The use of voting ensembles to improve the accuracy of deep neural networks as a non-invasive method to predict embryo ploidy status.

PURPOSE: To determine if creating voting ensembles combining convolutional neural networks (CNN), support vector machine (SVM), and multi-layer neural networks (NN) alongside clinical parameters improves the accuracy of artificial intelligence (AI) as a non-invasive method for predicting aneuploidy. METHODS: A cohort of 699 day 5 PGT-A tested blastocysts was used to train, validate, and test a CNN to classify embryos as euploid/aneuploid. All embryos were analyzed using a modified FAST-SeqS next-generation sequencing method. Patient characteristics such as maternal age, AMH level, paternal sperm quality, and total number of normally fertilized (2PN) embryos were processed using SVM and NN. To improve model performance, we created voting ensembles using CNN, SVM, and NN to combine our imaging data with clinical parameter variations. Statistical significance was evaluated with a one-sample t-test with 2 degrees of freedom. RESULTS: When assessing blastocyst images alone, the CNN test accuracy was 61.2% (± 1.32% SEM, n = 3 models) in correctly classifying euploid/aneuploid embryos (n = 140 embryos). When the best CNN model was assessed as a voting ensemble, the test accuracy improved to 65.0% (AMH; p = 0.1), 66.4% (maternal age; p = 0.06), 65.7% (maternal age, AMH; p = 0.08), 66.4% (maternal age, AMH, number of 2PNs; p = 0.06), and 71.4% (maternal age, AMH, number of 2PNs, sperm quality; p = 0.02) (n = 140 embryos). CONCLUSIONS: By combining CNNs with patient characteristics, voting ensembles can be created to improve the accuracy of classifying embryos as euploid/aneuploid from CNN alone, allowing for AI to serve as a potential non-invasive method to aid in karyotype screening and selection of embryos.

Advancements in the future of automating micromanipulation techniques in the IVF laboratory using deep convolutional neural networks.

PURPOSE: To determine if deep learning artificial intelligence algorithms can be used to accurately identify key morphologic landmarks on oocytes and cleavage stage embryo images for micromanipulation procedures such as intracytoplasmic sperm injection (ICSI) or assisted hatching (AH). METHODS: Two convolutional neural network (CNN) models were trained, validated, and tested over three replicates to identify key morphologic landmarks used to guide embryologists when performing micromanipulation procedures. The first model (CNN-ICSI) was trained (n = 13,992), validated (n = 1920), and tested (n = 3900) to identify the optimal location for ICSI through polar body identification. The second model (CNN-AH) was trained (n = 13,908), validated (n = 1908), and tested (n = 3888) to identify the optimal location for AH on the zona pellucida that maximizes distance from healthy blastomeres. RESULTS: The CNN-ICSI model accurately identified the polar body and corresponding optimal ICSI location with 98.9% accuracy (95% CI 98.5-99.2%) with a receiver operator characteristic (ROC) with micro and macro area under the curves (AUC) of 1. The CNN-AH model accurately identified the optimal AH location with 99.41% accuracy (95% CI 99.11-99.62%) with a ROC with micro and macro AUCs of 1. CONCLUSION: Deep CNN models demonstrate powerful potential in accurately identifying key landmarks on oocytes and cleavage stage embryos for micromanipulation. These findings are novel, essential stepping stones in the automation of micromanipulation procedures.

Quality assurance (QA) for monitoring the performance of assisted reproductive technology (ART) staff using artificial intelligence (AI).

