Objective assessment of stored blood quality by deep learning.

Stored red blood cells (RBCs) are needed for life-saving blood transfusions, but they undergo continuous degradation. RBC storage lesions are often assessed by microscopic examination or biochemical and biophysical assays, which are complex, time-consuming, and destructive to fragile cells. Here we demonstrate the use of label-free imaging flow cytometry and deep learning to characterize RBC lesions. Using brightfield images, a trained neural network achieved 76.7% agreement with experts in classifying seven clinically relevant RBC morphologies associated with storage lesions, comparable to 82.5% agreement between different experts. Given that human observation and classification may not optimally discern RBC quality, we went further and eliminated subjective human annotation in the training step by training a weakly supervised neural network using only storage duration times. The feature space extracted by this network revealed a chronological progression of morphological changes that better predicted blood quality, as measured by physiological hemolytic assay readouts, than the conventional expert-assessed morphology classification system. With further training and clinical testing across multiple sites, protocols, and instruments, deep learning and label-free imaging flow cytometry might be used to routinely and objectively assess RBC storage lesions. This would automate a complex protocol, minimize laboratory sample handling and preparation, and reduce the impact of procedural errors and discrepancies between facilities and blood donors. The chronology-based machine-learning approach may also improve upon humans' assessment of morphological changes in other biomedically important progressions, such as differentiation and metastasis.

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.

Label-Free Analysis of Red Blood Cell Storage Lesions Using Imaging Flow Cytometry.

Deleterious changes, collectively termed as storage lesions, alter the characteristics of red blood cell (RBC) morphology during in vitro storage. Due to gradual loss of cellular membrane, RBCs lose their original biconcave disk shape and begin a process of spherical deformation that is characterized by well-defined morphological criteria. At the spheroechinocyte stage, the structure of RBC is irreversibly damaged and lacks the elasticity necessary to efficiently deliver oxygen. Quantifying the prevalence of spheroechinocytes could provide an important morphological measure of the quality of stored blood products. Unlike the conventional RBC morphology characterization assay involving light microscopy, we introduce a label-free assay using imaging flow cytometry (IFC). The technique captures 100,000 images of a sample and calculates a relative measure of spheroechinocyte population in a fraction of the time required by the conventional method. A comparative method study, measuring a morphological index for 11 RCC units through storage, found that the two techniques measured similar trends with IFC reporting the metric at an average of 3.9% higher. We monitored 18 RCC units between Weeks 1 and 6 of storage and found that the spheroechinocyte population increased by an average of 26.2%. The large (3.5-64.1%) variation between the units' spheroechinocyte population percentage at Week 1 suggests a possible dependence of blood product quality on donor characteristics. Given our method's ability to rapidly monitor large samples and refine morphological characterization beyond conventional methods, we believe our technique offers good potential for studying the underlying relationships between RBC morphology and blood storage lesions. © 2019 International Society for Advancement of Cytometry.

Feasibility of photoacoustic imaging for the non-invasive quality management of stored blood bags.

BACKGROUND AND OBJECTIVES: During the in vitro storage of red blood cells (RBCs), unfavourable changes (storage lesions) cause a rapid consumption of intracellular diphosphoglycerate. The latter deregulates the oxygen-haemoglobin binding potential, subsequently increasing oxygen saturation (SO2 ) and membrane degradation, transforming RBCs from biconcave discs to rigid spherical bodies (spheroechinocytes). Current laboratory techniques invasively extract RBC samples to assess the quality of red cell concentrate (RCC) units. Optical technologies could provide a means of assessing quality non-invasively. MATERIALS AND METHODS: A photoacoustic (PA) imaging technique was developed for acquiring the SO2 of blood bags non-invasively. Seven RCC units were monitored every 3-5 days until expiry (6 weeks). Measurements were validated against a conventional blood gas analyzer (BGA). Using an image flow cytometry assay, morphological profile trends were compared against the SO2 trends during blood bag storage. RESULTS: A strong correlation (r2  ≥ 0·95) was found when comparing temporal data between PA and BGA SO2 measurements. Inter-sample PA variability was found to be similar to that produced by BGA (±0·8%). A strong correlation was found to exist between the temporal changes in SO2 and relative spheroechinocyte population (0·79 ≤ r2  ≤ 0·97). CONCLUSION: This study suggests that PA imaging can non-invasively track the SO2 of stored RBCs non-invasively. By longitudinally monitoring the change in SO2 , it is possible to infer the effects of the storage lesion on RBC morphology. This non-invasive monitoring technique allows for the assessment of blood bags, without compromising sterility pre-transfusion.

Assessing engineered tissues and biomaterials using ultrasound imaging: In vitro and in vivo applications.

Quantitative assessment of the structural, functional, and mechanical properties of engineered tissues and biomaterials is fundamental to their development for regenerative medicine applications. Ultrasound (US) imaging is a non-invasive, non-destructive, and cost-effective technique capable of longitudinal and quantitative monitoring of tissue structure and function across centimeter to sub-micron length scales. Here we present the fundamentals of US to contextualize its application for the assessment of biomaterials and engineered tissues, both in vivo and in vitro. We review key studies that demonstrate the versatility and broad capabilities of US for clinical and pre-clinical biomaterials research. Finally, we highlight emerging techniques that further extend the applications of US, including for ultrafast imaging of biomaterials and engineered tissues in vivo and functional monitoring of stem cells, organoids, and organ-on-a-chip systems in vitro.

High-frequency quantitative ultrasound for the assessment of the acoustic properties of engineered tissues in vitro.

