Automatic Assessment Research Articles

Automatic ploidy prediction and quality assessment of human blastocysts using time-lapse imaging

Assessing fertilized human embryos is crucial for in vitro fertilization, a task being revolutionized by artificial intelligence. Existing models used for embryo quality assessment and ploidy detection could be significantly improved by effectively utilizing time-lapse imaging to identify critical developmental time points for maximizing prediction accuracy. Addressing this, we develop and compare various embryo ploidy status prediction models across distinct embryo development stages. We present BELA, a state-of-the-art ploidy prediction model that surpasses previous image- and video-based models without necessitating input from embryologists. BELA uses multitask learning to predict quality scores that are thereafter used to predict ploidy status. By achieving an area under the receiver operating characteristic curve of 0.76 for discriminating between euploidy and aneuploidy embryos on the Weill Cornell dataset, BELA matches the performance of models trained on embryologists’ manual scores. While not a replacement for preimplantation genetic testing for aneuploidy, BELA exemplifies how such models can streamline the embryo evaluation process.

Automated condylar seating assessment using a deep learning-based three-step approach

ObjectivesIn orthognatic surgery, one of the primary determinants for reliable three-dimensional virtual surgery planning (3D VSP) and an accurate transfer of 3D VSP to the patient in the operation room is the condylar seating. Incorrectly seated condyles would primarily affect the accuracy of maxillary-first bimaxillary osteotomies as the maxillary repositioning is dependent on the positioning of the mandible in the cone-beam computed tomography (CBCT) scan. This study aimed to develop and validate a novel tool by utilizing a deep learning algorithm that automatically evaluates the condylar seating based on CBCT images as a proof of concept.Materials and methodsAs a reference, 60 CBCT scans (120 condyles) were labeled. The automatic assessment of condylar seating included three main parts: segmentation module, ray-casting, and feed-forward neural network (FFNN). The AI-based algorithm was trained and tested using fivefold cross validation. The method’s performance was evaluated by comparing the labeled ground truth with the model predictions on the validation dataset.ResultsThe model achieved an accuracy of 0.80, positive predictive value of 0.61, negative predictive value of 0.9 and F1-score of 0.71. The sensitivity and specificity of the model was 0.86 and 0.78, respectively. The mean AUC over all folds was 0.87.ConclusionThe innovative integration of multi-step segmentation, ray-casting and a FFNN demonstrated to be a viable approach for automating condylar seating assessment and have obtained encouraging results.Clinical relevanceAutomated condylar seating assessment using deep learning may improve orthognathic surgery, preventing errors and enhancing patient outcomes in maxillary-first bimaxillary osteotomies.

Automated identification of building features with deep learning for risk analysis

Accurate and up-to-date information about the building stock is fundamental to better understand and mitigate the impact caused by catastrophic earthquakes, as seen recently in Turkey, Syria, Morocco and Afghanistan. Planning for such events is necessary to increase the resilience of the building stock and to minimize casualties and economic losses. Although in several parts of the world new constructions follow more strict compliance with modern seismic codes, a large proportion of existing building stock still demands a more detailed and automated vulnerability analysis. Hence, this paper proposes the use of computer vision deep learning models to automatically classify buildings and create large scale (city or region) exposure models. Such approach promotes the use of open databases covering most cities in the world (cf. OpenStreetMap, Google Street View, Bing Maps and satellite imagery), Therefore providing valuable geographical, topological and image data that may cheaply be used to extract valuable information to feed exposure models. Our previous work using deep learning models achieved, in line with the results from other projects, high classification accuracy concerning building materials and number of storeys. This paper extends the approach by: (i) implementing four CNN-based models to perform classification of three sets of different/extended buildings’ characteristics; (ii) training and comparing the performance of the four models for each of the sets; (iii) comparing the risk assessment results based on data extracted from the best CNN-based model against the results obtained with traditional ground data. In brief, the best accuracy obtained with the three tested sets of buildings’ characteristics is higher than 80%. Moreover, it is shown that the error resulting from using exposure models fed by automatic classification is not only acceptable, but also far outweighs the time and costs of obtaining a manual and specialised classification of building stocks. Finally, we recognize that automatic assessment of certain complex buildings’ characteristics compares to similar limitations of traditional assessments performed by specialized civil engineers, typically related with the identification of the number of storeys and the construction material. However, the identified limitations do not show worse results when compared against the use of manual buildings’ assessment.

