically identify LSCs and HSCs in bone marrow samples from five AML patients and ten healthy donors, respectively. Next, we developed convolutional neural network (CNN) models for HSC-LSC discrimination using brightfield (BF), side scatter (SSC), and DNA images. Classification using only BF images achieved 86.96% accuracy, indicating significant morphological differences. Accuracy increased to 93.42% when combining BF with DNA images, highlighting differences in nuclear morphology, although DNA images alone were inadequate for accurate HSC-LSC discrimination. Model development using SSC images revealed minor granularity differences. Performance metrics varied substantially between AML patients, indicating considerable morphologic variations among LSCs. Overall, we demonstrate proof-of-concept results for accurate CNN-based HSC-LSC differentiation, instigating the development of a novel technique within AML monitoring.

Comparative analysis of feature-based ML and CNN for binucleated erythroblast quantification in myelodysplastic syndrome patients using imaging flow cytometry data

Myelodysplastic syndrome is primarily characterized by dysplasia in the bone marrow (BM), presenting a challenge in consistent morphology interpretation. Accurate diagnosis through traditional slide-based analysis is difficult, necessitating a standardized objective technique. Over the past two decades, imaging flow cytometry (IFC) has proven effective in combining image-based morphometric analyses with high-parameter phenotyping. We have previously demonstrated the effectiveness of combining IFC with a feature-based machine learning algorithm to accurately identify and quantify rare binucleated erythroblasts (BNEs) in dyserythropoietic BM cells. However, a feature-based workflow poses challenges requiring software-specific expertise. Here we employ a Convolutional Neural Network (CNN) algorithm for BNE identification and differentiation from doublets and cells with irregular nuclear morphology in IFC data. We demonstrate that this simplified AI workflow, coupled with a powerful CNN algorithm, achieves comparable BNE quantification accuracy to manual and feature-based analysis with substantial time savings, eliminating workflow complexity. This streamlined approach holds significant clinical value, enhancing IFC accessibility for routine diagnostic purposes.

Deductive automated pollen classification in environmental samples via exploratory deep learning and imaging flow cytometry

Pollen and tracheophyte spores are ubiquitous environmental indicators at local and global scales. Palynology is typically performed manually by microscopic analysis; a specialised and time-consuming task limited in taxonomical precision and sampling frequency, therefore restricting data quality used to inform climate change and pollen forecasting models. We build on the growing work using AI (artificial intelligence) for automated pollen classification to design a flexible network that can deal with the uncertainty of broad-scale environmental applications. We combined imaging flow cytometry with Guided Deep Learning to identify and accurately categorise pollen in environmental samples; here, pollen grains captured within c. 5500 Cal yr BP old lake sediments. Our network discriminates not only pollen included in training libraries to the species level but, depending on the sample, can classify previously unseen pollen to the likely phylogenetic order, family and even genus. Our approach offers valuable insights into the development of a widely transferable, rapid and accurate exploratory tool for pollen classification in 'real-world' environmental samples with improved accuracy over pure deep learning techniques. This work has the potential to revolutionise many aspects of palynology, allowing a more detailed spatial and temporal understanding of pollen in the environment with improved taxonomical resolution.

DeepIFC: Virtual fluorescent labeling of blood cells in imaging flow cytometry data with deep learning

Imaging flow cytometry (IFC) combines flow cytometry with microscopy, allowing rapid characterization of cellular and molecular properties via high-throughput single-cell fluorescent imaging. However, fluorescent labeling is costly and time-consuming. We present a computational method called DeepIFC based on the Inception U-Net neural network architecture, able to generate fluorescent marker images and learn morphological features from IFC brightfield and darkfield images. Furthermore, the DeepIFC workflow identifies cell types from the generated fluorescent images and visualizes the single-cell features generated in a 2D space. We demonstrate that rarer cell types are predicted well when a balanced data set is used to train the model, and the model is able to recognize red blood cells not seen during model training as a distinct entity. In summary, DeepIFC allows accurate cell reconstruction, typing and recognition of unseen cell types from brightfield and darkfield images via virtual fluorescent labeling.

Computer vision quantitation of erythrocyte shape abnormalities provides diagnostic, prognostic, and mechanistic insight

Examination of red blood cell (RBC) morphology in peripheral blood smears can help diagnose hematologic diseases, even in resource-limited settings, but this analysis remains subjective and semiquantitative with low throughput. Prior attempts to develop automated tools have been hampered by their poor reproducibility and limited clinical validation. Here, we present a novel, open-source machine-learning approach (denoted as RBC-diff) to quantify abnormal RBCs in peripheral smear images and generate an RBC morphology differential. RBC-diff cell counts showed high accuracy for single-cell classification (mean AUC, 0.93) and quantitation across smears (mean R2, 0.76 compared with experts, interexperts R2, 0.75). RBC-diff counts were concordant with the clinical morphology grading for 300 000+ images and recovered the expected pathophysiologic signals in diverse clinical cohorts. Criteria using RBC-diff counts distinguished thrombotic thrombocytopenic purpura and hemolytic uremic syndrome from other thrombotic microangiopathies, providing greater specificity than clinical morphology grading (72% vs 41%; P < .001) while maintaining high sensitivity (94% to 100%). Elevated RBC-diff schistocyte counts were associated with increased 6-month all-cause mortality in a cohort of 58 950 inpatients (9.5% mortality for schist. >1%, vs 4.7% for schist; <0.5%; P < .001) after controlling for comorbidities, demographics, clinical morphology grading, and blood count indices. RBC-diff also enabled the estimation of single-cell volume-morphology distributions, providing insight into the influence of morphology on routine blood count measures. Our codebase and expert-annotated images are included here to spur further advancement. These results illustrate that computer vision can enable rapid and accurate quantitation of RBC morphology, which may provide value in both clinical and research contexts.

