Dietary n-3 polyunsaturated fatty acids alter the number, fatty acid profile and coagulatory activity of circulating and platelet-derived extracellular vesicles: a randomized, controlled crossover trial.

BACKGROUND: Extracellular vesicles (EVs) are proposed to play a role in the development of cardiovascular diseases (CVDs) and are considered emerging markers of CVDs. n-3 PUFAs are abundant in oily fish and fish oil and are reported to reduce CVD risk, but there has been little research to date examining the effects of n-3 PUFAs on the generation and function of EVs. OBJECTIVES: We aimed to investigate the effects of fish oil supplementation on the number, generation, and function of EVs in subjects with moderate risk of CVDs. METHODS: A total of 40 participants with moderate risk of CVDs were supplemented with capsules containing either fish oil (1.9 g/d n-3 PUFAs) or control oil (high-oleic safflower oil) for 12 wk in a randomized, double-blind, placebo-controlled crossover intervention study. The effects of fish oil supplementation on conventional CVD and thrombogenic risk markers were measured, along with the number and fatty acid composition of circulating and platelet-derived EVs (PDEVs). PDEV proteome profiles were evaluated, and their impact on coagulation was assessed using assays including fibrin clot formation, thrombin generation, fibrinolysis, and ex vivo thrombus formation. RESULTS: n-3 PUFAs decreased the numbers of circulating EVs by 27%, doubled their n-3 PUFA content, and reduced their capacity to support thrombin generation by >20% in subjects at moderate risk of CVDs. EVs derived from n-3 PUFA-enriched platelets in vitro also resulted in lower thrombin generation, but did not alter thrombus formation in a whole blood ex vivo assay. CONCLUSIONS: Dietary n-3 PUFAs alter the number, composition, and function of EVs, reducing their coagulatory activity. This study provides clear evidence that EVs support thrombin generation and that this EV-dependent thrombin generation is reduced by n-3 PUFAs, which has implications for prevention and treatment of thrombosis. CLINICAL TRIAL REGISTRY: This trial was registered at clinicaltrials.gov as NCT03203512.

Evidence that inositol 1,4,5-trisphosphate 3-kinase and inositol 1,3,4,5-tetrakisphosphate are negative regulators of platelet function.

Background: Inositol 1,3,4,5-tetrakisphosphate (IP4) is formed from inositol 1,4,5-trisphosphate (IP3) by IP3 3-kinase (ITPK) in most cells. Its function is unknown but has been suggested to be involved in Ca2+ entry, IP3 regulation, and phosphoinositide 3-kinase antagonism. Objectives: To better elucidate a function for IP4, we tested a specific inhibitor of ITPK (GNF362) on platelets, the effects of IP4 directly in permeabilized platelets and its effect on phosphatidylinositol 3,4,5-trisphosphate (PIP3) binding to pleckstrin-homology (PH) domain-containing proteins in platelets. Methods: Human platelets were utilized in whole blood for thrombus formation, in platelet-rich plasma and washed suspensions for aggregation, and for Ca2+ studies, or resuspended in high K+ and low Na+ buffers for permeabilization experiments. Phosphorylation of AKT-Ser473 and Rap1-GTP formation were measured by Western blotting and PIP3 binding using PIP3 beads. Results: GNF362-enhanced platelet aggregation stimulated by low concentrations of ADP, collagen, thrombin, U46619, and thrombus formation in collagen-coated capillaries. GNF362 induced a transient elevation of Ca2+ concentration, elevated basal levels of IP3, and enhanced the peak height of Ca2+ elevated by agonists. In permeabilized platelets, IP4 inhibited GTPγS induced formation of AKT-Ser473 phosphorylation and platelet aggregation. IP4 reduced GTPγS-stimulated Rap1-GTP levels and potently reduced extraction of RASA3 and BTK by PIP3 beads. Conclusion: ITPK and IP4 are negative regulators of platelet function. IP4 regulation of PH domain-containing proteins may represent a pathway by which platelet activation may be controlled during thrombosis.

Endothelium-mediated regulation of platelet activation: Involvement of multiple protein kinases.