Deep learning based approach: automated gingival inflammation grading model using gingival removal strategy

Gingival inflammation grade serves as a well-established index in periodontitis. The aim of this study was to develop a deep learning network utilizing a novel feature extraction method for the automatic assessment of gingival inflammation. T-distributed Stochastic Neighbor Embedding (t-SNE) was utilized for dimensionality reduction. A convolutional neural network (CNN) model based on DenseNet was developed for the identification and evaluation of gingival inflammation. To enhance the performance of the deep learning (DL) model, a novel teeth removal algorithm was implemented. Additionally, a Grad-CAM + + encoder was applied to generate heatmaps for computer visual attention analysis. The mean Intersection over Union (MIoU) for the identification of gingivitis was 0.727 ± 0.117. The accuracy rates for the five inflammatory degrees were 77.09%, 77.25%, 74.38%, 73.68% and 79.22%. The Area Under the Receiver Operating Characteristic (AUROC) values were 0.83, 0.80, 0.81, 0.81 and 0.84, respectively. The attention ratio towards gingival tissue increased from 37.73% to 62.20%, and within 8 mm of the gingival margin, it rose from 21.11% to 38.23%. On the gingiva, the overall attention ratio increased from 51.82% to 78.21%. The proposed DL model with novel feature extraction method provides high accuracy and sensitivity for identifying and grading gingival inflammation.

Automatic rehabilitation exercise task assessment of stroke patients based on wearable sensors with a lightweight multichannel 1D-CNN model

Approximately 75% of stroke survivors have movement dysfunction. Rehabilitation exercises are capable of improving physical coordination. They are mostly conducted in the home environment without guidance from therapists. It is impossible to provide timely feedback on exercises without suitable devices or therapists. Human action quality assessment in the home setting is a challenging topic for current research. In this paper, a low-cost HREA system in which wearable sensors are used to collect upper limb exercise data and a multichannel 1D-CNN framework is used to automatically assess action quality. The proposed 1D-CNN model is first pretrained on the UCI-HAR dataset, and it achieves a performance of 91.96%. Then, five typical actions were selected from the Fugl-Meyer Assessment Scale for the experiment, wearable sensors were used to collect the participants’ exercise data, and experienced therapists were employed to assess participants’ exercise at the same time. Following the above process, a dataset was built based on the Fugl-Meyer scale. Based on the 1D-CNN model, a multichannel 1D-CNN model was built, and the model using the Naive Bayes fusion had the best performance (precision: 97.26%, recall: 97.22%, F1-score: 97.23%) on the dataset. This shows that the HREA system provides accurate and timely assessment, which can provide real-time feedback for stroke survivors’ home rehabilitation.

Advancing the integration of biosignal-based automated pain assessment methods into a comprehensive model for addressing cancer pain

BackgroundTailoring effective strategies for cancer pain management requires a careful analysis of multiple factors that influence pain phenomena and, ultimately, guide the therapy. While there is a wealth of research on automatic pain assessment (APA), its integration with clinical data remains inadequately explored. This study aimed to address the potential correlations between subjective and APA-derived objectives variables in a cohort of cancer patients.MethodsA multidimensional statistical approach was employed. Demographic, clinical, and pain-related variables were examined. Objective measures included electrodermal activity (EDA) and electrocardiogram (ECG) signals. Sensitivity analysis, multiple factorial analysis (MFA), hierarchical clustering on principal components (HCPC), and multivariable regression were used for data analysis.ResultsThe study analyzed data from 64 cancer patients. MFA revealed correlations between pain intensity, type, Eastern Cooperative Oncology Group Performance status (ECOG), opioids, and metastases. Clustering identified three distinct patient groups based on pain characteristics, treatments, and ECOG. Multivariable regression analysis showed associations between pain intensity, ECOG, type of breakthrough cancer pain, and opioid dosages. The analyses failed to find a correlation between subjective and objective pain variables.ConclusionsThe reported pain perception is unrelated to the objective variables of APA. An in-depth investigation of APA is required to understand the variables to be studied, the operational modalities, and above all, strategies for appropriate integration with data obtained from self-reporting.Trial registrationThis study is registered with ClinicalTrials.gov, number (NCT04726228), registered 27 January 2021, https://classic.clinicaltrials.gov/ct2/show/NCT04726228?term=nct04726228&draw=2&rank=1