Assessment of stored red blood cells through lab-on-a-chip technologies for precision transfusion medicine

Transfusion of red blood cells (RBCs) is one of the most valuable and widespread treatments in modern medicine. Lifesaving RBC transfusions are facilitated by the cold storage of RBC units in blood banks worldwide. Currently, RBC storage and subsequent transfusion practices are performed using simplistic workflows. More specifically, most blood banks follow the "first-in-first-out" principle to avoid wastage, whereas most healthcare providers prefer the "last-in-first-out" approach simply favoring chronologically younger RBCs. Neither approach addresses recent advances through -omics showing that stored RBC quality is highly variable depending on donor-, time-, and processing-specific factors. Thus, it is time to rethink our workflows in transfusion medicine taking advantage of novel technologies to perform RBC quality assessment. We imagine a future where lab-on-a-chip technologies utilize novel predictive markers of RBC quality identified by -omics and machine learning to usher in a new era of safer and precise transfusion medicine.

Label-Free Digital Holotomography Reveals Ibuprofen-Induced Morphological Changes to Red Blood Cells

Understanding the dose-dependent effect of over-the-counter drugs on red blood cells (RBCs) is crucial for hematology and digital pathology. Yet, it is challenging to continuously record the real-time, drug-induced shape changes of RBCs in a label-free manner. Here, we demonstrate digital holotomography (DHTM)-enabled real-time, label-free concentration-dependent and time-dependent monitoring of ibuprofen on RBCs from a healthy donor. The RBCs are segmented based on three-dimensional (3D) and four-dimensional (4D) refractive index tomograms, and their morphological and chemical parameters are retrieved with their shapes classified using machine learning. We directly observed the formation and motion of spicules on the RBC membrane when aqueous solutions of ibuprofen were drop-cast on wet blood, creating rough-membraned echinocyte forms. At low concentrations of 0.25-0.50 mM, the ibuprofen-induced morphological change was transient, but at high concentrations (1-3 mM) the spiculated RBC remained over a period of up to 1.5 h. Molecular simulations confirmed that aggregates of ibuprofen molecules at high concentrations significantly disrupted the RBC membrane structural integrity and lipid order but produced negligible effect at low ibuprofen concentrations. Control experiments on the effect of urea, hydrogen peroxide, and aqueous solutions on RBCs showed zero spicule formation. Our work clarifies the dose-dependent chemical effects on RBCs using label-free microscopes that can be deployed for the rapid detection of overdosage of over-the-counter and prescribed drugs.

Red Blood Cell Omics and Machine Learning in Transfusion Medicine: Singularity Is Near

Background

Blood transfusion is a life-saving intervention for millions of recipients worldwide. Over the last 15 years, the advent of high-throughput, affordable omics technologies - including genomics, proteomics, lipidomics, and metabolomics - has allowed transfusion medicine to revisit the biology of blood donors, stored blood products, and transfusion recipients.

Summary

Omics approaches have shed light on the genetic and non-genetic factors (environmental or other exposures) impacting the quality of stored blood products and efficacy of transfusion events, based on the current Food and Drug Administration guidelines (e.g., hemolysis and post-transfusion recovery for stored red blood cells). As a treasure trove of data accumulates, the implementation of machine learning approaches promises to revolutionize the field of transfusion medicine, not only by advancing basic science. Indeed, computational strategies have already been used to perform high-content screenings of red blood cell morphology in microfluidic devices, generate in silico models of erythrocyte membrane to predict deformability and bending rigidity, or design systems biology maps of the red blood cell metabolome to drive the development of novel storage additives.

Key Message

In the near future, high-throughput testing of donor genomes via precision transfusion medicine arrays and metabolomics of all donated products will be able to inform the development and implementation of machine learning strategies that match, from vein to vein, donors, optimal processing strategies (additives, shelf life), and recipients, realizing the promise of personalized transfusion medicine.

Blood quality evaluation via on-chip classification of cell morphology using a deep learning algorithm

The quality of red blood cells (RBCs) in stored blood has a direct impact on the recovery of patients treated by blood transfusion, which directly reflects the quality of blood. The traditional means for blood quality evaluation involve the use of reagents and multi-step and time-consuming operations. Here, a low-cost, multi-classification, label-free and high-precision method is developed, which combines microfluidic technology and a deep learning algorithm together to recognize and classify RBCs based on morphology. The microfluidic channel is designed to effectively and controllably solve the problem of cell overlap, which has a severe negative impact on the identification of cells. The object detection model in the deep learning algorithm is optimized and used to recognize multiple RBCs simultaneously in the whole field of view, so as to classify them into six morphological subcategories and count the numbers in each subgroup. The mean average precision of the developed object detection model reaches 89.24%. The blood quality can be evaluated by calculating the morphology index (MI) according to the numbers of cells in subgroups. The validation of the method is verified by evaluating three blood samples stored for 7 days, 21 days and 42 days, which have MIs of 84.53%, 73.33% and 24.34%, respectively, indicating good agreement with the actual blood quality. This method has the merits of cell identification in a wide channel, no need for single cell alignment as the image cytometry does and it is not only applicable to the quality evaluation of RBCs, but can also be used for general cell identifications with different morphologies.

