#233 : Deep Learning Classification Integrating Embryo Images with Associated Clinical Information from IVF Treatments

Abstract

Background and Aims: With the advent of artificial intelligence (AI), there is potential for AI applications in areas limited by human subjectivity, such as embryo selection. Therefore, we aimed to develop an AI model that integrates the advances of computer vision for embryo images with machine learning for clinical information. Method: Three AI models were developed, trained, and tested using a database comprised of a total of 1503 international treatment cycles (Thailand, Malaysia, and India): 1) A Clinical Multi-Layer Perceptron (MLP) for patient clinical data. 2) An Image Convolutional Neural Network (CNN) AI model using blastocyst images. 3) A fusion model using a combination of both models. All three models were evaluated against their ability to predict clinical pregnancy and live birth. Each of the models were further assessed through a visualisation process where the importance of each data point clarified which clinical and embryonic features contributed the most to the prediction. Results: The experiments achieved the following results for predicting clinical pregnancy, the MLP model achieved a strong performance of 81.76% accuracy, 90% average precision and 0.91 AUC, the CNN model achieved a performance of 66.89% accuracy, 74% average precision and 0.73 AUC, the Fusion model achieved 82.42% accuracy, 91% average precision and 0.91 AUC. From the visualisation process we found that female age and female BMI to be the most clinical factors, whilst Trophectoderm to be the most important blastocyst feature. Conclusion: The fusion AI model integrating clinical features and embryo images made more informed predictions, achieving better performance than separate models alone. This study demonstrates that AI for IVF applications can increase prediction performance by integrating blastocyst images with patient clinical information.