Automatic assessment of the fatigue life of cables of cable‐stayed bridges by on‐line monitoring

Automatic assessment of the fatigue life of cables of cable‐stayed bridges by on‐line monitoring

Rapid post-disaster assessment of residential buildings using Unmanned Aerial Vehicles

Disasters impose significant costs on the built environment due to extensive damages. Accelerated by climate change, disasters such as hurricanes have recently become more frequent and destructive, underscoring the need for rapid post-disaster assessments toward swift search and rescue efforts and damage evaluations. In this regard, this study proposes an image-processing-based method employed on Unmanned Aerial Vehicle (UAV) imagery for automatic assessment of post-disaster damaged buildings. The proposed approach integrates texture-based features, including dissimilarity and homogeneity, along with edge-based features, for which Canny edge detection is employed. The edge-based features introduce novel indices representing the level of irregularity by assessing the entropy as well as the uniformity in the distribution of edge angles. The proposed features are fed into a Naïve Bayesian Classification process to classify damaged and undamaged classes, which makes it possible to account for the underlying uncertainties. The proposed method demonstrates a validation accuracy of 89.3 percent using real-life post-disaster images, effectively distinguishing between damaged and undamaged houses. The findings underscore the potential of employing UAV-captured images and advanced image processing techniques for rapid and accurate post-disaster damage assessment.

Automatic Quality Assessment of Pork Belly via Deep Learning and Ultrasound Imaging.

Pork belly, prized for its unique flavor and texture, is often overlooked in breeding programs that prioritize lean meat production. The quality of pork belly is determined by the number and distribution of muscle and fat layers. This study aimed to assess the number of pork belly layers using deep learning techniques. Initially, semantic segmentation was considered, but the intersection over union (IoU) scores for the segmented parts were below 70%, which is insufficient for practical application. Consequently, the focus shifted to image classification methods. Based on the number of fat and muscle layers, a dataset was categorized into three groups: three layers (n = 1811), five layers (n = 1294), and seven layers (n = 879). Drawing upon established model architectures, the initial model was refined for the task of learning and predicting layer traits from B-ultrasound images of pork belly. After a thorough evaluation of various performance metrics, the ResNet18 model emerged as the most effective, achieving a remarkable training set accuracy of 99.99% and a validation set accuracy of 96.22%, with corresponding loss values of 0.1478 and 0.1976. The robustness of the model was confirmed through three interpretable analysis methods, including grad-CAM, ensuring its reliability. Furthermore, the model was successfully deployed in a local setting to process B-ultrasound video frames in real time, consistently identifying the pork belly layer count with a confidence level exceeding 70%. By employing a scoring system with 100 points as the threshold, the number of pork belly layers in vivo was categorized into superior and inferior grades. This innovative system offers immediate decision-making support for breeding determinations and presents a highly efficient and precise method for assessment of pork belly layers.

A dataset of synthetic art dialogues with ChatGPT

This paper introduces Art_GenEvalGPT, a novel dataset of synthetic dialogues centered on art generated through ChatGPT. Unlike existing datasets focused on conventional art-related tasks, Art_GenEvalGPT delves into nuanced conversations about art, encompassing a wide variety of artworks, artists, and genres, and incorporating emotional interventions, integrating speakers’ subjective opinions and different roles for the conversational agents (e.g., teacher-student, expert guide, anthropic behavior or handling toxic users). Generation and evaluation stages of GenEvalGPT platform are used to create the dataset, which includes 13,870 synthetic dialogues, covering 799 distinct artworks, 378 different artists, and 26 art styles. Automatic and manual assessment proof the high quality of the synthetic dialogues generated. For the profile recovery, promising lexical and semantic metrics for objective and factual attributes are offered. For subjective attributes, the evaluation for detecting emotions or subjectivity in the interventions achieves 92% of accuracy using LLM-self assessment metrics.