Artificial intelligence-assisted smartphone-based sensing for bioanalytical applications: A review

Artificial intelligence (AI) has received great attention since the concept was proposed, and it has developed rapidly in recent years with applications in many fields. Meanwhile, newer iterations of smartphone hardware technologies which have excellent data processing capabilities have leveraged on AI capabilities. Based on the desirability for portable detection, researchers have been investigating intelligent analysis by combining smartphones with AI algorithms. Various examples of the application of AI algorithm-based smartphone detection and analysis have been developed. In this review, we give an overview of this field, with a particular focus on bioanalytical detection applications. The applications are presented in terms of hardware design, software algorithms, and specific application areas. We also discuss the existing limitations of AI-based smartphone detection and analytical approaches, and their future prospects. The take-home message of our review is that the application of AI in the field of detection analysis is restricted by the limitations of the smartphone's hardware as well as the model building of AI for detection targets with insufficient data. Nevertheless, at this juncture, while bioanalytical diagnostics and health monitoring have set the pace for AI-based smartphone applicability, the future should see the technology making greater inroads into other fields. In relation to the latter, it is likely that the ordinary or average person will play a greater participatory role.

Optofluidic imaging meets deep learning: from merging to emerging

Propelled by the striking advances in optical microscopy and deep learning (DL), the role of imaging in lab-on-a-chip has dramatically been transformed from a silo inspection tool to a quantitative "smart" engine. A suite of advanced optical microscopes now enables imaging over a range of spatial scales (from molecules to organisms) and temporal window (from microseconds to hours). On the other hand, the staggering diversity of DL algorithms has revolutionized image processing and analysis at the scale and complexity that were once inconceivable. Recognizing these exciting but overwhelming developments, we provide a timely review of their latest trends in the context of lab-on-a-chip imaging, or coined optofluidic imaging. More importantly, here we discuss the strengths and caveats of how to adopt, reinvent, and integrate these imaging techniques and DL algorithms in order to tailor different lab-on-a-chip applications. In particular, we highlight three areas where the latest advances in lab-on-a-chip imaging and DL can form unique synergisms: image formation, image analytics and intelligent image-guided autonomous lab-on-a-chip. Despite the on-going challenges, we anticipate that they will represent the next frontiers in lab-on-a-chip imaging that will spearhead new capabilities in advancing analytical chemistry research, accelerating biological discovery, and empowering new intelligent clinical applications.

MorphoFeatures for unsupervised exploration of cell types, tissues, and organs in volume electron microscopy

Electron microscopy (EM) provides a uniquely detailed view of cellular morphology, including organelles and fine subcellular ultrastructure. While the acquisition and (semi-)automatic segmentation of multicellular EM volumes are now becoming routine, large-scale analysis remains severely limited by the lack of generally applicable pipelines for automatic extraction of comprehensive morphological descriptors. Here, we present a novel unsupervised method for learning cellular morphology features directly from 3D EM data: a neural network delivers a representation of cells by shape and ultrastructure. Applied to the full volume of an entire three-segmented worm of the annelid Platynereis dumerilii, it yields a visually consistent grouping of cells supported by specific gene expression profiles. Integration of features across spatial neighbours can retrieve tissues and organs, revealing, for example, a detailed organisation of the animal foregut. We envision that the unbiased nature of the proposed morphological descriptors will enable rapid exploration of very different biological questions in large EM volumes, greatly increasing the impact of these invaluable, but costly resources.

Predicting willingness to donate blood based on machine learning: two blood donor recruitments during COVID-19 outbreaks

Machine learning methods are a novel way to predict and rank donors' willingness to donate blood and to achieve precision recruitment, which can improve the recruitment efficiency and meet the challenge of blood shortage. We collected information about experienced blood donors via short message service (SMS) recruitment and developed 7 machine learning-based recruitment models using PyCharm-Python Environment and 13 features which were described as a method for ranking and predicting donors' intentions to donate blood with a floating number between 0 and 1. Performance of the prediction models was assessed by the Area under the receiver operating characteristic curve (AUC), accuracy, precision, recall, and F1 score in the full dataset, and by the accuracy in the four sub-datasets. The developed models were applied to prospective validations of recruiting experienced blood donors during two COVID-19 pandemics, while the routine method was used as a control. Overall, a total of 95,476 recruitments via SMS and their donation results were enrolled in our modelling study. The strongest predictor features for the donation of experienced donors were blood donation interval, age, and donation frequency. Among the seven baseline models, the eXtreme Gradient Boosting (XGBoost) and Support vector machine models (SVM) achieved the best performance: mean (95%CI) with the highest AUC: 0.809 (0.806-0.811), accuracy: 0.815 (0.812-0.818), precision: 0.840 (0.835-0.845), and F1 score of XGBoost: 0.843 (0.840-0.845) and recall of SVM: 0.991 (0.988-0.994). The hit rate of the XGBoost model alone and the combined XGBoost and SVM models were 1.25 and 1.80 times higher than that of the conventional method as a control in 2 recruitments respectively, and the hit rate of the high willingness to donate group was 1.96 times higher than that of the low willingness to donate group. Our results suggested that the machine learning models could predict and determine the experienced donors with a strong willingness to donate blood by a ranking score based on personalized donation data and demographical details, significantly improve the recruitment rate of blood donors and help blood agencies to maintain the blood supply in emergencies.