The endothelial regulation of platelet activity is incompletely understood. Here we describe novel approaches to find molecular pathways implicated on the platelet-endothelium interaction. Using high-shear whole-blood microfluidics, employing coagulant or non-coagulant conditions at physiological temperature, we observed that the presence of human umbilical vein endothelial cells (HUVEC) strongly suppressed platelet adhesion and activation, via the collagen receptor glycoprotein VI (GPVI) and the PAR receptors for thrombin. Real-time monitoring of the cytosolic Ca2+ rises in the platelets indicated no major improvement of inhibition by prostacyclin or nitric oxide. Similarly under stasis, exposure of isolated platelets to HUVEC reduced the Ca2+ responses by collagen-related peptide (CRP-XL, GPVI agonist) and thrombin (PAR agonist). We then analyzed the label-free phosphoproteome of platelets (three donors), exposed to HUVEC, CRP-XL, and/or thrombin. High-resolution mass spectrometry gave 5463 phosphopeptides, corresponding to 1472 proteins, with good correlation between biological and technical replicates (R > .86). Stringent filtering steps revealed 26 regulatory pathways (Reactome) and 143 regulated kinase substrates (PhosphoSitePlus), giving a set of protein phosphorylation sites that was differentially (44) or similarly (110) regulated by HUVEC or agonist exposure. The differential regulation was confirmed by stable-isotope analysis of platelets from two additional donors. Substrate analysis indicated major roles of poorly studied protein kinase classes (MAPK, CDK, DYRK, STK, PKC members). Collectively, these results reveal a resetting of the protein phosphorylation profile in platelets exposed to endothelium or to conventional agonists and to endothelium-promoted activity of a multi-kinase network, beyond classical prostacyclin and nitric oxide actors, that may contribute to platelet inhibition.

Multiple myeloma and its treatment contribute to increased platelet reactivity.

Multiple myeloma (MM) and its precursor states, smoldering myeloma (SM) and monoclonal gammopathy of undetermined significance (MGUS) are associated with increased incidence of thrombosis, however the cause of this is unknown. Lenalidomide treatment of MM substantially improves patient survival, although significantly increases thrombotic risk by an unknown mechanism. This pilot study aimed to establish the impact of MM and its treatment with Lenalidomide on platelet function. We analyzed platelet function in MGUS, SM and MM compared to healthy controls. We report an increase in platelet reactivity in MGUS, SM, and MM where increases in fibrinogen binding, P-selectin exposure, altered receptor expression, elevated levels of aggregation and enhanced sensitivity to agonist stimulation were observed. We also demonstrate an increase in patient platelet reactivity post Lenalidomide treatment compared to pre-treatment. We show Lenalidomide treatment of platelets ex vivo increased reactivity that was associated with formation of larger thrombi at arterial shear rates but not venous shear rates. This study demonstrates a clear increase in platelet reactivity and prothrombotic potential in patients with MGUS, SM and MM which is elevated further upon treatment with Lenalidomide. Our observations suggest that more detailed studies are warranted to determine mechanisms of thrombotic complications to enable the development of new preventative strategies that specifically target platelets.

What is the context?Multiple myeloma is associated with increased risk of thrombosis, although the potential role of platelets in this has not been evaluated.What is new?We show in this pilot study that multiple myeloma and its precursor states of smoldering myeloma and monoclonal gammopathy of undetermined significance are associated with increased levels of platelet responses. This is further exacerbated by treatment with the immunomodulatory drug lenalidomide.What is the impact?This study suggests that more detailed studies are warranted to explore the mechanisms that cause these effects in a larger population of patients, since this may reveal new approaches to prevent myeloma-associated thrombotic complications.

Regulation of Glycoprotein VI-Dependent Platelet Activation and Thrombus Formation by Heparan Sulfate Proteoglycan Perlecan.

Proteoglycans form a heterogeneous family of proteins with covalently bound sulfated glycosaminoglycans. The extracellular matrix proteoglycan perlecan has been proposed to bind to the platelet- and megakaryocyte-specific receptor G6bB, co-regulating platelet glycoprotein VI (GPVI) signaling. The derived non-sulfate proteoglycan endorepellin was previously shown to enhance platelet adhesion via the collagen receptor, integrin α2ß1. Here, we compared the roles of perlecan and other matrix proteoglycans in platelet responses and thrombus formation. We used multi-color flow cytometry to measure the degranulation and integrin αIIbß3 activation of washed platelets in response to various proteoglycans and collagen-related peptide (CRP), the GPVI agonist. Perlecan, but not endorepellin, enhanced the CRP-induced activation of platelets in a time- and concentration-dependent manner. Similar to collagen, immobilized perlecan, but not other proteoglycans, supported static platelet adhesion and spreading. In-flowed whole-blood perlecan diminished shear-dependent platelet adhesion, while it enforced GPVI-dependent thrombus formation-to a larger extent than endorepellin-to induce more contracted aggregates of activated platelets. We concluded that the sulfated proteoglycan perlecan enhances GPVI-dependent platelet responses extending to thrombus formation, but it does so at the expense of reduced adhesion of platelets under flow.

