Figure 1 - available via license: Creative Commons Attribution-NonCommercial 4.0 International
Content may be subject to copyright.
Flowchart for generating the artificial intelligence classifiers. The artificial intelligence classifier consisted of a combination of 10 Layers of a
Source publication
BACKGROUND
The achievement of live birth is the goal of assisted reproductive technology in reproductive medicine. When the selected blastocyst is transferred to the uterus, the degree of implantation of the blastocyst is evaluated by microscopic inspection, and the result is only about 30%-40%, and the method of predicting live birth from the blas...
Contexts in source publication
Context 1
... classification programs were developed as shown in Figure 1. AI classifiers which were made up of both CNN [19][20][21][22][23][24] with L2 regularization [25,26] and elementwise functions that apply a function to each element of a tensor for each factor of the CEE to obtain the probability of predicting a live birth or non-live birth, as shown in Figure 1. ...
Context 2
... classification programs were developed as shown in Figure 1. AI classifiers which were made up of both CNN [19][20][21][22][23][24] with L2 regularization [25,26] and elementwise functions that apply a function to each element of a tensor for each factor of the CEE to obtain the probability of predicting a live birth or non-live birth, as shown in Figure 1. We introduced deep learning for images with a published CNN architecture except for a softmax layer [14] . ...
Citations
... Therefore, fertilized eggs' developmental abnormalities could be explained from the viewpoint of the free energy principle. Recently, many embryo evaluation methods using artificial intelligence [23][24][25][26] and estimation of chromosomal aberrations [27,28] have been reported. However, as this research method is in its early stages, the measurement of various parameters related to time and kinetic energy offers potential for prenatal diagnosis, including embryonic development, prediction of live birth, and detection of chromosomal aberrations and genetic abnormalities. ...
The retrospective noninterventional study investigated the kinetic energy of video im- ages of 18 fertilized eggs (7 were normal and 11 were abnormal) recorded by a time-lapse de- vice leading up to the beginning of the first cleavage. The norm values of cytoplasmic particles were measured by the optical flow method. Three phase profiles for normal cases were found regarding the kinetic energy: 2.199 × 10E−24 ± 2.076 × 10E−24, 2.369 × 10E−24 ± 1.255 × 10E−24, and 1.078 × 10E−24 ± 4.720 × 10E−25 (J) for phases 1, 2, and 3, respectively. In phase 2, the energies were 2.369 × 10E−24 ± 1.255 × 10E−24 and 4.694 × 10E−24 ± 2.996 × 10E−24 (J) (mean ± SD, p = 0.0372), and the time required was 8.114 ± 2.937 and 6.018 ± 5.685 (H) (p = 0.0413) for the normal and abnormal cases, respectively. The kinetic energy change was considered a condition for applying the free energy principle, which states that for any self-organized system to be in equilibrium in its environment, it must minimize its informational free energy. The kinetic energy, while interpreting it in terms of the free energy principle suggesting clinical usefulness, would further our understanding of the phenomenon of fertilized egg development with respect to the birth of human life.
... Artificial intelligence (AI) has recently become a more common and easily applied tool in medical science. Some AI applications involve medical imaging [10][11][12][13][14][15][16][17][18][19][20], though some do not [21][22][23][24][25]. Machine learning is part of the concept of AI and can acquire rules for judging unknown data by learning patterns latent in the data. ...
... 11 definition of organ dysfunction is changed, or many factors, including unknown ones, are added to the definition of organ dysfunction, the method presented in this study, which is based on AI using multiple factors correlated with fibrinogen and FDP and avoiding multicollinearity to obtain the boundary line dividing the plane of fibrinogen and FDP, can be expected to be a useful criterion for organ dysfunction occurrence. Informed Consent Statement: Informed consent was obtained from all subjects involved in the study. ...
# artificial intelligence
# statistical analysis
# novel method
(1) Background: Although diagnostic criteria for massive hemorrhage with organ dysfunction such as disseminated intravascular coagulation associated with delivery have been empirically established based on clinical findings, strict logic has yet to be used to establish numerical criteria. (2) Methods: A dataset of 107 deliveries with ≥2,000 g of blood loss, among 13,368 deliveries from nine national perinatal centers in Japan between 2020 and 2023 was obtained. Twenty‐three patients had fibrinogen levels <170 mg/dl, which is the initiation of coagulation system failure per our previous reports. Three of these patients had hematuria. We used six machine learning methods to identify the borderline criteria dividing the fibrinogen/fibrin/fibrinogen degradation product (FDP) planes, using 15 coagulation fibrinolytic factors. (3) Results: The boundaries of hematuria development on a two‐dimensional plane of fibrinogen and FDP were obtained. If the FDP–fibrinogen/3–60 (mg/dl) value is positive, this indicates hematuria; otherwise, the case is non‐hematuria, as demonstrated by the support vector machine method that seemed the most appropriate. (4) Conclusions: The borderline criterion dividing the fibrinogen/FDP plane for patients with hematuria that could be considered organ dysfunction in massive hemorrhage during delivery was obtained using artificial intelligence, and this method seemed to be useful.