Data augmentation with improved regularisation and sampling for imbalanced blood cell image classification

Due to progression in cell-cycle or duration of storage, classification of morphological changes in human blood cells is important for correct and effective clinical decisions. Automated classification systems help avoid subjective outcomes and are more efficient. Deep learning and more specifically Convolutional Neural Networks have achieved state-of-the-art performance on various biomedical image classification problems. However, real-world data often suffers from the data imbalance problem, owing to which the trained classifier is biased towards the majority classes and does not perform well on the minority classes. This study presents an imbalanced blood cells classification method that utilises Wasserstein divergence GAN, mixup and novel nonlinear mixup for data augmentation to achieve oversampling of the minority classes. We also present a minority class focussed sampling strategy, which allows effective representation of minority class samples produced by all three data augmentation techniques and contributes to the classification performance. The method was evaluated on two publicly available datasets of immortalised human T-lymphocyte cells and Red Blood Cells. Classification performance evaluated using F1-score shows that our proposed approach outperforms existing methods on the same datasets.

Dimensionality reduction by UMAP for visualizing and aiding in classification of imaging flow cytometry data

Recent advances in imaging flow cytometry (IFC) have revolutionized high-throughput multiparameter analyses at single-cell resolution. Although enabling the discovery of population heterogeneities and the detection of rare events, IFC generates hyperdimensional datasets that demand innovative analytical approaches. Current methods work in a supervised manner, utilize only limited information content, or require large annotated reference datasets. Dimensionality reduction algorithms, including uniform manifold approximation and projection (UMAP), have been successfully applied to analyze the large number of parameters generated in various high-throughput techniques.

Here, we apply a workflow incorporating UMAP to analyze different IFC datasets. We demonstrate that it out-competes other popular dimensionality reduction methods in speed and accuracy. Moreover, it enables fast visualization, clustering, and tagging of unannotated objects in large-scale experiments. We anticipate that our workflow will be a robust method to address complex IFC datasets, either alone or as an upstream addition to the deep learning approaches.

•

UMAP dimensionality reduction provides fast and accurate method of IFC data analysis

•

UMAP yields improved object clustering and tagging of the multispectral IFC data

•

PCA decomposition allows multispectral signals merging for direct image embedding

Combining imaging flow cytometry and machine learning for high-throughput schistocyte quantification: A SVM classifier development and external validation cohort

Background

Schistocyte counts are a cornerstone of the diagnosis of thrombotic microangiopathy syndrome (TMA). Their manual quantification is complex and alternative automated methods suffer from pitfalls that limit their use. We report a method combining imaging flow cytometry (IFC) and artificial intelligence for the direct label-free and operator-independent quantification of schistocytes in whole blood.

Methods

We used 135,045 IFC images from blood acquisition among 14 patients to extract 188 features with IDEAS® software and 128 features from a convolutional neural network (CNN) with Keras framework in order to train a support vector machine (SVM) blood elements’ classifier used for schistocytes quantification.

Finding

Keras features showed better accuracy (94.03%, CI: 93.75-94.31%) than ideas features (91.54%, CI: 91.21-91.87%) in recognising whole-blood elements, and together they showed the best accuracy (95.64%, CI: 95.39-95.88%). We obtained an excellent correlation (0.93, CI: 0.90-0.96) between three haematologists and our method on a cohort of 102 patient samples. All patients with schistocytosis (>1% schistocytes) were detected with excellent specificity (91.3%, CI: 82.0-96.7%) and sensitivity (100%, CI: 89.4-100.0%). We confirmed these results with a similar specificity (91.1%, CI: 78.8-97.5%) and sensitivity (100%, CI: 88.1-100.0%) on a validation cohort (n=74) analysed in an independent healthcare centre. Simultaneous analysis of 16 samples in both study centres showed a very good correlation between the 2 imaging flow cytometers (Y=1.001x).

Interpretation

We demonstrate that IFC can represent a reliable tool for operator-independent schistocyte quantification with no pre-analytical processing which is of most importance in emergency situations such as TMA.

Funding

None.

Erysense, a Lab-on-a-Chip-Based Point-of-Care Device to Evaluate Red Blood Cell Flow Properties With Multiple Clinical Applications

In many medical disciplines, red blood cells are discovered to be biomarkers since they "experience" various conditions in basically all organs of the body. Classical examples are diabetes and hypercholesterolemia. However, recently the red blood cell distribution width (RDW), is often referred to, as an unspecific parameter/marker (e.g., for cardiac events or in oncological studies). The measurement of RDW requires venous blood samples to perform the complete blood cell count (CBC). Here, we introduce Erysense, a lab-on-a-chip-based point-of-care device, to evaluate red blood cell flow properties. The capillary chip technology in combination with algorithms based on artificial neural networks allows the detection of very subtle changes in the red blood cell morphology. This flow-based method closely resembles in vivo conditions and blood sample volumes in the sub-microliter range are sufficient. We provide clinical examples for potential applications of Erysense as a diagnostic tool [here: neuroacanthocytosis syndromes (NAS)] and as cellular quality control for red blood cells [here: hemodiafiltration (HDF) and erythrocyte concentrate (EC) storage]. Due to the wide range of the applicable flow velocities (0.1-10 mm/s) different mechanical properties of the red blood cells can be addressed with Erysense providing the opportunity for differential diagnosis/judgments. Due to these versatile properties, we anticipate the value of Erysense for further diagnostic, prognostic, and theragnostic applications including but not limited to diabetes, iron deficiency, COVID-19, rheumatism, various red blood cell disorders and anemia, as well as inflammation-based diseases including sepsis.

