Feasibility of deep learning for predicting live birth from a blastocyst image in patients classified by age

Reproductive medicine and biology

article

Yasunari Miyagi¹  Toshihiro Habara³  Rei Hirata³  Nobuyoshi Hayashi³ 

[1] Medical Data Labo;Department of Gynecologic Oncology, Saitama Medical University International Medical Center;Okayama Couple’s Clinic

关键词: artificial intelligence;    blastocyst;    deep learning;    live birth;    neural network;   

DOI  :  10.1002/rmb2.12266

学科分类：工业工程学

来源: Wiley

【 摘 要 】

Purpose: To identify artificial intelligence (AI) classifiers in images of blastocysts to predict the probability of achieving a live birth in patients classified by age. Results are compared to those obtained by conventional embryo (CE) evaluation. Methods: A total of 5691 blastocysts were retrospectively enrolled. Images captured 115 hours after insemination (or 139 hours if not yet large enough) were classified according to maternal age as follows: <35, 35‐37, 38‐39, 40‐41, and ≥42 years. The classifiers for each category and a classifier for all ages were related to convolutional neural networks associated with deep learning. Then, the live birth functions pre‐ dicted by the AI and the multivariate logistic model functions predicted by CE were tested. The feasibility of the AI was investigated. Results: The accuracies of AI/CE for predicting live birth were 0.64/0.61, 0.71/0.70, 0.78/0.77, 0.81/0.83, 0.88/0.94, and 0.72/0.74 for the age categories <35, 35‐37, 38‐39, 40‐41, and ≥42 years and all ages, respectively. The sum value of the sensitiv‐ ity and specificity revealed that AI performed better than CE (P = 0.01). Conclusions: AI classifiers categorized by age can predict the probability of live birth from an image of the blastocyst and produced better results than were achieved using CE.

【 授权许可】

CC BY|CC BY-NC|CC BY-NC-ND