PURPOSE: Deep learning neural networks have been used to predict the developmental fate and implantation potential of embryos with high accuracy. Such networks have been used as an assistive quality assurance (QA) tool to identify perturbations in the embryo culture environment which may impact clinical outcomes. The present study aimed to evaluate the utility of an AI-QA tool to consistently monitor ART staff performance (MD and embryologist) in embryo transfer (ET), embryo vitrification (EV), embryo warming (EW), and trophectoderm biopsy (TBx). METHODS: Pregnancy outcomes from groups of 20 consecutive elective single day 5 blastocyst transfers were evaluated for the following procedures: MD performed ET (N = 160 transfers), embryologist performed ET (N = 160 transfers), embryologist performed EV (N = 160 vitrification procedures), embryologist performed EW (N = 160 warming procedures), and embryologist performed TBx (N = 120 biopsies). AI-generated implantation probabilities for the same embryo cohorts were estimated, as were mean AI-predicted and actual implantation rates for each provider and compared using Wilcoxon singed-rank test. RESULTS: Actual implantation rates following ET performed by one MD provider: "H" was significantly lower than AI-predicted (20% vs. 61%, p = 0.001). Similar results were observed for one embryologist, "H" (30% vs. 60%, p = 0.011). Embryos thawed by embryologist "H" had lower implantation rates compared to AI prediction (25% vs. 60%, p = 0.004). There were no significant differences between actual and AI-predicted implantation rates for EV, TBx, or for the rest of the clinical staff performing ET or EW. CONCLUSIONS: AI-based QA tools could provide accurate, reproducible, and efficient staff performance monitoring in an ART practice.

Using artificial intelligence to avoid human error in identifying embryos: a retrospective cohort study.

PURPOSE: To determine whether convolutional neural networks (CNN) can be used to accurately ascertain the patient identity (ID) of cleavage and blastocyst stage embryos based on image data alone. METHODS: A CNN model was trained and validated over three replicates on a retrospective cohort of 4889 time-lapse embryo images. The algorithm processed embryo images for each patient and produced a unique identification key that was associated with the patient ID at a timepoint on day 3 (~ 65 hours post-insemination (hpi)) and day 5 (~ 105 hpi) forming our data library. When the algorithm evaluated embryos at a later timepoint on day 3 (~ 70 hpi) and day 5 (~ 110 hpi), it generates another key that was matched with the patient's unique key available in the library. This approach was tested using 400 patient embryo cohorts on day 3 and day 5 and number of correct embryo identifications with the CNN algorithm was measured. RESULTS: CNN technology matched the patient identification within random pools of 8 patient embryo cohorts on day 3 with 100% accuracy (n = 400 patients; 3 replicates). For day 5 embryo cohorts, the accuracy within random pools of 8 patients was 100% (n = 400 patients; 3 replicates). CONCLUSIONS: This study describes an artificial intelligence-based approach for embryo identification. This technology offers a robust witnessing step based on unique morphological features of each embryo. This technology can be integrated with existing imaging systems and laboratory protocols to improve specimen tracking.

Deep learning early warning system for embryo culture conditions and embryologist performance in the ART laboratory.

Staff competency is a crucial component of the in vitro fertilization (IVF) laboratory quality management system because it impacts clinical outcomes and informs the key performance indicators (KPIs) used to continuously monitor and assess culture conditions. Contemporary quality control and assurance in the IVF lab can be automated (collect, store, retrieve, and analyze), to elevate quality control and assurance beyond the cursory monthly review. Here we demonstrate that statistical KPI monitoring systems for individual embryologist performance and culture conditions can be detected by artificial intelligence systems to provide systemic, early detection of adverse outcomes, and identify clinically relevant shifts in pregnancy rates, providing critical validation for two statistical process controls proposed in the Vienna Consensus Document; intracytoplasmic sperm injection (ICSI) fertilization rate and day 3 embryo quality.

Hybrid Paper-Plastic Microchip for Flexible and High-Performance Point-of-Care Diagnostics.