Technologies for measuring red blood cell deformability

Human red blood cells (RBCs) are approximately 8 μm in diameter, but must repeatedly deform through capillaries as small as 2 μm in order to deliver oxygen to all parts of the body. The loss of this capability is associated with the pathology of many diseases, and is therefore a potential biomarker for disease status and treatment efficacy. Measuring RBC deformability is a difficult problem because of the minute forces (∼pN) that must be exerted on these cells, as well as the requirements for throughput and multiplexing. The development of technologies for measuring RBC deformability date back to the 1960s with the development of micropipette aspiration, ektacytometry, and the cell transit analyzer. In the past 10 years, significant progress has been made using microfluidics by leveraging the ability to precisely control fluid flow through microstructures at the size scale of individual RBCs. These technologies have now surpassed traditional methods in terms of sensitivity, throughput, consistency, and ease of use. As a result, these efforts are beginning to move beyond feasibility studies and into applications to enable biomedical discoveries. In this review, we provide an overview of both traditional and microfluidic techniques for measuring RBC deformability. We discuss the capabilities of each technique and compare their sensitivity, throughput, and robustness in measuring bulk and single-cell RBC deformability. Finally, we discuss how these tools could be used to measure changes in RBC deformability in the context of various applications including pathologies caused by malaria and hemoglobinopathies, as well as degradation during storage in blood bags prior to blood transfusions.

Storage-Induced Micro-Erythrocytes Can Be Quantified and Sorted by Flow Cytometry

Refrigerated storage of red cell concentrates before transfusion is associated with progressive alterations of red blood cells (RBC). Small RBC (type III echinocytes, sphero-echinocytes, and spherocytes) defined as storage-induced micro-erythrocytes (SME) appear during pretransfusion storage. SME accumulate with variable intensity from donor to donor, are cleared rapidly after transfusion, and their proportion correlates with transfusion recovery. They can be rapidly and objectively quantified using imaging flow cytometry (IFC). Quantifying SME using flow cytometry would further facilitate a physiologically relevant quality control of red cell concentrates. RBC stored in blood bank conditions were stained with a carboxyfluorescein succinimidyl ester (CFSE) dye and incubated at 37°C. CFSE intensity was assessed by flow cytometry and RBC morphology evaluated by IFC. We observed the accumulation of a CFSE ^high RBC subpopulation by flow cytometry that accounted for 3.3 and 47.2% at day 3 and 42 of storage, respectively. IFC brightfield images showed that this CFSE ^high subpopulation mostly contains SME while the CFSE ^low subpopulation mostly contains type I and II echinocytes and discocytes. Similar numbers of SME were quantified by IFC (based on projected surface area) and by flow cytometry (based on CFSE intensity). IFC and scanning electron microscopy showed that ≥95% pure subpopulations of CFSE ^high and CFSE ^low RBC were obtained by flow cytometry-based sorting. SME can now be quantified using a common fluorescent dye and a standard flow cytometer. The staining protocol enables specific sorting of SME, a useful tool to further characterize this RBC subpopulation targeted for premature clearance after transfusion.

Assessing red blood cell deformability from microscopy images using deep learning

Red blood cells (RBCs) must be highly deformable to transit through the microvasculature to deliver oxygen to tissues. The loss of RBC deformability resulting from pathology, natural aging, or storage in blood bags can impede the proper function of these cells. A variety of methods have been developed to measure RBC deformability, but these methods require specialized equipment, long measurement time, and highly skilled personnel. To address this challenge, we investigated whether a machine learning approach could be used to predict donor RBC deformability based on morphological features from single cell microscope images. We used the microfluidic ratchet device to sort RBCs based on deformability. Sorted cells are then imaged and used to train a deep learning model to classify RBC based image features related to cell deformability. This model correctly predicted deformability of individual RBCs with 81 ± 11% accuracy averaged across ten donors. Using this model to score the deformability of RBC samples was accurate to within 10.4 ± 6.8% of the value obtained using the microfluidic ratchet device. While machine learning methods are frequently developed to automate human image analysis, our study is remarkable in showing that deep learning of single cell microscopy images could be used to assess RBC deformability, a property not normally measurable by imaging. Measuring RBC deformability by imaging is also desirable because it can be performed rapidly using a standard microscopy system, potentially enabling RBC deformability studies to be performed as part of routine clinical assessments.

Highly accurate differentiation of bone marrow cell morphologies using deep neural networks on a large image data set

A data set of >170 000 microscopic images allows training neural networks for identification of BM cells with high accuracy.

Neural networks outperform a feature-based approach to BM cell classification and can be analyzed with explainability and feature embedding methods.

Biomedical applications of deep learning algorithms rely on large expert annotated data sets. The classification of bone marrow (BM) cell cytomorphology, an important cornerstone of hematological diagnosis, is still done manually thousands of times every day because of a lack of data sets and trained models. We applied convolutional neural networks (CNNs) to a large data set of 171 374 microscopic cytological images taken from BM smears from 945 patients diagnosed with a variety of hematological diseases. The data set is the largest expert-annotated pool of BM cytology images available in the literature. It allows us to train high-quality classifiers of leukocyte cytomorphology that identify a wide range of diagnostically relevant cell species with high precision and recall. Our CNNs outcompete previous feature-based approaches and provide a proof-of-concept for the classification problem of single BM cells. This study is a step toward automated evaluation of BM cell morphology using state-of-the-art image-classification algorithms. The underlying data set represents an educational resource, as well as a reference for future artificial intelligence–based approaches to BM cytomorphology.

