Development of deep learning algorithms for predicting blastocyst formation and quality by time-lapse monitoring.
Ontology highlight
ABSTRACT:
SUBMITTER: Liao Q
PROVIDER: S-EPMC7998018 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:STUDY QUESTION:Can a deep learning model predict the probability of pregnancy with fetal heart (FH) from time-lapse videos? SUMMARY ANSWER:We created a deep learning model named IVY, which was an objective and fully automated system that predicts the probability of FH pregnancy directly from raw time-lapse videos without the need for any manual morphokinetic annotation or blastocyst morphology assessment. WHAT IS KNOWN ALREADY:The contribution of time-lapse imaging in effective embryo selection is promising. Existing algorithms for the analysis of time-lapse imaging are based on morphology and morphokinetic parameters that require subjective human annotation and thus have intrinsic inter-reader and intra-reader variability. Deep learning offers promise for the automation and standardization of embryo selection. STUDY DESIGN, SIZE, DURATION:A retrospective analysis of time-lapse videos and clinical outcomes of 10?638 embryos from eight different IVF clinics, across four different countries, between January 2014 and December 2018. PARTICIPANTS/MATERIALS, SETTING, METHODS:The deep learning model was trained using time-lapse videos with known FH pregnancy outcome to perform a binary classification task of predicting the probability of pregnancy with FH given time-lapse video sequence. The predictive power of the model was measured using the average area under the curve (AUC) of the receiver operating characteristic curve over 5-fold stratified cross-validation. MAIN RESULTS AND THE ROLE OF CHANCE:The deep learning model was able to predict FH pregnancy from time-lapse videos with an AUC of 0.93 [95% CI 0.92-0.94] in 5-fold stratified cross-validation. A hold-out validation test across eight laboratories showed that the AUC was reproducible, ranging from 0.95 to 0.90 across different laboratories with different culture and laboratory processes. LIMITATIONS, REASONS FOR CAUTION:This study is a retrospective analysis demonstrating that the deep learning model has a high level of predictability of the likelihood that an embryo will implant. The clinical impacts of these findings are still uncertain. Further studies, including prospective randomized controlled trials, are required to evaluate the clinical significance of this deep learning model. The time-lapse videos collected for training and validation are Day 5 embryos; hence, additional adjustment would need to be made for the model to be used in the context of Day 3 transfer. WIDER IMPLICATIONS OF THE FINDINGS:The high predictive value for embryo implantation obtained by the deep learning model may improve the effectiveness of previous approaches used for time-lapse imaging in embryo selection. This may improve the prioritization of the most viable embryo for a single embryo transfer. The deep learning model may also prove to be useful in providing the optimal order for subsequent transfers of cryopreserved embryos. STUDY FUNDING/COMPETING INTEREST(S):D.T. is the co-owner of Harrison AI that has patented this methodology in association with Virtus Health. P.I. is a shareholder in Virtus Health. S.C., P.I. and D.G. are all either employees or contracted with Virtus Health. D.G. has received grant support from Vitrolife, the manufacturer of the Embryoscope time-lapse imaging used in this study. The equipment and time for this study have been jointly provided by Harrison AI and Virtus Health.