A low-cost and easy-to-fabricate microchip remains a key challenge for the development of true point-of-care (POC) diagnostics. Cellulose paper and plastic are thin, light, flexible, and abundant raw materials, which make them excellent substrates for mass production of POC devices. Herein, a hybrid paper-plastic microchip (PPMC) is developed, which can be used for both single and multiplexed detection of different targets, providing flexibility in the design and fabrication of the microchip. The developed PPMC with printed electronics is evaluated for sensitive and reliable detection of a broad range of targets, such as liver and colon cancer protein biomarkers, intact Zika virus, and human papillomavirus nucleic acid amplicons. The presented approach allows a highly specific detection of the tested targets with detection limits as low as 102 ng mL-1 for protein biomarkers, 103 particle per milliliter for virus particles, and 102 copies per microliter for a target nucleic acid. This approach can potentially be considered for the development of inexpensive and stable POC microchip diagnostics and is suitable for the detection of a wide range of microbial infections and cancer biomarkers.

Emerging technologies for point-of-care management of HIV infection.

The global HIV/AIDS pandemic has resulted in 39 million deaths to date, and there are currently more than 35 million people living with HIV worldwide. Prevention, screening, and treatment strategies have led to major progress in addressing this disease globally. Diagnostics is critical for HIV prevention, screening and disease staging, and monitoring antiretroviral therapy (ART). Currently available diagnostic assays, which include polymerase chain reaction (PCR), enzyme-linked immunosorbent assay (ELISA), and western blot (WB), are complex, expensive, and time consuming. These diagnostic technologies are ill suited for use in low- and middle-income countries, where the challenge of the HIV/AIDS pandemic is most severe. Therefore, innovative, inexpensive, disposable, and rapid diagnostic platform technologies are urgently needed. In this review, we discuss challenges associated with HIV management in resource-constrained settings and review the state-of-the-art HIV diagnostic technologies for CD4(+) T lymphocyte count, viral load measurement, and drug resistance testing.

Electrically Oscillating Plasmonic Nanoparticles for Enhanced DNA Vaccination against Hepatitis C Virus.

The promise of DNA vaccines is far-reaching. However, the development of potent immunization methods remains a key challenge for its use in clinical applications. Here, an approach for in vivo DNA vaccination by electrically activated plasmonic Au nanoparticles is reported. The electrical excitation of plasmonic nanoparticles can drive vibrational and dipole-like oscillations that are able to disrupt nearby cell membranes. In combination with their intrinsic ability to focus and magnify the electric field on the surface of cells, Au nanoparticles allow enhanced cell poration and facilitate the uptake of DNA vaccine. Mice immunized with this approach showed up to 100-fold higher gene expression compared to control treatments (without nanoparticles) and exhibited significantly increased levels of both antibody and cellular immune responses against a model hepatitis C virus DNA vaccine. This approach can be tuned to establish controlled and targeted delivery of different types of therapeutic molecules into cells and live animals as well.

Strategies in Ebola virus disease (EVD) diagnostics at the point of care.

Ebola virus disease (EVD) is a devastating, highly infectious illness with a high mortality rate. The disease is endemic to regions of Central and West Africa, where there is limited laboratory infrastructure and trained staff. The recent 2014 West African EVD outbreak has been unprecedented in case numbers and fatalities, and has proven that such regional outbreaks can become a potential threat to global public health, as it became the source for the subsequent transmission events in Spain and the USA. The urgent need for rapid and affordable means of detecting Ebola is crucial to control the spread of EVD and prevent devastating fatalities. Current diagnostic techniques include molecular diagnostics and other serological and antigen detection assays; which can be time-consuming, laboratory-based, often require trained personnel and specialized equipment. In this review, we discuss the various Ebola detection techniques currently in use, and highlight the potential future directions pertinent to the development and adoption of novel point-of-care diagnostic tools. Finally, a case is made for the need to develop novel microfluidic technologies and versatile rapid detection platforms for early detection of EVD.

Advances in Candida detection platforms for clinical and point-of-care applications.