Deep learning-based fully automatic Risser stage assessment model using abdominal radiographs.

Artificial intelligence has been increasingly used in medical imaging and has demonstrated expert level performance in image classification tasks. To develop a fully automatic approach for determining the Risser stage using deep learning on abdominal radiographs. In this multicenter study, 1,681 supine abdominal radiographs (age range, 9-18years, 50% female) obtained between January 2019 and April 2022 were collected retrospectively from three medical institutions and graded manually using the United States Risser staging system. A total of 1,577 images from Hospitals 1 and 2 were used for development, and 104 images from Hospital 3 for external validation. From each radiograph, right and left iliac crest patch images were extracted using the pelvic bone segmentation model DeepLabv3 + with the EfficientNet-B0 encoder trained with 90 digitally reconstructed radiographs from pelvic computed tomography scans with a pelvic bone mask. Using these patch images, ConvNeXt-B was trained to grade according to the Risser classification. The model's performance was evaluated using accuracy, area under the receiver operating characteristic curve (AUROC), and mean absolute error. The fully automatic Risser stage assessment model showed an accuracy of 0.87 and 0.75, mean absolute error of 0.13 and 0.26, and AUROC of 0.99 and 0.95 on internal and external test sets, respectively. We developed a deep learning-based, fully automatic segmentation and classification model for Risser stage assessment using abdominal radiographs.

Automatic Optic Nerve Assessment From Transorbital Ultrasound Images: A Deep Learning-based Approach.

Transorbital Ultrasonography (TOS) is a promising imaging technology that can be used to characterize the structures of the optic nerve and the potential alterations that may occur in those structures as a result of an increase in intracranial pressure (ICP) or the presence of other disorders such as multiple sclerosis (MS) and hydrocephalus. In this paper, the primary objective is to develop a fully automated system that is capable of segmenting and calculating the diameters of structures that are associated with the optic nerve in TOS images. These structures include the optic nerve diameter sheath (ONSD) and the optic nerve diameter (OND). A fully convolutional neural network (FCN) model that has been pre-trained serves as the foundation for the segmentation method. The method that was developed was utilized to collect 464 different photographs from 110 different people, and it was accomplished with the assistance of four distinct pieces of apparatus. An examination was carried out to compare the outcomes of the automatic measurements with those of a manual operator. Both OND and ONSD have a typical inaccuracy of -0.12 0.32 mm and 0.14 0.58 mm, respectively, when compared to the operator. The Pearson correlation coefficient (PCC) for OND is 0.71, while the coefficient for ONSD is 0.64, showing that there is a positive link between the two measuring tools. A conclusion may be drawn that the technique that was developed is automatic, and the average error (AE) that was reached for the ONSD measurement is compatible with the ranges of inter-operator variability that have been discovered in the literature.

Comparative evaluation of image-based vs. text-based vs. multimodal AI approaches for automatic breast density assessment in mammograms

Background and objectivesIn the last decade, there has been a growing interest in applying artificial intelligence (AI) systems to breast cancer assessment, including breast density evaluation. However, few models have been developed to integrate textual mammographic reports and mammographic images. Our aims are (1) to generate a natural language processing (NLP)-based AI system, (2) to evaluate an external image-based software, and (3) to develop a multimodal system, using the late fusion approach, by integrating image and text inferences for the automatic classification of breast density according to the American College of Radiology (ACR) guidelines in mammograms and radiological reports. MethodsWe first compared different NLP models, three based on n-gram term frequency – inverse document frequency and two transformer-based architectures, using 1533 unstructured mammogram reports as a training set and 303 reports as a test set. Subsequently, we evaluated an external image-based software using 303 mammogram images. Finally, we assessed our multimodal system taking into account both text and mammogram images. ResultsOur best NLP model achieved 88 % accuracy, while the external software and the multimodal system achieved 75 % and 80 % accuracy, respectively, in classifying ACR breast densities. ConclusionAlthough our multimodal system outperforms the image-based tool, it currently does not improve the results offered by the NLP model for ACR breast density classification. Nevertheless, the promising results observed here open the possibility to more comprehensive studies regarding the utilization of multimodal tools in the assessment of breast density.