| S-EPMC6554189 | biostudies-literature
Project description:BackgroundTime-lapse imaging combined with embryo morphokinetics may offer a non-invasive means for improving embryo selection. Data from clinics worldwide are necessary to compare and ultimately develop embryo classifications models using kinetic data. The primary objective of this study was to determine if there were kinetic differences between embryos with limited potential and those more often associated with in vitro blastocyst formation and/or implantation. We also wanted to compare putative kinetic markers for embryo selection as proposed by other laboratories to what we were observing in our own laboratory setting.MethodsKinetic data and cycle outcomes were retrospectively analyzed in patients age 39 and younger with 7 or more zygotes cultured in the Embryoscope. Timing of specific events from the point of insemination were determined using time-lapse (TL) imaging. The following kinetic markers were assessed: time to syngamy (tPNf), t2, time to two cells (c), 3c (t3), 4c ( t4), 5c (t5), 8c (t8), morula (tMor), start of blastulation (tSB); tBL, blastocyst (tBL); expanded blastocyst (tEBL). Durations of the second (cc2) and third (cc3) cell cycles, the t5-t2 interval as well as time to complete synchronous divisions s1, s2 and s3 were calculated. Incidence and impact on development of nuclear and cleavage anomalies were also assessed.ResultsA total of 648 embryos transferred on day 5 were analyzed. The clinical pregnancy and implantation rate were 72% and 50%, respectively. Morphokinetic data showed that tPNf, t2,t4, t8, s1, s2,s3 and cc2 were significantly different in embryos forming blastocysts (ET or frozen) versus those with limited potential either failing to blastulate or else forming poor quality blastocysts ,ultimately discarded. Comparison of embryo kinetics in cycles with all embryos implanting (KID+) versus no implantation (KID-) suggested that markers of embryo competence to implant may be different from ability to form a blastocyst. The incidence of multinucleation and reverse cleavage amongst the embryos observed was 25% and 7%, respectively. Over 40% of embryos exhibiting these characteristics did however form blastocysts meeting our criteria for freezing.ConclusionsThese data provide us with a platform with which to potentially enhance embryo selection for transfer.
| S-EPMC4074839 | biostudies-literature
Project description:Many natural and man-made systems are prone to critical transitions-abrupt and potentially devastating changes in dynamics. Deep learning classifiers can provide an early warning signal for critical transitions by learning generic features of bifurcations from large simulated training data sets. So far, classifiers have only been trained to predict continuous-time bifurcations, ignoring rich dynamics unique to discrete-time bifurcations. Here, we train a deep learning classifier to provide an early warning signal for the five local discrete-time bifurcations of codimension-one. We test the classifier on simulation data from discrete-time models used in physiology, economics and ecology, as well as experimental data of spontaneously beating chick-heart aggregates that undergo a period-doubling bifurcation. The classifier shows higher sensitivity and specificity than commonly used early warning signals under a wide range of noise intensities and rates of approach to the bifurcation. It also predicts the correct bifurcation in most cases, with particularly high accuracy for the period-doubling, Neimark-Sacker and fold bifurcations. Deep learning as a tool for bifurcation prediction is still in its nascence and has the potential to transform the way we monitor systems for critical transitions.
| S-EPMC10564974 | biostudies-literature
Project description:BackgroundIn this paper, we examine whether machine learning and deep learning can be used to predict difficult airway intubation in patients undergoing thyroid surgery.MethodsWe used 10 machine learning and deep learning algorithms to establish a corresponding model through a training group, and then verify the results in a test group. We used R for the statistical analysis and constructed the machine learning prediction model in Python.ResultsThe top 5 weighting factors for difficult airways identified by the average algorithm in machine learning were age, sex, weight, height, and BMI. In the training group, the AUC values and accuracy and the Gradient Boosting precision were 0.932, 0.929, and 100%, respectively. As for the modeled effects of predicting difficult airways in test groups, among the models constructed by the 10 algorithms, the three algorithms with the highest AUC values were Gradient Boosting, CNN, and LGBM, with values of 0.848, 0.836, and 0.812, respectively; In addition, among the algorithms, Gradient Boosting had the highest accuracy with a value of 0.913; Additionally, among the algorithms, the Gradient Boosting algorithm had the highest precision with a value of 100%.ConclusionAccording to our results, Gradient Boosting performed best overall, with an AUC >0.8, an accuracy >90%, and a precision of 100%. Besides, the top 5 weighting factors identified by the average algorithm in machine learning for difficult airways were age, sex, weight, height, and BMI.