Invasive candidiasis remains one of the most serious community and healthcare-acquired infections worldwide. Conventional Candida detection methods based on blood and plate culture are time-consuming and require at least 2-4 days to identify various Candida species. Despite considerable advances for candidiasis detection, the development of simple, compact and portable point-of-care diagnostics for rapid and precise testing that automatically performs cell lysis, nucleic acid extraction, purification and detection still remains a challenge. Here, we systematically review most prominent conventional and nonconventional techniques for the detection of various Candida species, including Candida staining, blood culture, serological testing and nucleic acid-based analysis. We also discuss the most advanced lab on a chip devices for candida detection.

Engineering cancer microenvironments for in vitro 3-D tumor models.

The natural microenvironment of tumors is composed of extracellular matrix (ECM), blood vasculature, and supporting stromal cells. The physical characteristics of ECM as well as the cellular components play a vital role in controlling cancer cell proliferation, apoptosis, metabolism, and differentiation. To mimic the tumor microenvironment outside the human body for drug testing, two-dimensional (2-D) and murine tumor models are routinely used. Although these conventional approaches are employed in preclinical studies, they still present challenges. For example, murine tumor models are expensive and difficult to adopt for routine drug screening. On the other hand, 2-D in vitro models are simple to perform, but they do not recapitulate natural tumor microenvironment, because they do not capture important three-dimensional (3-D) cell-cell, cell-matrix signaling pathways, and multi-cellular heterogeneous components of the tumor microenvironment such as stromal and immune cells. The three-dimensional (3-D) in vitro tumor models aim to closely mimic cancer microenvironments and have emerged as an alternative to routinely used methods for drug screening. Herein, we review recent advances in 3-D tumor model generation and highlight directions for future applications in drug testing.

Acute on-chip HIV detection through label-free electrical sensing of viral nano-lysate.

Development of portable biosensors has broad applications in environmental monitoring, clinical diagnosis, public health, and homeland security. There is an unmet need for pathogen detection at the point-of-care (POC) using a fast, sensitive, inexpensive, and easy-to-use method that does not require complex infrastructure and well-trained technicians. For instance, detection of Human Immunodeficiency Virus (HIV-1) at acute infection stage has been challenging, since current antibody-based POC technologies are not effective due to low concentration of antibodies. In this study, we demonstrated for the first time a label-free electrical sensing method that can detect lysed viruses, i.e. viral nano-lysate, through impedance analysis, offering an alternative technology to the antibody-based methods such as dipsticks and Enzyme-linked Immunosorbent Assay (ELISA). The presented method is a broadly applicable platform technology that can potentially be adapted to detect multiple pathogens utilizing impedance spectroscopy for other infectious diseases including herpes, influenza, hepatitis, pox, malaria, and tuberculosis. The presented method offers a rapid and portable tool that can be used as a detection technology at the POC in resource-constrained settings, as well as hospital and primary care settings.

Could artificial intelligence revolutionize the development of nanovectors for gene therapy and mRNA vaccines?

Gene therapy enables the introduction of nucleic acids like DNA and RNA into host cells, and is expected to revolutionize the treatment of a wide range of diseases. This growth has been further accelerated by the discovery of CRISPR/Cas technology, which allows accurate genomic editing in a broad range of cells and organisms in vitro and in vivo. Despite many advances in gene delivery and the development of various viral and non-viral gene delivery vectors, the lack of highly efficient non-viral systems with low cellular toxicity remains a challenge. The application of cutting-edge technologies such as artificial intelligence (AI) has great potential to find new paradigms to solve this issue. Herein, we review AI and its major subfields including machine learning (ML), neural networks (NNs), expert systems, deep learning (DL), computer vision and robotics. We discuss the potential of AI-based models and algorithms in the design of targeted gene delivery vehicles capable of crossing extracellular and intracellular barriers by viral mimicry strategies. We finally discuss the role of AI in improving the function of CRISPR/Cas systems, developing novel nanobots, and mRNA vaccine carriers.

Validation of a smartphone-based device to measure concentration, motility, and morphology in swine ejaculates.