Validation of a novel, low-fidelity virtual reality simulator and an artificial intelligence assessment approach for peg transfer laparoscopic training

Simulators are widely used in medical education, but objective and automatic assessment is not feasible with low-fidelity simulators, which can be solved with artificial intelligence (AI) and virtual reality (VR) solutions. The effectiveness of a custom-made VR simulator and an AI-based evaluator of a laparoscopic peg transfer exercise was investigated. Sixty medical students were involved in a single-blinded randomised controlled study to compare the VR simulator with the traditional box trainer. A total of 240 peg transfer exercises from the Fundamentals of Laparoscopic Surgery programme were analysed. The experts and AI-based software used the same criteria for evaluation. The algorithm detected pitfalls and measured exercise duration. Skill improvement showed no significant difference between the VR and control groups. The AI-based evaluator exhibited 95% agreement with the manual assessment. The average difference between the exercise durations measured by the two evaluation methods was 2.61 s. The duration of the algorithmic assessment was 59.47 s faster than the manual assessment. The VR simulator was an effective alternative practice compared with the training box simulator. The AI-based evaluation produced similar results compared with the manual assessment, and it could significantly reduce the evaluation time. AI and VR could improve the effectiveness of basic laparoscopic training.

Automatic Pronunciation Assessment Systems for English Students from Argentina

Automatic Pronunciation Assessment Systems for English Students from Argentina

Automatic quality assessment of knee radiographs using knowledge graphs and convolutional neural networks.

X-ray radiography is a widely used imaging technique worldwide, and its image quality directly affects diagnostic accuracy. Therefore, X-ray image quality control (QC) is essential. However, subjectively assessing image quality is inefficient and inconsistent, especially when large amounts of image data are being evaluated. Thus, subjective assessment cannot meet current QC needs. To meet current QC needs and improve the efficiency of image quality assessment, a complete set of quality assessment criteria must be established and implemented using artificial intelligence (AI) technology. Therefore, we proposed a multi-criteria AI system for automatically assessing the image quality of knee radiographs. A knee radiograph QC knowledge graph containing 16 "acquisition technique" labels representing 16 image quality defects and five "clarity" labels representing five grades of clarity were developed. Ten radiographic technologists conducted three rounds of QC based on this graph. The single-person QC results were denoted as QC1 and QC2, and the multi-person QC results were denoted as QC3. Each technologist labeled each image only once. The ResNet model structure was then used to simultaneously perform classification (detection of image quality defects) and regression (output of a clarity score) tasks to construct an image QC system. The QC3 results, comprising 4324 anteroposterior and lateral knee radiographs, were used for model training (70% of the images), validation (10%), and testing (20%). The 865 test set data were used to evaluate the effectiveness of the AI model, and an AI QC result, QC4, was automatically generated by the model after training. Finally, using a double-blind method, the senior QC expert reviewed the final QC results of the test set with reference to the results QC3 and QC4 and used them as a reference standard to evaluate the performance of the model. The precision and mean absolute error (MAE) were used to evaluate the quality of all the labels in relation to the reference standard. For the 16 "acquisition technique" features, QC4 exhibited the highest weighted average precision (98.42%±0.81%), followed by QC3 (91.39%±1.35%), QC2 (87.84%±1.68%), and QC1 (87.35%±1.71%). For the image clarity features, the MAEs between QC1, QC2, QC3, and QC4 and the reference standard were 0.508±0.021, 0.475±0.019, 0.237±0.016, and 0.303±0.018, respectively. The experimental results show that our automated quality assessment system performed well in classifying the acquisition technique used for knee radiographs. The image clarity quality evaluation accuracy of the model must be further improved but is generally close to that of radiographic technologists. Intelligent QC methods using knowledge graphs and convolutional neural networks have the potential for clinical applications.