| S-EPMC9399522 | biostudies-literature
Project description:Ecological biodiversity is declining at an unprecedented rate. To combat such irreversible changes in natural ecosystems, biodiversity conservation initiatives are being conducted globally. However, the lack of a feasible methodology to quantify biodiversity in real-time and investigate population dynamics in spatiotemporal scales prevents the use of ecological data in environmental planning. Traditionally, ecological studies rely on the census of an animal population by the "capture, mark and recapture" technique. In this technique, human field workers manually count, tag and observe tagged individuals, making it time-consuming, expensive, and cumbersome to patrol the entire area. Recent research has also demonstrated the potential for inexpensive and accessible sensors for ecological data monitoring. However, stationary sensors collect localised data which is highly specific on the placement of the setup. In this research, we propose the methodology for biodiversity monitoring utilising state-of-the-art deep learning (DL) methods operating in real-time on sample payloads of mobile robots. Such trained DL algorithms demonstrate a mean average precision (mAP) of 90.51% in an average inference time of 67.62 milliseconds within 6,000 training epochs. We claim that the use of such mobile platform setups inferring real-time ecological data can help us achieve our goal of quick and effective biodiversity surveys. An experimental test payload is fabricated, and online as well as offline field surveys are conducted, validating the proposed methodology for species identification that can be further extended to geo-localisation of flora and fauna in any ecosystem.
| S-EPMC10495972 | biostudies-literature
Project description:Early identification of pathogenic bacteria in food, water, and bodily fluids is very important and yet challenging, owing to sample complexities and large sample volumes that need to be rapidly screened. Existing screening methods based on plate counting or molecular analysis present various tradeoffs with regard to the detection time, accuracy/sensitivity, cost, and sample preparation complexity. Here, we present a computational live bacteria detection system that periodically captures coherent microscopy images of bacterial growth inside a 60-mm-diameter agar plate and analyses these time-lapsed holograms using deep neural networks for the rapid detection of bacterial growth and the classification of the corresponding species. The performance of our system was demonstrated by the rapid detection of Escherichia coli and total coliform bacteria (i.e., Klebsiella aerogenes and Klebsiella pneumoniae subsp. pneumoniae) in water samples, shortening the detection time by >12 h compared to the Environmental Protection Agency (EPA)-approved methods. Using the preincubation of samples in growth media, our system achieved a limit of detection (LOD) of ~1 colony forming unit (CFU)/L in ≤9 h of total test time. This platform is highly cost-effective (~$0.6/test) and has high-throughput with a scanning speed of 24 cm2/min over the entire plate surface, making it highly suitable for integration with the existing methods currently used for bacteria detection on agar plates. Powered by deep learning, this automated and cost-effective live bacteria detection platform can be transformative for a wide range of applications in microbiology by significantly reducing the detection time and automating the identification of colonies without labelling or the need for an expert.
| S-EPMC7351775 | biostudies-literature
Project description:PurposeTo evaluate high accumulation of coronary artery calcium (CAC) from retinal fundus images with deep learning technologies as an inexpensive and radiation-free screening method.MethodsIndividuals who underwent bilateral retinal fundus imaging and CAC score (CACS) evaluation from coronary computed tomography scans on the same day were identified. With this database, performances of deep learning algorithms (inception-v3) to distinguish high CACS from CACS of 0 were evaluated at various thresholds for high CACS. Vessel-inpainted and fovea-inpainted images were also used as input to investigate areas of interest in determining CACS.ResultsA total of 44,184 images from 20,130 individuals were included. A deep learning algorithm for discrimination of no CAC from CACS >100 achieved area under receiver operating curve (AUROC) of 82.3% (79.5%-85.0%) and 83.2% (80.2%-86.3%) using unilateral and bilateral fundus images, respectively, under a 5-fold cross validation setting. AUROC increased as the criterion for high CACS was increased, showing a plateau at 100 and losing significant improvement thereafter. AUROC decreased when fovea was inpainted and decreased further when vessels were inpainted, whereas AUROC increased when bilateral images were used as input.ConclusionsVisual patterns of retinal fundus images in subjects with CACS > 100 could be recognized by deep learning algorithms compared with those with no CAC. Exploiting bilateral images improves discrimination performance, and ablation studies removing retinal vasculature or fovea suggest that recognizable patterns reside mainly in these areas.Translational relevanceRetinal fundus images can be used by deep learning algorithms for prediction of high CACS.
