Assessing red blood cell deformability from microscopy images using deep learning

Lamoureux, Erik S.; Islamzada, Emel; Wiens, Matthew V.J.; Matthews, Kerryn; Duffy, Simon P.; Ma, Hongshen

doi:10.1039/d1lc01006a

Cited by 28 publications

(30 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…, of stored RBCs, results in a change in the RBC lateral distribution, especially at high velocities ( Figures 2 , 4 ). Additionally, employing machine learning algorithms enabled us to characterize pathological RBC morphologies under constant flow, similar to previous studies in stasis ( Moon et al, 2021 ; Simionato et al, 2021 ; Song et al, 2021 ; Lamoureux et al, 2022 ). This allowed us to detect morphological changes, distinctive for a certain disease, such as the acanthocytes shown in Figure 2 , or treatment (HDF, Figure 3 ).…”

Section: Discussionmentioning

confidence: 67%

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

et al. 2022

View full text Add to dashboard Cite

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.

show abstract

Section: Discussionmentioning

confidence: 67%

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

et al. 2022

View full text Add to dashboard Cite

show abstract

“…151 Since the morphological changes due to the storage lesion are associated with decreased deformability, deep learning techniques were extended to assess RBC deformability directly. 152 In this study, RBCs were sorted based on deformability through a microfluidic ratchet sorting device, and subsequently sorted cells were imaged using brightfield microscopy at 40× magnification. These images were used to train and test the deep neural network, achieving deep learning-derived rigidity scores within 10.4 ± 6.8% of the values derived from cell sorting using the microfluidic ratchet device.…”

Section: Imaging and Machine Learning Techniquesmentioning

confidence: 99%

“…These images were used to train and test the deep neural network, achieving deep learning-derived rigidity scores within 10.4 ± 6.8% of the values derived from cell sorting using the microfluidic ratchet device. 152 Additional work will be required to assess the generalizability of this approach, but there are indications of the research potential of this area. For example, there is emerging indications that machine learning-enabled technologies can aid the assessment of RBC quality for transfusion.…”

Section: Imaging and Machine Learning Techniquesmentioning

confidence: 99%

Technologies for measuring red blood cell deformability

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…ML techniques are also applied to microscale blood flow. Examples include classification of RBC shapes in capillary blood flow [54], modelling RBC deformation and prediction of RBC trajectory in microfluidic devices [55,56], and estimation of cell deformability [57,58]. ML was also used to integrate images of blood flow to underlying physical laws to infer the flow field in microaneurysm [59].…”

Section: Introductionmentioning

confidence: 99%

Application of machine learning in predicting blood flow and red cell distribution in capillary vessel networks

Ebrahimi

Bagchi

2022

J. R. Soc. Interface.

View full text Add to dashboard Cite

Capillary blood vessels in the body partake in the exchange of gas and nutrients with tissues. They are interconnected via multiple vascular junctions forming the microvascular network. Distributions of blood flow and red cells (RBCs) in such networks are spatially uneven and vary in time. Since they dictate the pathophysiology of tissues, their knowledge is important. Theoretical models used to obtain flow and RBC distribution in large networks have limitations as they treat each vessel as a one-dimensional segment and do not explicitly consider cell–cell and cell–vessel interactions. High-fidelity computational models that accurately model each individual RBC are computationally too expensive to predict haemodynamics in large vascular networks and over a long time. Here we investigate the applicability of machine learning (ML) techniques to predict blood flow and RBC distributions in physiologically realistic vascular networks. We acquire data from high-fidelity simulations of deformable RBC suspension flowing in the networks. With the flow and haematocrit specified at an inlet of vasculature, the ML models predict the time-averaged flow rate and RBC distributions in the entire network, time-dependent flow rate and haematocrit in each vessel and vascular bifurcation in isolation over a long time, and finally, simultaneous spatially and temporally evolving quantities through the vessel hierarchy in the networks.

show abstract

Assessing red blood cell deformability from microscopy images using deep learning

Abstract: 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...

Cited by 28 publications

References 56 publications

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

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

Technologies for measuring red blood cell deformability

Application of machine learning in predicting blood flow and red cell distribution in capillary vessel networks

Contact Info

Product

Resources

About