Assessment of swine semen quality is important as it is used as an estimate of the fertility of an ejaculate. There are many methods to measure sperm morphology, concentration, and motility, however, some methods require expensive instrumentation or are not easy to use on-farm. A portable, low-cost, automated device could provide the potential to assess semen quality in field conditions. The objective of this study was to validate the use of Fertile-Eyez (FE), a smartphone-based device, to measure sperm concentration, total motility, and morphology in boar ejaculates. Semen from six sexually mature boars were collected and mixed to create a total of 18 unique semen samples for system evaluations. Each sample was then diluted to 1:4, 1:8, 1:10, and 1:16 (for concentration only) with Androhep Plus semen extender (n = 82 total). Sperm concentration was evaluated using FE and compared to results measured using a Nucleocounter and computer assisted sperm analysis (CASA: Ceros II, Hamilton Thorne). Sperm motility was evaluated using FE and CASA. Sperm morphological assessments were evaluated by a single technician manually counting abnormalities and compared to FE deep-learning technology. Data were analyzed using both descriptive statistics (mean, standard deviation, intra-assay coefficient of variance, and residual standard deviation [RSD]) and statistical tests (correlation analysis between devices and Bland-Altman methods). Concentration analysis was strongly correlated (n = 18; r > 0.967; P < 0.0001) among all devices and dilutions. Analysis of motility showed moderate correlation and was significant when all dilutions are analyzed together (n = 54; r = 0.558; P < 0.001). The regression analysis for motility also showed the RSD as 3.95% between FE and CASA indicating a tight fit between devices. This RSD indicates that FE can find boars with unacceptable motility (boars for example with less than 70%) which impact fertility and litter size. The Bland-Altman analysis showed that FE-estimated morphological assessment and the conventionally estimated morphological score were similar, with a mean difference of ~1% (%95 Limits of Agreement: -6.2 to 8.1; n = 17). The results of this experiment demonstrate that FE, a portable and automated smartphone-based device, is capable of assessing concentration, motility, and morphology of boar semen samples.

Deep learning-assisted sensitive detection of fentanyl using a bubbling-microchip.

Deep learning-enabled smartphone-based image processing has significant advantages in the development of point-of-care diagnostics. Conventionally, most deep-learning applications require task specific large scale expertly annotated datasets. Therefore, these algorithms are oftentimes limited only to applications that have large retrospective datasets available for network development. Here, we report the possibility of utilizing adversarial neural networks to overcome this challenge by expanding the utility of non-specific data for the development of deep learning models. As a clinical model, we report the detection of fentanyl, a small molecular weight drug that is a type of opioid, at the point-of-care using a deep-learning empowered smartphone assay. We used the catalytic property of platinum nanoparticles (PtNPs) in a smartphone-enabled microchip bubbling assay to achieve high analytical sensitivity (detecting fentanyl at concentrations as low as 0.23 ng mL-1 in phosphate buffered saline (PBS), 0.43 ng mL-1 in human serum and 0.64 ng mL-1 in artificial human urine). Image-based inferences were made by our adversarial-based SPyDERMAN network that was developed using a limited dataset of 104 smartphone images of microchips with bubble signals from tests performed with known fentanyl concentrations and using our retrospective library of 17 573 non-specific bubbling-microchip images. The accuracy (± standard error of mean) of the developed system in determining the presence of fentanyl, when using a cutoff concentration of 1 ng mL-1, was 93 ± 0% in human serum (n = 100) and 95.3 ± 1.5% in artificial human urine (n = 100).

Disabled-2 modulates homotypic and heterotypic platelet interactions by binding to sulfatides.

