Optimizing CNN Hyperparameters for Blastocyst Quality Assessment in Small Datasets

Abstract

Morphological assessment of blastocyst quality is one of the most significant challenges in the IVF process because the current assessment is still based on the evaluation of an embryologist, so it is still manual, subjective, and lacks precision. Artificial Intelligence (AI) plays a role in overcoming the limitations of the manual assessment system, and it is expected to increase implantation in the IVF process. The study aims to optimize the convolutional neural networks (CNN) model by grid search method and evaluate different machine learning models in classifying blastocyst quality in a small dataset. The reliability of the proposed model will be compared with other machine learning as logistic regression (LR), support vector machine (SVM), k-nearest neighbors (KNN), boosting algorithm, and adding canny operator as a segmentation process and principal component analysis (PCA) as feature extraction.We evaluate the results with different performance measures like Precision, Recall, F1-measure, Accuracy, and Area under the receiver operating characteristic curve (AUC-ROC). The final results showed that our proposed CNN model achieves validation accuracy of 84.00%, test accuracy of 83.33%, and AUC 0.844. McNemar’s statistical test results support that our CNN model outperforms the other classifiers.