Imaging flow cytometry data analysis using convolutional neural network for quantitative investigation of phagocytosis

Macrophages play an important role in the adaptive immune system. Their ability to neutralize cellular targets through Fc receptor-mediated phagocytosis has relied upon immunotherapy that has become of particular interest for the treatment of cancer and autoimmune diseases. A detailed investigation of phagocytosis is the key to the improvement of the therapeutic efficiency of existing medications and the creation of new ones. A promising method for studying the process is imaging flow cytometry (IFC) that acquires thousands of cell images per second in up to 12 optical channels and allows multiparametric fluorescent and morphological analysis of samples in the flow. However, conventional IFC data analysis approaches are based on a highly subjective manual choice of masks and other processing parameters that can lead to the loss of valuable information embedded in the original image. Here, we show the application of a Faster region-based convolutional neural network (CNN) for accurate quantitative analysis of phagocytosis using imaging flow cytometry data. Phagocytosis of erythrocytes by peritoneal macrophages was chosen as a model system. CNN performed automatic high-throughput processing of datasets and demonstrated impressive results in the identification and classification of macrophages and erythrocytes, despite the variety of shapes, sizes, intensities, and textures of cells in images. The developed procedure allows determining the number of phagocytosed cells, disregarding cases with a low probability of correct classification. We believe that CNN-based approaches will enable powerful in-depth investigation of a wide range of biological processes and will reveal the intricate nature of heterogeneous objects in images, leading to completely new capabilities in diagnostics and therapy.

Practical machine learning for disease diagnosis

Deep learning neural networks are a powerful tool in the analytical toolbox of modern microscopy, but they come with an exacting requirement for accurately annotated, ground truth cell images. Otesteanu et al. (2021) elegantly streamline this process, implementing network training by using patient-level rather than cell-level disease classification.

A weakly supervised deep learning approach for label-free imaging flow-cytometry-based blood diagnostics

The application of machine learning approaches to imaging flow cytometry (IFC) data has the potential to transform the diagnosis of hematological diseases. However, the need for manually labeled single-cell images for machine learning model training has severely limited its clinical application. To address this, we present iCellCnn, a weakly supervised deep learning approach for label-free IFC-based blood diagnostics. We demonstrate the capability of iCellCnn to achieve diagnosis of Sézary syndrome (SS) from patient samples on the basis of bright-field IFC images of T cells obtained after fluorescence-activated cell sorting of human peripheral blood mononuclear cell specimens. With a sample size of four healthy donors and five SS patients, iCellCnn achieved a 100% classification accuracy. As iCellCnn is not restricted to the diagnosis of SS, we expect such weakly supervised approaches to tap the diagnostic potential of IFC by providing automatic data-driven diagnosis of diseases with so-far unknown morphological manifestations.

Deep learning for bioimage analysis in developmental biology

Deep learning has transformed the way large and complex image datasets can be processed, reshaping what is possible in bioimage analysis. As the complexity and size of bioimage data continues to grow, this new analysis paradigm is becoming increasingly ubiquitous. In this Review, we begin by introducing the concepts needed for beginners to understand deep learning. We then review how deep learning has impacted bioimage analysis and explore the open-source resources available to integrate it into a research project. Finally, we discuss the future of deep learning applied to cell and developmental biology. We analyze how state-of-the-art methodologies have the potential to transform our understanding of biological systems through new image-based analysis and modelling that integrate multimodal inputs in space and time.

CellProfiler Analyst 3.0: Accessible data exploration and machine learning for image analysis

 

Image-based experiments can yield many thousands of individual measurements describing each object of interest, such as cells in microscopy screens. CellProfiler Analyst is a free, open-source software package designed for the exploration of quantitative image-derived data and the training of machine learning classifiers with an intuitive user interface. We have now released CellProfiler Analyst 3.0, which in addition to enhanced performance adds support for neural network classifiers, identifying rare object subsets, and direct transfer of objects of interest from visualisation tools into the Classifier tool for use as training data. This release also increases interoperability with the recently released CellProfiler 4, making it easier for users to detect and measure particular classes of objects in their analyses.

AVAILABILITY

CellProfiler Analyst binaries for Windows and MacOS are freely available for download at https://cellprofileranalyst.org/. Source code is implemented in Python 3 and is available at https://github.com/CellProfiler/CellProfiler-Analyst/. A sample data set is available at https://cellprofileranalyst.org/examples, based on images freely available from the Broad Bioimage Benchmark Collection (BBBC).

Deep Learning-based Phenotypic Assessment of Red Cell Storage Lesions for Safe Transfusions

This study presents a novel approach to automatically perform instant phenotypic assessment of red blood cell (RBC) storage lesion in phase images obtained by digital holographic microscopy. The proposed model combines a generative adversarial network (GAN) with marker-controlled watershed segmentation scheme. The GAN model performed RBC segmentations and classifications to develop ageing markers, and the watershed segmentation was used to completely separate overlapping RBCs. Our approach achieved good segmentation and classification accuracy with a Dices coefficient of 0.94 at a high throughput rate of about 152 cells per second. These results were compared with other deep neural network architectures. Moreover, our image-based deep learning models recognized the morphological changes that occur in RBCs during storage. Our deep learning-based classification results were in good agreement with previous findings on the changes in RBC markers (dominant shapes) affected by storage duration. We believe that our image-based deep learning models can be useful for automated assessment of RBC quality, storage lesions for safe transfusions, and diagnosis of RBC-related diseases.