... Therefore, fertilized eggs' developmental abnormality could be explained from the viewpoint of the free energy principle. Recently, many embryo evaluation methods using artificial intelligence [23][24][25][26] and estimation of chromosomal aberrations [27,28] have been reported. However, as this research method is in its early stages, the measurement of various parameters related to time and kinetic energy offer potential for prenatal diagnosis, including embryo development, prediction of live birth, and detection of chromosomal aberrations and genetic abnormalities. ...
The retrospective noninterventional study investigated the kinetic energy of video images of 18 fertilized eggs (7 were normal and 11 were abnormal) recorded by a time-lapse device leading up to the beginning of the first cleavage. The norm values of cytoplasmic particles were measured by the optical flow method. Three phases profile for normal cases were found regarding the kinetic energy that were 2.199×10<sup>−24</sup>±2.076×10<sup>−24</sup>, 2.369×10<sup>−24</sup>±1.255×10<sup>−24</sup>, and 1.078×10<sup>−24</sup>±4.720×10<sup>−25</sup> (J) for the phases 1, 2, and 3, respectively. In phase 2, the energies were 2.369 × 10<sup>−24</sup> ± 1.255 × 10<sup>−24</sup> and 4.694 × 10<sup>−24</sup> ± 2.996 × 10<sup>−24</sup> (J) (mean ± SD, P = 0.0372), and the time required was 8.114 ± 2.937 and 6.018 ± 5.685 (H) (P = 0.0413) for the normal and abnormal cases, respectively. The kinetic energy change was considered a condition for applying the free energy principle that states that, for any self-organized system to be in equilibrium in its environment, it must minimize its informational free energy. The kinetic energy while interpreting it in terms of the free energy principle suggesting clinical usefulness would further our understanding of the phenomenon of fertilized egg development with respect to the birth of human life.
... Different from using blastocyst images alone to predict clinical outcomes, Miyagi et al., 2020 proposed to use blastocyst images together with maternal clinical features including maternal age, AMH, and BMI and reported an AUC of 0.74, the highest accuracy in literature (Miyagi et al., 2020). However, two questions remain elusive. ...
... Different from using blastocyst images alone to predict clinical outcomes, Miyagi et al., 2020 proposed to use blastocyst images together with maternal clinical features including maternal age, AMH, and BMI and reported an AUC of 0.74, the highest accuracy in literature (Miyagi et al., 2020). However, two questions remain elusive. ...
... As shown in Figure 3, 16 patient couple's clinical features comprehensively include maternal basal characteristics (age and BMI); hormone profiles measured after period (LH and FT4), on HCG day (PE2, P, and LH), and before transfer (E2); endometrium statusrelated features (endometrium thickness on HCG day and before transfer, endometrium pattern on HCG day); features related to oocytes (AFC, retrieved oocyte number); the day of blastocyst transfer; number of ovarian stimulation cycles; and paternal features (the ratio of grade A sperm after semen processing). For comparison, the data set studied by Miyagi et al., 2020 did not contain endometrium status-related features and key hormone profiles (e.g., P, E2, and LH). There are numerous IVF data sets containing over 100,000 records of clinical features and live birth outcomes (Nelson and Lawlor, 2011;McLernon et al., 2016;La Marca et al., 2021); however, there are no blastocyst images in these data sets, and thus, these data sets cannot be used for building models to evaluate blastocysts from their images. ...
Background: In infertility treatment, blastocyst morphological grading is commonly used in clinical practice for blastocyst evaluation and selection, but has shown limited predictive power on live birth outcomes of blastocysts. To improve live birth prediction, a number of artificial intelligence (AI) models have been established. Most existing AI models for blastocyst evaluation only used images for live birth prediction, and the area under the receiver operating characteristic (ROC) curve (AUC) achieved by these models has plateaued at ~0.65.
Methods: This study proposed a multimodal blastocyst evaluation method using both blastocyst images and patient couple’s clinical features (e.g., maternal age, hormone profiles, endometrium thickness, and semen quality) to predict live birth outcomes of human blastocysts. To utilize the multimodal data, we developed a new AI model consisting of a convolutional neural network (CNN) to process blastocyst images and a multilayer perceptron to process patient couple’s clinical features. The data set used in this study consists of 17,580 blastocysts with known live birth outcomes, blastocyst images, and patient couple’s clinical features.
Results: This study achieved an AUC of 0.77 for live birth prediction, which significantly outperforms related works in the literature. Sixteen out of 103 clinical features were identified to be predictors of live birth outcomes and helped improve live birth prediction. Among these features, maternal age, the day of blastocyst transfer, antral follicle count, retrieved oocyte number, and endometrium thickness measured before transfer are the top five features contributing to live birth prediction. Heatmaps showed that the CNN in the AI model mainly focuses on image regions of inner cell mass and trophectoderm (TE) for live birth prediction, and the contribution of TE-related features was greater in the CNN trained with the inclusion of patient couple's clinical features compared with the CNN trained with blastocyst images alone.