Automatic assessment of body composition in children with lymphoma: results of a [18F]FDG-PET/MR study.

To use Dixon-MR images extracted from [18F]FDG-PET/MR scans to perform an automatic, volumetric segmentation and quantification of body composition in pediatric patients with lymphoma. Pediatric patients with lymphoma examined by [18F]FDG-PET/MR at diagnosis and restaging were included. At each time point, axial fat and water Dixon T1w images of the thighs were automatically segmented and muscle volume, subcutaneous, intramuscular, and intermuscular fat volume were quantified. The metabolic activity of the largest nodal lesion and of muscles and subcutaneous fat was recorded. The paired samples t-test and Spearman's correlation coefficient were applied to evaluate potential differences between the two time points and the relationship between metabolic and body composition metrics, respectively. By logistic regression analysis, the prognostic role of the investigated variables was assessed. The applied significance level was p < 0.05 for all analyses. Thirty-seven patients (mean age ± SD 14 ± 3-years-old; 20 females) matched the inclusion criteria. After chemotherapy (interval between the two PET/MR scans, 56-80 days; median 65 days), muscle volume significantly decreased (629 ± 259 cm3 vs 567 ± 243 cm3, p < 0.001) while subcutaneous, intramuscular and intermuscular fat increased (476 ± 255 cm3 vs 607 ± 254 cm3, p < 0.001; 63 ± 20 cm3 vs 76 ± 26 cm3, p < 0.001; 58 ± 19 cm3 vs 71 ± 23 cm3, p < 0.001); the metabolic activity of the main nodal lesion, muscles, and subcutaneous fat significantly decreased (p < 0.05, each). None of the examined variables acted as predictors of the response to treatment (p = 0.283). A strong correlation between BMI and subcutaneous fat volume at diagnosis (r = 0.675, p < 0.001) and restaging (r = 0.600, p < 0.001) emerged. The proposed method demonstrated that pediatric patients with lymphoma undergo muscle loss and an increase of subcutaneous fat during treatment. The proposed automatic and volumetric MR-based assessment of body composition in children with lymphoma can be used to monitor the effect of chemotherapy and may guide tailored exercise programs during chemotherapy. T1w Dixon images can be used for the automatic segmentation and quantification of body composition. Muscle and subcutaneous fat volume do not act as predictors of the response to treatment in children with lymphoma. Chemotherapy induces changes in body composition in children with lymphoma.

Automatic Clinical Assessment of Swallowing Behavior and Diagnosis of Silent Aspiration Using Wireless Multimodal Wearable Electronics.

Dysphagia is more common in conditions such as stroke, Parkinson's disease, and head and neck cancer. This can lead to pneumonia, choking, malnutrition, and dehydration. Currently, the diagnostic gold standard uses radiologic imaging, the videofluoroscopic swallow study (VFSS); however, it is expensive and necessitates specialized facilities and trained personnel. Although several devices attempt to address the limitations, none offer the clinical-grade quality and accuracy of the VFSS. Here, this study reports a wireless multimodal wearable system with machine learning for automatic, accurate clinical assessment of swallowing behavior and diagnosis of silent aspirations from dysphagia patients. The device includes a kirigami-structured electrode that suppresses changes in skin contact impedance caused by movements and a microphone with a gel layer that effectively blocks external noise for measuring high-quality electromyograms and swallowing sounds. The deep learning algorithm offers the classification of swallowing patterns while diagnosing silent aspirations, with an accuracy of 89.47%. The demonstration with post-stroke patients captures the system's significance in measuring multiple physiological signals in real-time for detecting swallowing disorders, validated by comparing them with the VFSS. The multimodal electronics can ensure a promising future for dysphagia healthcare and rehabilitation therapy, providing an accurate, non-invasive alternative for monitoring swallowing and aspiration events.