Deepometry, a framework for applying supervised and weakly supervised deep learning to imaging cytometry

Deep learning offers the potential to extract more than meets the eye from images captured by imaging flow cytometry. This protocol describes the application of deep learning to single-cell images to perform supervised cell classification and weakly supervised learning, using example data from an experiment exploring red blood cell morphology. We describe how to acquire and transform suitable input data as well as the steps required for deep learning training and inference using an open-source web-based application. All steps of the protocol are provided as open-source Python as well as MATLAB runtime scripts, through both command-line and graphic user interfaces. The protocol enables a flexible and friendly environment for morphological phenotyping using supervised and weakly supervised learning and the subsequent exploration of the deep learning features using multi-dimensional visualization tools. The protocol requires 40 h when training from scratch and 1 h when using a pre-trained model.

An image-based flow cytometric approach to the assessment of the nucleus-to-cytoplasm ratio

The nucleus-to-cytoplasm ratio (N:C) can be used as one metric in histology for grading certain types of tumor malignancy. Current N:C assessment techniques are time-consuming and low throughput. Thus, in high-throughput clinical contexts, there is a need for a technique that can assess cell malignancy rapidly. In this study, we assess the N:C ratio of four different malignant cell lines (OCI-AML-5-blood cancer, CAKI-2-kidney cancer, HT-29-colon cancer, SK-BR-3-breast cancer) and a non-malignant cell line (MCF-10A -breast epithelium) using an imaging flow cytometer (IFC). Cells were stained with the DRAQ-5 nuclear dye to stain the cell nucleus. An Amnis ImageStreamX® IFC acquired brightfield/fluorescence images of cells and their nuclei, respectively. Masking and gating techniques were used to obtain the cell and nucleus diameters for 5284 OCI-AML-5 cells, 1096 CAKI-2 cells, 6302 HT-29 cells, 3159 SK-BR-3 cells, and 1109 MCF-10A cells. The N:C ratio was calculated as the ratio of the nucleus diameter to the total cell diameter. The average cell and nucleus diameters from IFC were 12.3 ± 1.2 μm and 9.0 ± 1.1 μm for OCI-AML5 cells, 24.5 ± 2.6 μm and 15.6 ± 2.1 μm for CAKI-2 cells, 16.2 ± 1.8 μm and 11.2 ± 1.3 μm for HT-29 cells, 18.0 ± 3.7 μm and 12.5 ± 2.1 μm for SK-BR-3 cells, and 19.4 ± 2.2 μm and 10.1 ± 1.8 μm for MCF-10A cells. Here we show a general N:C ratio of ~0.6-0.7 across varying malignant cell lines and a N:C ratio of ~0.5 for a non-malignant cell line. This study demonstrates the use of IFC to assess the N:C ratio of cancerous and non-cancerous cells, and the promise of its use in clinically relevant high-throughput detection scenarios to supplement current workflows used for cancer cell grading.

Image-based cell phenotyping with deep learning

A cell's phenotype is the culmination of several cellular processes through a complex network of molecular interactions that ultimately result in a unique morphological signature. Visual cell phenotyping is the characterization and quantification of these observable cellular traits in images. Recently, cellular phenotyping has undergone a massive overhaul in terms of scale, resolution, and throughput, which is attributable to advances across electronic, optical, and chemical technologies for imaging cells. Coupled with the rapid acceleration of deep learning-based computational tools, these advances have opened up new avenues for innovation across a wide variety of high-throughput cell biology applications. Here, we review applications wherein deep learning is powering the recognition, profiling, and prediction of visual phenotypes to answer important biological questions. As the complexity and scale of imaging assays increase, deep learning offers computational solutions to elucidate the details of previously unexplored cellular phenotypes.

Image- and Fluorescence-Based Test Shows Oxidant-Dependent Damages in Red Blood Cells and Enables Screening of Potential Protective Molecules

An increase of oxygen saturation within blood bags and metabolic dysregulation occur during storage of red blood cells (RBCs). It leads to the gradual exhaustion of RBC antioxidant protective system and, consequently, to a deleterious state of oxidative stress that plays a major role in the apparition of the so-called storage lesions. The present study describes the use of a test (called TSOX) based on fluorescence and label-free morphology readouts to simply and quickly evaluate the oxidant and antioxidant properties of various compounds in controlled conditions. Here, TSOX was applied to RBCs treated with four antioxidants (ascorbic acid, uric acid, trolox and resveratrol) and three oxidants (AAPH, diamide and H₂O₂) at different concentrations. Two complementary readouts were chosen: first, where ROS generation was quantified using DCFH-DA fluorescent probe, and second, based on digital holographic microscopy that measures morphology alterations. All oxidants produced an increase of fluorescence, whereas H₂O₂ did not visibly impact the RBC morphology. Significant protection was observed in three out of four of the added molecules. Of note, resveratrol induced diamond-shape “Tirocytes”. The assay design was selected to be flexible, as well as compatible with high-throughput screening. In future experiments, the TSOX will serve to screen chemical libraries and probe molecules that could be added to the additive solution for RBCs storage.