Role of heat shock protein 47 in platelet glycoprotein VI dimerization and signaling.

Background: Heat shock protein 47 (HSP47) is an intracellular chaperone protein with an indispensable role in collagen biosynthesis in collagen-secreting cells. This chaperone has also been shown to be released and present on the surface of platelets. The inhibition of HSP47 in human platelets or its ablation in mouse platelets reduces platelet function in response to collagen and the glycoprotein (GP) VI collagen receptor agonist CRP-XL. Objectives: In this study, we sought, through experiments, to explore cellular distribution, trafficking, and influence on GPVI interactions to understand how HSP47 modulates collagen receptor signaling. Methods: HSP47-deficient mouse platelets and SMIH- treated human platelets were used to study the role of HSP47 in collagen mediated responses and signaling. Results: Using subcellular fractionation analysis and immunofluorescence microscopy, HSP47 was found to be localized to the platelet-dense tubular system. Following platelet stimulation, HSP47 mobilization to the cell surface was shown to be dependent on actin polymerization, a feature common to other dense tubular system resident platelet proteins that are released to the cell surface during activation. In this location, HSP47 was found to contribute to platelet adhesion to collagen or CRP-XL but not to GFOGER peptide (an integrin α2ß1-binding sequence within collagens), indicating selective effects of HSP47 on GPVI function. Dimerization of GPVI on the platelet surface increases its affinity for collagen. GPVI dimerization was reduced following HSP47 inhibition, as was collagen and CRP-XL-mediated signaling. Conclusion: The present study identifies a role for cell surface-localized HSP47 in modulating platelet responses to collagen through dimerization of GPVI, thereby enhancing platelet signaling and activation.

Identification of new drugs to counteract anti-spike IgG-induced hyperinflammation in severe COVID-19.

Previously, we and others have shown that SARS-CoV-2 spike-specific IgG antibodies play a major role in disease severity in COVID-19 by triggering macrophage hyperactivation, disrupting endothelial barrier integrity, and inducing thrombus formation. This hyperinflammation is dependent on high levels of anti-spike IgG with aberrant Fc tail glycosylation, leading to Fcγ receptor hyperactivation. For development of immune-regulatory therapeutics, drug specificity is crucial to counteract excessive inflammation whereas simultaneously minimizing the inhibition of antiviral immunity. We here developed an in vitro activation assay to screen for small molecule drugs that specifically counteract antibody-induced pathology. We identified that anti-spike-induced inflammation is specifically blocked by small molecule inhibitors against SYK and PI3K. We identified SYK inhibitor entospletinib as the most promising candidate drug, which also counteracted anti-spike-induced endothelial dysfunction and thrombus formation. Moreover, entospletinib blocked inflammation by different SARS-CoV-2 variants of concern. Combined, these data identify entospletinib as a promising treatment for severe COVID-19.

Platelet factor XIII-A regulates platelet function and promotes clot retraction and stability.

Background: Factor XIII (FXIII) is an important proenzyme in the hemostatic system. The plasma-derived enzyme activated FXIII cross-links fibrin fibers within thrombi to increase their mechanical strength and cross-links fibrin to fibrinolytic inhibitors, specifically α2-antiplasmin, to increase resistance to fibrinolysis. We have previously shown that cellular FXIII (factor XIII-A [FXIII-A]), which is abundant in the platelet cytoplasm, is externalized onto the activated membrane and cross-links extracellular substrates. The contribution of cellular FXIII-A to platelet activation and platelet function has not been extensively studied. Objectives: This study aims to identify the role of platelet FXIII-A in platelet function. Methods: We used normal healthy platelets with a cell permeable FXIII inhibitor and platelets from FXIII-deficient patients as a FXIII-free platelet model in a range of platelet function and clotting tests. Results: Our data demonstrate that platelet FXIII-A enhances fibrinogen binding to the platelet surface upon agonist stimulation and improves the binding of platelets to fibrinogen and aggregation under flow in a whole-blood thrombus formation assay. In the absence of FXIII-A, platelets show reduced sensitivity to agonist stimulation, including decreased P-selectin exposure and fibrinogen binding. We show that FXIII-A is involved in platelet spreading where a lack of FXIII-A reduces the ability of platelets to fully spread on fibrinogen and collagen. Our data demonstrate that platelet FXIII-A is important for clot retraction where clots formed in its absence retracted to a lesser extent. Conclusion: Overall, this study shows that platelet FXIII-A functions during thrombus formation by aiding platelet activation and thrombus retraction in addition to its antifibrinolytic roles.