Disabled-2 (Dab2) inhibits platelet aggregation by competing with fibrinogen for binding to the α(IIb) ß(3) integrin receptor, an interaction that is modulated by Dab2 binding to sulfatides at the outer leaflet of the platelet plasma membrane. The disaggregatory function of Dab2 has been mapped to its N-terminus phosphotyrosine-binding (N-PTB) domain. Our data show that the surface levels of P-selectin, a platelet transmembrane protein known to bind sulfatides and promote cell-cell interactions, are reduced by Dab2 N-PTB, an event that is reversed in the presence of a mutant form of the protein that is deficient in sulfatide but not in integrin binding. Importantly, Dab2 N-PTB, but not its sulfatide binding-deficient form, was able to prevent sulfatide-induced platelet aggregation when tested under haemodynamic conditions in microfluidic devices at flow rates with shear stress levels corresponding to those found in vein microcirculation. Moreover, the regulatory role of Dab2 N-PTB extends to platelet-leucocyte adhesion and aggregation events, suggesting a multi-target role for Dab2 in haemostasis.

Microfluidic mixing using contactless dielectrophoresis.

The first experimental evidence of mixing enhancement in a microfluidic system using contactless dielectrophoresis (cDEP) is presented in this work. Pressure-driven flow of deionized water containing 0.5 µm beads was mixed in various chamber geometries by imposing a dielectrophoresis (DEP) force on the beads. In cDEP the electrodes are not in direct contact with the fluid sample but are instead capacitively coupled to the mixing chamber through thin dielectric barriers, which eliminates many of the problems encountered with standard DEP. Four system designs with rectangular and circular mixing chambers were fabricated in PDMS. Mixing tests were conducted for flow rates from 0.005 to 1 mL/h subject to an alternating current signal range of 0-300 V at 100-600 kHz. When the time scales of the bulk fluid motion and the DEP motion were commensurate, rapid mixing was observed. The rectangular mixing chambers were found to be more efficient than the circular chambers. This approach shows potential for mixing low diffusivity biological samples, which is a very challenging problem in laminar flows at small scales.

Customizing the Protoscolicidal Activity by a Drug Delivery System: Application of Guar Gum in Electrospun Nanofibers.

BACKGROUND: The present study aimed to control mebendazole drug release from ethyl cellulose nanofibers containing guar gum produced by Electrospinning Method (ESM) on mortality of hydatid cyst protoscoleces under laboratory conditions. METHODS: The study was conducted in Arak Islamic Azad University, 2019. After preparation of ethyl cellulose nanofibers containing guar gum with concentrations 10, 250, 50 and 500 ppm with ESM, the uniformity and fineness of nanofibers were investigated by electron microscope. By determining the absorption of nanofibers during 312 h via spectrophotometry method, the amount of drug release was obtained. Then, the mortality of live protoscoleces in-vitro with nanofibers made with different concentrations was studied during 13 days. RESULTS: Guar gum nanofiber with four concentrations of 10, 50, 250 and 500 ppm had 0.78512, 0.83729, 1.0098 and 1.0633 absorption respectively and showed drug release 42.09%, 39.95%, 33.05% and 30.96% after 312 hours. Therefore, the survival of protoscoleces in the presence of guar gum with four concentrations was zero after 3, 6, 11 and 13 days (P<0.05). CONCLUSION: To produce nanofibers carrying the drug for research related to the treatment of hydatid cysts, the electrospinning technique can be considered as a reliable method.

Evaluation of deep convolutional neural networks in classifying human embryo images based on their morphological quality.

A critical factor that influences the success of an in-vitro fertilization (IVF) treatment cycle is the quality of the transferred embryo. Embryo morphology assessments, conventionally performed through manual microscopic analysis suffer from disparities in practice, selection criteria, and subjectivity due to the experience of the embryologist. Convolutional neural networks (CNNs) are powerful, promising algorithms with significant potential for accurate classifications across many object categories. Network architectures and hyper-parameters affect the efficiency of CNNs for any given task. Here, we evaluate multi-layered CNNs developed from scratch and popular deep-learning architectures such as Inception v3, ResNET-50, Inception-ResNET-v2, NASNetLarge, ResNeXt-101, ResNeXt-50, and Xception in differentiating between embryos based on their morphological quality at 113 h post insemination (hpi). Xception performed the best in differentiating between the embryos based on their morphological quality.