Application of unsupervised machine learning to identify areas of blood product wastage in transfusion medicine

BACKGROUND

Wastage of blood products can be a significant cost to blood banks. However, the cause of wastage is often complex and makes it difficult to determine wastage-associated factors. Machine learning techniques may be useful tools to investigate these complex associations. We investigated whether unsupervised machine learning can identify patterns associated with wastage in our blood bank.

MATERIALS AND METHODS

Data on red blood cells, platelets and frozen products were obtained from the laboratory information system of the Central Zone Blood Transfusion Services at Nova Scotia Health Authority. A total of 879 532 transactions were analysed by association rule mining, a type of machine learning algorithm. Associations with lift scores greater than 25 and with clinical relevance were flagged for further examination.

RESULTS

Association rule mining returned a total of 3355 associations related to wastage. Several notable associations were identified. For example, certain wards were associated with wastage due to thawing unused frozen products. Other examples included association between smaller blood banks and evening work shifts with product wastage due to excess time outside the laboratory or returning products with high temperatures.

CONCLUSION

This paper demonstrates the effective use of unsupervised machine learning for the purpose of investigating wastage in a large blood bank. The use of association rule mining was able to identify wastage factors, which can help guide quality improvement initiatives. This technique can be automated to provide rapid analysis of complex associations contributing to wastage and could be utilized in modern blood banks.

Touchable cell biophysics property recognition platforms enable multifunctional blood smart health care

As a crucial biophysical property, red blood cell (RBC) deformability is pathologically altered in numerous disease states, and biochemical and structural changes occur over time in stored samples of otherwise normal RBCs. However, there is still a gap in applying it further to point-of-care blood devices due to the large external equipment (high-resolution microscope and microfluidic pump), associated operational difficulties, and professional analysis. Herein, we revolutionarily propose a smart optofluidic system to provide a differential diagnosis for blood testing via precise cell biophysics property recognition both mechanically and morphologically. Deformation of the RBC population is caused by pressing the hydrogel via an integrated mechanical transfer device. The biophysical properties of the cell population are obtained by the designed smartphone algorithm. Artificial intelligence-based modeling of cell biophysics properties related to blood diseases and quality was developed for online testing. We currently achieve 100% diagnostic accuracy for five typical clinical blood diseases (90 megaloblastic anemia, 78 myelofibrosis, 84 iron deficiency anemia, 48 thrombotic thrombocytopenic purpura, and 48 thalassemias) via real-world prospective implementation; furthermore, personalized blood quality (for transfusion in cardiac surgery) monitoring is achieved with an accuracy of 96.9%. This work suggests a potential basis for next-generation blood smart health care devices.

Exploring dyserythropoiesis in patients with myelodysplastic syndrome by imaging flow cytometry and machine-learning assisted morphometrics

BACKGROUND

The hallmark of myelodysplastic syndrome (MDS) remains dysplasia in the bone marrow (BM). However, diagnosing MDS may be challenging and subject to inter-observer variability. Thus, there is an unmet need for novel objective, standardized and reproducible methods for evaluating dysplasia. Imaging flow cytometry (IFC) offers combined analyses of phenotypic and image-based morphometric parameters, for example, cell size and nuclearity. Hence, we hypothesized IFC to be a useful tool in MDS diagnostics.

METHODS

Using a different-from-normal approach, we investigated dyserythropoiesis by quantifying morphometric features in a median of 5953 erythroblasts (range: 489-68,503) from 14 MDS patients, 11 healthy donors, 6 non-MDS controls with increased erythropoiesis, and 6 patients with cytopenia.

RESULTS

First, we morphometrically confirmed normal erythroid maturation, as immunophenotypically defined erythroid precursors could be sequenced by significantly decreasing cell-, nuclear- and cytoplasm area. In MDS samples, we demonstrated cell size enlargement and increased fractions of macronormoblasts in late-stage erythroblasts (both p < .0001). Interestingly, cytopenic controls with high-risk mutational patterns displayed highly aberrant cell size morphometrics. Furthermore, assisted by machine learning algorithms, we reliably identified and enumerated true binucleated erythroblasts at a significantly higher frequency in two out of three erythroblast maturation stages in MDS patients compared to normal BM (both p = .0001).

CONCLUSION

We demonstrate proof-of-concept results of the applicability of automated IFC-based techniques to study and quantify morphometric changes in dyserythropoietic BM cells. We propose that IFC holds great promise as a powerful and objective tool in the complex setting of MDS diagnostics with the potential for minimizing inter-observer variability.

Emerging use of machine learning and advanced technologies to assess red cell quality

Improving blood product quality and patient outcomes is an accepted goal in transfusion medicine research. Thus, there is an urgent need to understand the potential adverse effects on red blood cells (RBCs) during pre-transfusion storage. Current assessment techniques of these degradation events, termed "storage lesions", are subjective, labor-intensive, and complex. Here we describe emerging technologies that assess the biochemical, biophysical, and morphological characteristics of RBC storage lesions. Of these emerging techniques, machine learning (ML) has shown potential to overcome the limitations of conventional RBC assessment methods. Our previous work has shown that neural networks can extract chronological progressions of morphological changes in RBCs during storage without human input. We hypothesize that, with broader training and testing of multivariate data (e.g., varying donor factors and manufacturing methods), ML can further our understanding of clinical transfusion outcomes in multiple patient groups.