Quantifying impairment and disease severity using AI models trained on healthy subjects

Automatic assessment of impairment and disease severity is a key challenge in data-driven medicine. We propose a framework to address this challenge, which leverages AI models trained exclusively on healthy individuals. The COnfidence-Based chaRacterization of Anomalies (COBRA) score exploits the decrease in confidence of these models when presented with impaired or diseased patients to quantify their deviation from the healthy population. We applied the COBRA score to address a key limitation of current clinical evaluation of upper-body impairment in stroke patients. The gold-standard Fugl-Meyer Assessment (FMA) requires in-person administration by a trained assessor for 30-45 minutes, which restricts monitoring frequency and precludes physicians from adapting rehabilitation protocols to the progress of each patient. The COBRA score, computed automatically in under one minute, is shown to be strongly correlated with the FMA on an independent test cohort for two different data modalities: wearable sensors (ρ = 0.814, 95% CI [0.700,0.888]) and video (ρ = 0.736, 95% C.I [0.584, 0.838]). To demonstrate the generalizability of the approach to other conditions, the COBRA score was also applied to quantify severity of knee osteoarthritis from magnetic-resonance imaging scans, again achieving significant correlation with an independent clinical assessment (ρ = 0.644, 95% C.I [0.585,0.696]).

O-297 Prediction of pregnancy outcomes of single vitrified-warmed blastocyst transfer using combination of an automatic classification algorithm applied on cleavage stage embryos and blastocyst morphology

Abstract Study question Does combination of embryo assessment algorithm on cleavage-stage based on the automatic annotation of morphokinetic and blastocyst morphology in embryo selection improve implantation outcomes? Summary answer Combination of embryo assessment algorithm on cleavage-stage based on the automatic morphokinetic annotation and blastocyst morphological evaluation was showed significantly predictive for implantation outcomes. What is known already Conventional morphological assessment is still the gold standard for embryo selection. Timelapse monitoring of embryo development may represent a superior way to culture and select embryos in vitro. Nowadays, time-lapse culture systems are becoming more popular, many algorithms have been developed for embryo selection based on embryo morphokinetics, providing additional information for morphological assessment. However, manual annotations of developmental events and application of algorithms can be time-consuming and subjective processes. Automation of morphokinetic annotation can be a potential approach that reduces subjectivity in embryo selection. Study design, size, duration The observational, retrospective study was conducted in a single centre between 2020-2023 and included 511 single vitrified-warmed blastocyst transfer cycles. Blastocyst selected for transfer on Day 5,6 based on conventional morphological evaluation. Embryos were evaluated on Day 3 with a score from 1 (best) to 5 (worst) (from highest to lowest developmental potential) by the automatic embryo assessment algorithm. The correlation of the algorithms scoring and pregnancy outcomes was qualified by generalized estimating equations (GEEs). Participants/materials, setting, methods Embryos were cultured in timelapse GERI incubator and classified on day 3 by automatic embryo assessment algorithm depending on four parameters: P2 (t3-t2), P3 (t4-t3), oocyte age, and number of cells. The correlation of the algorithms scoring and pregnancy outcomes was qualified by generalized estimating equations (GEEs). Three GEE model using embryo assessment algorithm, conventional morphological assessment, and a combination of both classification system as the predictor were compared. Main results and the role of chance The implantation rate was higher with lower the scores generated by the embryo assessment algorithm. A GEE model showed the negative association between higher embryo score and lower odds of implantation. The OR of Score 3; 4; 5 vs 1 were 0.335; 0.259; 0.245 (95% CI 0.194-0.580; 0.138-0.485; 0.111-0.544, P = 0.000), respectively, for implantation. The AUC of the model using embryo assessment algorithm for implantation potential = 0.641. The AUC of the model combining both embryo assessment algorithm and conventional morphological assessment for implantation potential = 0.733. The differences were statistically significant (z-statistic = 3.896, p = 0.0001). Limitations, reasons for caution The sample size was enough to confirm the ability of the model for embryo selection. However, the retrospective nature of this study may be a limitation. Wider implications of the findings Using combination of timelapse technology with automated embryo assessment and conventional morphological assessment can predict the success rates of assisted reproduction cycles. To our knowledge, this is the first study using embryo dataset from single vitrified-warmed blastocyst transfer cycles with this embryo assessment algorithm. Trial registration number not applicable