Download

Reproduction AI Database

Download (2186) Download (2186) Download (2186)

Add Publication

genetics Al model

Computer-Assisted Low-Cost Point-of-Care UltraSound (CALOPUS)

Fertility image Testing Through Embryo (FiTTE)

Stacking ensemble, linear regression, random forest, extra tree regression, K-nearest neighbour in R and XGBoost

Logistic regression multivariate models

Logistic Regression, Decision Tree, Naive Beyes, Random Forest, Support Vector Machine, Neural Network, Gradient Boost Decision Tree, eXtreme Gradient Boosting, Super Learner

ML- GBoost algorithm

Logistic regression (LR), support vector classification, random forest, Extreme Gradient Boosting (XGBoost) and, Stacking generalization (Stack) as the machine learning classifiers were used to predict IUI success by Python v3.7

ML - best algorithm was random forest "Yang-Peavy Embryo Enhancement Algorithm"

Machine Learning algorithm -prediction model Model 4 BBT and HR - regular group

Deep-Learning-Based Embryo Component Segmentation Network (ECS-Net)

Logistic Regression, Random Forest, Support Vector Machine, Light Gradient Boosting Machine, Extreme Gradient Boosting, Multilayer Perceptron

Gradient Boosting Decision Tree

Deep Learning-Based Segmentation Algorithm

Time-lapse Microscopy

KNN regression model

Viability Artificial Intelligence Model

eXtreme Gradient Boosting (XGB)

Temporal Cycle Consistency

iDAScore

random forest algorithm vs logistic regression

XGBoost ( eXtreme Gradient Boosting - a decision-tree-based algorithm).

five machine learning models and two types of deep learning networks used to develop predictive algorithms.

Machine learning model

machine learning model ( tested

Four machine learning algorithms including Random forest ,AdaBoost, Gradient boosted decision tree & multilayer perceptron models were compared

random forest model for predicting upgrade in sperm following varicocele repair

Convolutional neural network model

Logistic Regression, Random Forests, Artificial Neural Networks, Decision Trees

Logistic Regression, Random Forest, Support Vector Machine, Adaptive Boosting, Extreme Gradient Boosting

MGRFE

Random Forest Algorithm

Deep learning (OB-4000)

Sprint Semantic Segmentation Network (SSS-Net)

ANN: Multilayer Perceptron

Random forest classifier (RFC), scikit-learn gradient boosting classifier, support vector machine, multivariate logistic regression, and naïve Bayes ML models

Decision Tree

Spatial Transformation Network (STN)

Generative Adversarial Networks (GAN)

U-Net Based Convolutional Neural Network

Max-flow algorithm for Segmentation

Modified U-Net [ Convolutional Neural Network]

Multiple: ANN, random forest, PLS, SVM, and linear models using the caret package in R

Convolutional neural network (CNN)

Deep Learning Model

Mixed effect logistic model

Multiple: ANN, random forest, PLS, SVM, and linear models

image analysis, collinearity analysis, ANN and genetic algorithms

Adaptive adversarial neural network (CNN)

Deep Learning Network

Multivariable logistic regression model

ML algorithm (CNN + LSTM)

Deep neural network

CNN

Commentary

Hybrid algorith including classification and regression trees, random forests, support vector machines, logistic regression, and neural networks

Review

Deep convolutional neural network (CNN)

Artificial Neural Network (ANN)

Naive Bayes, Selective Naive Bayes, Semi Naive, Bayes, TAN, KDB, TAN-wrapper and KDB-wrapper

Decision trees with Genetic Algorithms

Neural Networks and logistic regression

Bayesian Network

Decision trees and Bayesian Networks

Neural network

Multilayer perceptron, Decision Tree, Naive Bayes (Kernel), Support vector machine+Particle swarm optimization and Support vector machine

Ranking algorith RIMARC

Bayesian Network - Naive Bayes, K-nearest neighbor, decision trees, Suppot vector machines, Multilayer perceptron and RBFNN

Naïve Bayes, Support vector machines, Multilayer Perceptron, IBK, KStar, Bagging, Random Committee and Random Forest

Support vector machines

Support vector machine-based decision tree

Decision trees

Support vector machines, recursive partitioning, random forest, adaptive boosting, one-neerest neighbor

Artificial neural network and principal component analysis

Artificial neural network

Convolutional neural networks

Support Vector Machines with 10-fold cross validation

Bayesian network model

Fuzzy radial basis function neural networks

Multilayer perceptron, support vector machines, C4.5, classification and regression trees and random forest.