Delineating Zinc Influx Mechanisms during Platelet Activation.

Zinc (Zn2+) is released by platelets during a hemostatic response to injury. Extracellular zinc ([Zn2+]o) initiates platelet activation following influx into the platelet cytosol. However, the mechanisms that permit Zn2+ influx are unknown. Fluctuations in intracellular zinc ([Zn2+]i) were measured in fluozin-3-loaded platelets using fluorometry and flow cytometry. Platelet activation was assessed using light transmission aggregometry. The detection of phosphoproteins was performed by Western blotting. [Zn2+]o influx and subsequent platelet activation were abrogated by blocking the sodium/calcium exchanged, TRP channels, and ZIP7. Cation store depletion regulated Zn2+ influx. [Zn2+]o stimulation resulted in the phosphorylation of PKC substates, MLC, and ß3 integrin. Platelet activation via GPVI or Zn2+ resulted in ZIP7 phosphorylation in a casein kinase 2-dependent manner and initiated elevations of [Zn2+]i that were sensitive to the inhibition of Orai1, ZIP7, or IP3R-mediated pathways. These data indicate that platelets detect and respond to changes in [Zn2+]o via influx into the cytosol through TRP channels and the NCX exchanger. Platelet activation results in the externalization of ZIP7, which further regulates Zn2+ influx. Increases in [Zn2+]i contribute to the activation of cation-dependent enzymes. Sensitivity of Zn2+ influx to thapsigargin indicates a store-operated pathway that we term store-operated Zn2+ entry (SOZE). These mechanisms may affect platelet behavior during thrombosis and hemostasis.

Developing Biomimetic Hydrogels of the Arterial Wall as a Prothrombotic Substrate for In Vitro Human Thrombosis Models.

Current in vitro thrombosis models utilise simplistic 2D surfaces coated with purified components of the subendothelial matrix. The lack of a realistic humanised model has led to greater study of thrombus formation in in vivo tests in animals. Here we aimed to develop 3D hydrogel-based replicas of the medial and adventitial layers of the human artery to produce a surface that can optimally support thrombus formation under physiological flow conditions. These tissue-engineered medial- (TEML) and adventitial-layer (TEAL) hydrogels were developed by culturing human coronary artery smooth muscle cells and human aortic adventitial fibroblasts within collagen hydrogels, both individually and in co-culture. Platelet aggregation upon these hydrogels was studied using a custom-made parallel flow chamber. When cultured in the presence of ascorbic acid, the medial-layer hydrogels were able to produce sufficient neo-collagen to support effective platelet aggregation under arterial flow conditions. Both TEML and TEAL hydrogels possessed measurable tissue factor activity and could trigger coagulation of platelet-poor plasma in a factor VII-dependent manner. Biomimetic hydrogel replicas of the subendothelial layers of the human artery are effective substrates for a humanised in vitro thrombosis model that could reduce animal experimentation by replacing current in vivo models.

The rate of platelet activation determines thrombus size and structure at arterial shear.

BACKGROUND: The response of platelets to activating stimuli and pharmaceutical agents varies greatly within the normal population. Current platelet function tests are used to measure end-point levels of platelet activation without taking the speed at which platelets activate into account, potentially missing vital metrics to characterize platelet reactivity. OBJECTIVES: To identify variability, to agonists and among individuals, in platelet activation kinetics and assess the impact of this on thrombus formation. METHODS: We have developed a bespoke real-time flow cytometry assay and analysis package to measure the rate of platelet activation over time using 2 parameters of platelet activation, fibrinogen binding and P-selectin exposure. RESULTS: The rate of platelet activation varied considerably within the normal population but did not correlate with maximal platelet activation, demonstrating that platelet activation rate is a separate and novel metric to describe platelet reactivity. The relative rate of platelet response between agonists was strongly correlated, suggesting that a central control mechanism regulates the rate of platelet response to all agonists. CONCLUSION: For the first time, we have shown that platelet response rate corresponds to thrombus size and structure, wherein faster responders form larger, more densely packed thrombi at arterial, but crucially not venous, shear. We have demonstrated that the rate of platelet activation is an important metric in stratifying individual platelet responses and will provide a novel focus for the design and development of antiplatelet therapy, targeting high-shear thrombosis without exacerbating bleeding at low shear.