Conclusions: The results suggest that the inclusion of patient couple’s clinical features along with blastocyst images increases live birth prediction accuracy.
Funding: Natural Sciences and Engineering Research Council of Canada and the Canada Research Chairs Program.
... But we considered it statistically important that we had developed a method that was at least comparable to the conventional method. It is impossible to predict the future completely, but we developed a new method derived from compressive sensing that is one of the information technologies used in artificial intelligence that we have applied to medical studies in recent several years [15,16,26,[50][51][52][53][54][55][56][57][58][59][60][61]. Our method for predicting unknown data including the observed data can be applied to various types of data including length, weight, volume etc. ...
To develop a new method for interim analysis to obtain the p-values distribution profile of the log-rank test and the statistical power at various information fraction by iteratively predicting the lacking time data of censored and uncensored cases respectively for each arm at the time when the determined sample size will be achieved. A compressive sensing algorithm derived from artificial intelligence was developed for comparing two groups of clinical trial data from real-world databases of deidentified individual participant-level data. The judgement of the interim analysis was compared to the conventional method, with our method demonstrating that it was at least comparable to the conventional method. The power by our method was higher than the conditional power of the conventional method. When α-error by log-rank test was focused, our method seemed to have made the right decision earlier than the conventional method. It may be possible to expand the options of applicable methods for interim analysis. It would be helpful in establishing efficacy and futility judgement in clinical trials.
... In different fields of obstetrics and gynecology, research works relevant to AI have been published. [26][27][28][29][30][31][32][33][34][35] A well-trained AI classifier that can evaluate and classify fetal facial expressions would help investigate the development of the fetal central nervous system. The AI recognition of adult facial expressions has been investigated. ...
... The advantage of multi-modalities for AI has been presented in the classification of the uterine cervical squamous epithelial lesion from colposcopy images combined with HPV types 27 and the predicting live birth from blastocyst images combined with the conventional clinical embryo evaluation parameters. 29 Therefore, fetal facial expressions can be classified by image and by incorporating images with gestational age and other associated parameters. Established AI has no intrinsic bias for classifying images. ...
Fetal facial expressions are useful parameters for assessing brain function and development in the latter half of pregnancy. Previous investigations have studied subjective assessment of fetal facial expressions using four-dimensional ultrasound. Artificial intelligence (AI) can enable the objective assessment of fetal facial expressions. Artificial intelligence recognition of fetal facial expressions may open the door to the new scientific field, such as "AI science of fetal brain", and fetal neurobehavioral science using AI is at the dawn of a new era. Our knowledge of fetal neurobehavior and neurodevelopment will be advanced through AI recognition of fetal facial expressions. Artificial intelligence may be an important modality in current and future research on fetal facial expressions and may assist in the evaluation of fetal brain function.
https://doi.org/10.5005/jp-journals-10009-1710
... Live birth *-D5/D6-blastocyst ( ) Accuracy, sensitivity, specificity, informedness, AUC [27] Static image, annotations, patient info (age, BMI, ...) ...
Embryo selection within in vitro fertilization (IVF) is the process of evaluating qualities of fertilized oocytes (embryos) and selecting the best embryo(s) available within a patient cohort for subsequent transfer or cryopreservation. In recent years, artificial intelligence (AI) has been used extensively to improve and automate the embryo ranking and selection procedure by extracting relevant information from embryo microscopy images. The AI models are evaluated based on their ability to identify the embryo(s) with the highest chance(s) of achieving a successful pregnancy. Whether such evaluations should be based on ranking performance or pregnancy prediction, however, seems to divide studies. As such, a variety of performance metrics are reported, and comparisons between studies are often made on different outcomes and data foundations. Moreover, superiority of AI methods over manual human evaluation is often claimed based on retrospective data, without any mentions of potential bias. In this paper, we provide a technical view on some of the major topics that divide how current AI models are trained, evaluated and compared. We explain and discuss the most common evaluation metrics and relate them to the two separate evaluation objectives, ranking and prediction. We also discuss when and how to compare AI models across studies and explain in detail how a selection bias is inevitable when comparing AI models against current embryo selection practice in retrospective cohort studies.
During the last few years, the number of frozen-thawed embryo transfer cycles (FET) significantly increased due to the universal application of more efficient cryopreservation techniques in the IVF laboratory and the improved survival rates of blastocyst stage embryos and the wide implementation of “freeze all” IVF cycles to prevent OHSS, or for preimplantation genetic testing for aneuploidy (PGT-A). Blastocyst cryopreservation allows single embryo transfers to reduce the rate of multiple pregnancies and improve perinatal outcomes. There is no consensus regarding the optimal laboratory protocol for blastocyst cryopreservation, and research is ongoing for its amelioration. This review summarizes different laboratory methods that may improve frozen-thawed blastocyst embryo transfer outcomes, alone or in combination. Some of the techniques relate to embryo survival; some of them work on endometrial receptivity.