| S-EPMC7410115 | biostudies-literature
Project description:Despite recent improvements in microscope technologies, segmenting and tracking cells in three-dimensional time-lapse images (3D + T images) to extract their dynamic positions and activities remains a considerable bottleneck in the field. We developed a deep learning-based software pipeline, 3DeeCellTracker, by integrating multiple existing and new techniques including deep learning for tracking. With only one volume of training data, one initial correction, and a few parameter changes, 3DeeCellTracker successfully segmented and tracked ~100 cells in both semi-immobilized and 'straightened' freely moving worm's brain, in a naturally beating zebrafish heart, and ~1000 cells in a 3D cultured tumor spheroid. While these datasets were imaged with highly divergent optical systems, our method tracked 90-100% of the cells in most cases, which is comparable or superior to previous results. These results suggest that 3DeeCellTracker could pave the way for revealing dynamic cell activities in image datasets that have been difficult to analyze.
| S-EPMC8009680 | biostudies-literature
Project description:Live cell segmentation is a crucial step in biological image analysis and is also a challenging task because time-lapse microscopy cell sequences usually exhibit complex spatial structures and complicated temporal behaviors. In recent years, numerous deep learning based methods have been proposed to tackle this task and obtained promising results. However, designing a network with excellent performance requires professional knowledge and expertise and is very time-consuming and labor-intensive. Recently emerged neural architecture search (NAS) methods hold great promise in eliminating these disadvantages, because they can automatically search an optimal network for the task. We propose a novel NAS based solution for deep-learning based cell segmentation in time-lapse microscopy images. Different from current NAS methods, we propose 1) jointly searching non-repeatable micro architectures to construct the macro network for exploring greater NAS potential and better performance and 2) defining a specific search space suitable for the live cell segmentation task, including the incorporation of a convolutional long short-term memory network for exploring the temporal information in time-lapse sequences. Comprehensive evaluations on the 2D datasets from the cell tracking challenge demonstrate the competitiveness of the proposed method compared to the state of the art. The experimental results show that the method is capable of achieving more consistent top performance across all ten datasets than the other challenge methods. The executable files of the proposed method as well as configurations for each dataset used in the presented experiments will be available for non-commercial purposes from https://github.com/291498346/nas_cellseg. Supplementary data are available at Bioinformatics online.
| S-EPMC8665766 | biostudies-literature
Project description:BackgroundIntraoperative physiological monitoring generates a large quantity of time-series data that might be associated with postoperative outcomes. Using a deep learning model based on intraoperative time-series monitoring data to predict postoperative quality of recovery has not been previously reported.MethodsPerioperative data from female patients having laparoscopic hysterectomy were prospectively collected. Deep learning, logistic regression, support vector machine, and random forest models were trained using different datasets and evaluated by 5-fold cross-validation. The quality of recovery on postoperative day 1 was assessed using the Quality of Recovery-15 scale. The quality of recovery was dichotomized into satisfactory if the score ≥122 and unsatisfactory if <122. Models' discrimination was estimated using the area under the receiver operating characteristics curve (AUROC). Models' calibration was visualized using the calibration plot and appraised by the Brier score. The SHapley Additive exPlanation (SHAP) approach was used to characterize different input features' contributions.ResultsData from 699 patients were used for modeling. When using preoperative data only, all four models exhibited poor performance (AUROC ranging from 0.65 to 0.68). The inclusion of the intraoperative intervention and/or monitoring data improved the performance of the deep leaning, logistic regression, and random forest models but not the support vector machine model. The AUROC of the deep learning model based on the intraoperative monitoring data only was 0.77 (95% CI, 0.72-0.81), which was indistinct from that based on the intraoperative intervention data only (AUROC, 0.79; 95% CI, 0.75-0.82) and from that based on the preoperative, intraoperative intervention, and monitoring data combined (AUROC, 0.81; 95% CI, 0.78-0.83). In contrast, when using the intraoperative monitoring data only, the logistic regression model had an AUROC of 0.72 (95% CI, 0.68-0.77), and the random forest model had an AUROC of 0.74 (95% CI, 0.73-0.76). The Brier score of the deep learning model based on the intraoperative monitoring data was 0.177, which was lower than that of other models.ConclusionsDeep learning based on intraoperative time-series monitoring data can predict post-hysterectomy quality of recovery. The use of intraoperative monitoring data for outcome prediction warrants further investigation.Trial registrationThis trial (Identifier: NCT03641625 ) was registered at ClinicalTrials.gov by the principal investigator, Lingzhong Meng, on August 22, 2018.
| S-EPMC8022389 | biostudies-literature