Acoustic properties of biomaterials and engineered tissues reflect their structure and cellularity. High-frequency ultrasound (US) can non-invasively characterize and monitor these properties with sub-millimetre resolution. We present an approach to estimate the speed of sound, acoustic impedance, and acoustic attenuation of cell-laden hydrogels that accounts for frequency-dependent effects of attenuation in coupling media, hydrogel thickness, and interfacial transmission/reflection coefficients of US waves, all of which can bias attenuation estimates. Cell-seeded fibrin hydrogel disks were raster-scanned using a 40 MHz US transducer. Thickness, speed of sound, acoustic impedance, and acoustic attenuation coefficients were determined from the difference in the time-of-flight and ratios of the magnitudes of US signals, interfacial transmission/reflection coefficients, and acoustic properties of the coupling media. With this approach, hydrogel thickness was accurately measured by US, with agreement to confocal microscopy (r2 = 0.97). Accurate thickness measurement enabled acoustic property measurements that were independent of hydrogel thickness, despite up to 60% reduction in thickness due to cell-mediated contraction. Notably, acoustic attenuation coefficients increased with increasing cell concentration (p < 0.001), reflecting hydrogel cellularity independent of contracted hydrogel thickness. This approach enables accurate measurement of the intrinsic acoustic properties of biomaterials and engineered tissues to provide new insights into their structure and cellularity. STATEMENT OF SIGNIFICANCE: High-frequency ultrasound can measure the acoustic properties of engineered tissues non-invasively and non-destructively with µm-scale resolution. Acoustic properties, including acoustic attenuation, are related to intrinsic material properties, such as scatterer density. We developed an analytical approach to estimate the acoustic properties of cell-laden hydrogels that accounts for the frequency-dependent effects of attenuation in coupling media, the reflection/transmission of ultrasound waves at the coupling interfaces, and the dependency of measurements on hydrogel thickness. Despite up to 60% reduction in hydrogel thickness due to cell-mediated contraction, our approach enabled measurements of acoustic properties that were substantially independent of thickness. Acoustic attenuation increased significantly with increasing cell concentration (p < 0.001), demonstrating the ability of acoustic attenuation to reflect intrinsic physical properties of engineered tissues.

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.

Photoacoustic imaging biomarkers for monitoring biophysical changes during nanobubble-mediated radiation treatment.

The development of novel anticancer therapies warrants the parallel development of biomarkers that can quantify their effectiveness. Photoacoustic imaging has the potential to measure changes in tumor vasculature during treatment. Establishing the accuracy of imaging biomarkers requires direct comparisons with gold histological standards. In this work, we explore whether a new class of submicron, vascular disrupting, ultrasonically stimulated nanobubbles enhance radiation therapy. In vivo experiments were conducted on mice bearing prostate cancer tumors. Combined nanobubble plus radiation treatments were compared against conventional microbubbles and radiation alone (single 8 Gy fraction). Acoustic resolution photoacoustic imaging was used to monitor the effects of the treatments 2- and 24-hs post-administration. Histological examination provided metrics of tumor vascularity and tumoral cell death, both of which were compared to photoacoustic-derived biomarkers. Photoacoustic metrics of oxygen saturation reveal a 20 % decrease in oxygenation within 24 h post-treatment. The spectral slope metric could separate the response of the nanobubble treatments from the microbubble counterparts. This study shows that histopathological assessment correlated well with photoacoustic biomarkers of treatment response.

Determination of cell nucleus-to-cytoplasmic ratio using imaging flow cytometry and a combined ultrasound and photoacoustic technique: a comparison study.

While the nucleus-to-cytoplasmic (N:C) ratio has traditionally been used for assessing cell malignancy, most N:C measurement techniques are time-consuming and performed on thin histological sections, which prohibit assessment of three-dimensional cell structure. A combined ultrahigh frequency ultrasound (US) and photoacoustic (PA) technique was used to assess the size and N:C ratio of cultured cancer cells in three dimensions (3D). The diameters of the cells and their stained nuclei were obtained by fitting the power spectrum of backscattered US pulses and emitted PA waves, respectively, to well-established theoretical models. For comparison, an imaging flow cytometer (IFC) was also used to determine the two-dimensional cell and nucleus sizes from large cell populations using brightfield and fluorescence images, respectively. An N:C ratio was calculated for each cell using the quotient of the measured nucleus diameter and the total cell diameter. The mean N:C ratios calculated using the sound-based approach were 0.68, 0.66, and 0.54 for MCF-7, PC-3, and MDA-MB-231 cells, respectively, and were in good agreement with the corresponding values of 0.68, 0.67, and 0.68 obtained using the IFC. The combined US and PA technique, which assesses cellular N:C ratio in 3D, has potential applications in the detection of circulating tumor cells in liquid biopsies.

Sizing biological cells using a microfluidic acoustic flow cytometer.

We describe a new technique that combines ultrasound and microfluidics to rapidly size and count cells in a high-throughput and label-free fashion. Using 3D hydrodynamic flow focusing, cells are streamed single file through an ultrasound beam where ultrasound scattering events from each individual cell are acquired. The ultrasound operates at a center frequency of 375 MHz with a wavelength of 4 µm; when the ultrasound wavelength is similar to the size of a scatterer, the power spectra of the backscattered ultrasound waves have distinct features at specific frequencies that are directly related to the cell size. Our approach determines cell sizes through a comparison of these distinct spectral features with established theoretical models. We perform an analysis of two types of cells: acute myeloid leukemia cells, where 2,390 measurements resulted in a mean size of 10.0 ± 1.7 µm, and HT29 colorectal cancer cells, where 1,955 measurements resulted in a mean size of 15.0 ± 2.3 µm. These results and histogram distributions agree very well with those measured from a Coulter Counter Multisizer 4. Our technique is the first to combine ultrasound and microfluidics to determine the cell size with the potential for multi-parameter cellular characterization using fluorescence, light scattering and quantitative photoacoustic techniques.