Sperm Whale Optimization algorithm with Artificial neural networks

Multilayer perceptron

Residual neural networks / deep residual network (ResNet)

Convolutional neural networks - Xception

Two convolutional neural networks classifiers vote-based. AlexNet and fully connected layers to extract features, which were further classified with different algorithms

Logistic regression, naive Bayes, nearest neighbors, random forest, neural network, and support vector machine. Used 5 fold cross validation

Convolutional neural networks - ResNet-50 (transfer learning from imageNet)

Random forest and multivariate logistic regression model

Feed forward deep learning

Inception-V1 architecture, a transfer learning algorithm of the model trained for ImageNet

Voting system of eight convolutional neural network models (ResNet-152 and DenseNet-161)

Probabilistic bayesian, Support Vector Machines, deep neural network, decision tree, and Random Forest

Convolutional neural network

Deep neural network of fully connected layers

Neural networks, are a beautiful biologically-inspired programming paradigm which enables a computer to learn from observational data. Deep learning, a powerful set of techniques for learning in neural networks.

Neural networks and deep learning currently provide the best solutions to many problems in image recognition, speech recognition, and natural language processing.

Neural Networks

Tree-based machine learning methods are among the most commonly used supervised learning methods.

Decision tree learning is one of the predictive modelling approaches used in statistics, data mining and machine learning.

Tree Based Methods

Discriminative models, also referred to as conditional models or backward models, are a class of supervised machine learning used for classification or regression. Typical discriminative models include logistic regression (LR), support vector machines (SVM), conditional random fields (CRFs).

Discrimination-Based Methods

Proposed AI solutions

Proposed Architecture

Repro-Ai: The repository for reproduction studies using artificial intelligence

Repro-AI.org is an interdiscplinary team of technologists, reproductive scientists, mathematicians, and physicians working to advance artificial intelligence applications in reproductive medicine.

Repro-Ai.org centralizes all AI publications in reproduction and provides easy to make, beautiful graphics for publications, reviews, posters and abstracts.

Successful human reproduction is a complex problem with so many variables that even the best-planned studies can quickly become confounded, yielding inconclusive results.

Inherent variation and subjectivity are the enemy of consistency and objectivity. AI can address these challenges. It is perfectly suited for the seemingly intractable questions of reproductive medicine, for example; embryo selection; the complex dialogue between endometrium and embryo and recurrent miscarriage; the physiological function of the uterus and disease states like endometriosis and adenomyosis; therapeutic targets for biological and chronological ovarian ageing; preimplantation genetics to improve pregnancy outcomes; and recurrent implantation failure.

Artificial Intelligence has been used in many aspects of reproduction, from research and experiment to clinical practice.

More research is needed to promote the application of AI in reproductive medicine. A significant challenge lies in determining the best ways to implement AI in clinical work. AI models are mostly a black box, lacking a universal understanding of inner workings. The performance of AI is related to various factors, including the quantity and quality of the data. Small training datasets can lead to wrong decisions if they are biased. Deep learning requires a significant amount of data for training; it may perform poorly if the data is insufficient. Selection bias from sample collection can result in poor performance of AI models in a clinical setting

Ethical, transparent data collection and sharing is of utmost importance, both of which will enable the use of high-quality data efficiently.

Collaborators

Artificial intelligence (AI) has the potential to enhance our diagnostic and prognostic capabilities, minimize variability and error, and maximize precision and speed of IVF treatment.

AI Special Interest Group

ASRM

AIVF

AIVF

Massachusetts General Hospital

MGH

Fertility Guidance Technologies

FGT

Brigham and Women's Hospital

BWH

Weill Cornell Medicine

WMC

Future Fertility

Future Fertility

ART Compass

ARTC

New Hope Fertility

New Hope Fertility

Apricity

Apricity

Fenomatch

Fenomatch

IVIRMA Valencia

IVIRMA Valencia

ERICA

ERICA

Embryonics

Embryonics

Contact

Repro-AI.org is an interdiscplinary team of technologists, reproductive scientists, mathematicians, and physicians working to advance artificial intelligence applications in reproductive medicine.