Immobility-associated thromboprotection is conserved across mammalian species from bear to human.

Venous thromboembolism (VTE) comprising deep venous thrombosis and pulmonary embolism is a major cause of morbidity and mortality. Short-term immobility-related conditions are a major risk factor for the development of VTE. Paradoxically, long-term immobilized free-ranging hibernating brown bears and paralyzed spinal cord injury (SCI) patients are protected from VTE. We aimed to identify mechanisms of immobility-associated VTE protection in a cross-species approach. Mass spectrometry-based proteomics revealed an antithrombotic signature in platelets of hibernating brown bears with heat shock protein 47 (HSP47) as the most substantially reduced protein. HSP47 down-regulation or ablation attenuated immune cell activation and neutrophil extracellular trap formation, contributing to thromboprotection in bears, SCI patients, and mice. This cross-species conserved platelet signature may give rise to antithrombotic therapeutics and prognostic markers beyond immobility-associated VTE.

An agent-based approach for modelling and simulation of glycoprotein VI receptor diffusion, localisation and dimerisation in platelet lipid rafts.

Receptor diffusion plays an essential role in cellular signalling via the plasma membrane microenvironment and receptor interactions, but the regulation is not well understood. To aid in understanding of the key determinants of receptor diffusion and signalling, we developed agent-based models (ABMs) to explore the extent of dimerisation of the platelet- and megakaryocyte-specific receptor for collagen glycoprotein VI (GPVI). This approach assessed the importance of glycolipid enriched raft-like domains within the plasma membrane that lower receptor diffusivity. Our model simulations demonstrated that GPVI dimers preferentially concentrate in confined domains and, if diffusivity within domains is decreased relative to outside of domains, dimerisation rates are increased. While an increased amount of confined domains resulted in further dimerisation, merging of domains, which may occur upon membrane rearrangements, was without effect. Modelling of the proportion of the cell membrane which constitutes lipid rafts indicated that dimerisation levels could not be explained by these alone. Crowding of receptors by other membrane proteins was also an important determinant of GPVI dimerisation. Together, these results demonstrate the value of ABM approaches in exploring the interactions on a cell surface, guiding the experimentation for new therapeutic avenues.

Repeated platelet activation and the potential of previously activated platelets to contribute to thrombus formation.

BACKGROUND: Especially in disease conditions, platelets can encounter activating agents in circulation. OBJECTIVES: To investigate the extent to which previously activated platelets can be reactivated and whether in-and reactivation applies to different aspects of platelet activation and thrombus formation. METHODS: Short-and long-term effects of glycoprotein VI (GPVI) and G protein-coupled receptor (GPCR) stimulation on platelet activation and aggregation potential were compared via flow cytometry and plate-based aggregation. Using fluorescence and electron microscopy, we assessed platelet morphology and content, as well as thrombus formation. RESULTS: After 30 minutes of stimulation with thrombin receptor activator peptide 6 (TRAP6) or adenosine diphosphate (ADP), platelets secondarily decreased in PAC-1 binding and were less able to aggregate. The reversibility of platelets after thrombin stimulation was concentration dependent. Reactivation was possible via another receptor. In contrast, cross-linked collagen-related peptide (CRP-XL) or high thrombin stimulation evoked persistent effects in αIIbß3 activation and platelet aggregation. However, after 60 minutes of CRP-XL or high thrombin stimulation, when αIIbß3 activation slightly decreased, restimulation with ADP or CRP-XL, respectively, increased integrin activation again. Compatible with decreased integrin activation, platelet morphology was reversed. Interestingly, reactivation of reversed platelets again resulted in shape change and if not fully degranulated, additional secretion. Moreover, platelets that were previously activated with TRAP6 or ADP regained their potential to contribute to thrombus formation under flow. On the contrary, prior platelet triggering with CRP-XL was accompanied by prolonged platelet activity, leading to a decreased secondary platelet adhesion under flow. CONCLUSION: This work emphasizes that prior platelet activation can be reversed, whereafter platelets can be reactivated through a different receptor. Reversed, previously activated platelets can contribute to thrombus formation.

Exploring the constituent mechanisms of hepatitis: a dynamical systems approach.

Hepatitis is the term used to describe inflammation in the liver. It is associated with a high rate of mortality, but the underlying disease mechanisms are not completely understood and treatment options are limited. We present a mathematical model of hepatitis that captures the complex interactions between hepatocytes (liver cells), hepatic stellate cells (cells in the liver that produce hepatitis-associated fibrosis) and the immune components that mediate inflammation. The model is in the form of a system of ordinary differential equations. We use numerical techniques and bifurcation analysis to characterize and elucidate the physiological mechanisms that dominate liver injury and its outcome to a healthy or unhealthy, chronic state. This study reveals the complex interactions between the multiple cell types and mediators involved in this complex disease and highlights potential problems in targeting inflammation in the liver therapeutically.

Activation of Human Platelets by Staphylococcus aureus Secreted Protease Staphopain A.

Infection by Staphylococcus aureus is the leading cause of infective endocarditis (IE). Activation of platelets by this pathogen results in their aggregation and thrombus formation which are considered to be important steps in the development and pathogenesis of IE. Here, we show that a secreted cysteine protease, staphopain A, activates human platelets and induces their aggregation. The culture supernatant of a scpA mutant deficient in staphopain A production was reduced in its ability to trigger platelet aggregation. The platelet agonist activity of purified staphopain A was inhibited by staphostatin A, a specific inhibitor, thus implicating its protease activity in the agonism. In whole blood, using concentrations of staphopain A that were otherwise insufficient to induce platelet aggregation, increased binding to collagen and thrombus formation was observed. Using antagonists specific to protease-activated receptors 1 and 4, we demonstrate their role in mediating staphopain A induced platelet activation.

Coagulation Factor XIIIa and Activated Protein C Activate Platelets via GPVI and PAR1.

Platelet and coagulation activation are highly reciprocal processes driven by multi-molecular interactions. Activated platelets secrete several coagulation factors and expose phosphatidylserine, which supports the activation of coagulation factor proteins. On the other hand, the coagulation cascade generates known ligands for platelet receptors, such as thrombin and fibrin. Coagulation factor (F)Xa, (F)XIIIa and activated protein C (APC) can also bind to platelets, but the functional consequences are unclear. Here, we investigated the effects of the activated (anti)coagulation factors on platelets, other than thrombin. Multicolor flow cytometry and aggregation experiments revealed that the 'supernatant of (hirudin-treated) coagulated plasma' (SCP) enhanced CRP-XL-induced platelet responses, i.e., integrin αIIbß3 activation, P-selectin exposure and aggregate formation. We demonstrated that FXIIIa in combination with APC enhanced platelet activation in solution, and separately immobilized FXIIIa and APC resulted in platelet spreading. Platelet activation by FXIIIa was inhibited by molecular blockade of glycoprotein VI (GPVI) or Syk kinase. In contrast, platelet spreading on immobilized APC was inhibited by PAR1 blockade. Immobilized, but not soluble, FXIIIa and APC also enhanced in vitro adhesion and aggregation under flow. In conclusion, in coagulation, factors other than thrombin or fibrin can induce platelet activation via GPVI and PAR receptors.

Fully automated platelet differential interference contrast image analysis via deep learning.

Platelets mediate arterial thrombosis, a leading cause of myocardial infarction and stroke. During injury, platelets adhere and spread over exposed subendothelial matrix substrates of the damaged blood vessel wall. The mechanisms which govern platelet activation and their interaction with a range of substrates are therefore regularly investigated using platelet spreading assays. These assays often use differential interference contrast (DIC) microscopy to assess platelet morphology and analysis performed using manual annotation. Here, a convolutional neural network (CNN) allowed fully automated analysis of platelet spreading assays captured by DIC microscopy. The CNN was trained using 120 generalised training images. Increasing the number of training images increases the mean average precision of the CNN. The CNN performance was compared to six manual annotators. Significant variation was observed between annotators, highlighting bias when manual analysis is performed. The CNN effectively analysed platelet morphology when platelets spread over a range of substrates (CRP-XL, vWF and fibrinogen), in the presence and absence of inhibitors (dasatinib, ibrutinib and PRT-060318) and agonist (thrombin), with results consistent in quantifying spread platelet area which is comparable to published literature. The application of a CNN enables, for the first time, automated analysis of platelet spreading assays captured by DIC microscopy.