Department of Gynecology, Miyake Ofuku Clinic, Okayama, Japan.
Medical Data Labo, Okayama, Japan.
J Perinat Med. 2021 Feb 8;49(5):596-603. doi: 10.1515/jpm-2020-0537. Print 2021 Jun 25.
The development of the artificial intelligence (AI) classifier to recognize fetal facial expressions that are considered as being related to the brain development of fetuses as a retrospective, non-interventional pilot study.
Images of fetal faces with sonography obtained from outpatient pregnant women with a singleton fetus were enrolled in routine conventional practice from 19 to 38 weeks of gestation from January 1, 2020, to September 30, 2020, with completely de-identified data. The images were classified into seven categories, such as eye blinking, mouthing, face without any expression, scowling, smiling, tongue expulsion, and yawning. The category in which the number of fetuses was less than 10 was eliminated before preparation. Next, we created a deep learning AI classifier with the data. Statistical values such as accuracy for the test dataset and the AI confidence score profiles for each category per image for all data were obtained.
The number of fetuses/images in the rated categories were 14/147, 23/302, 33/320, 8/55, and 10/72 for eye blinking, mouthing, face without any expression, scowling, and yawning, respectively. The accuracy of the AI fetal facial expression for the entire test data set was 0.985. The accuracy/sensitivity/specificity values were 0.996/0.993/1.000, 0.992/0.986/1.000, 0.985/1.000/0.979, 0.996/0.888/1.000, and 1.000/1.000/1.000 for the eye blinking, mouthing, face without any expression, scowling categories, and yawning, respectively.
The AI classifier has the potential to objectively classify fetal facial expressions. AI can advance fetal brain development research using ultrasound.
开发人工智能（AI）分类器，以识别被认为与胎儿大脑发育相关的胎儿面部表情，这是一项回顾性、非介入性的初步研究。
从 2020 年 1 月 1 日至 9 月 30 日，在常规常规实践中，从 19 周到 38 周的门诊孕妇中招募了具有单一胎儿的胎儿面部超声图像，数据完全去识别。将图像分为 7 个类别，如眨眼、张嘴、无表情、皱眉、微笑、吐舌和打哈欠。在准备之前，将类别中胎儿数量少于 10 的类别删除。接下来，我们使用数据创建了一个深度学习 AI 分类器。获得了测试数据集的准确率和每个图像每个类别的 AI 置信度评分分布等统计值。
在评定的类别中，眨眼、张嘴、无表情、皱眉和打哈欠的胎儿/图像数量分别为 14/147、23/302、33/320、8/55 和 10/72。整个测试数据集的 AI 胎儿面部表情的准确率为 0.985。AI 的准确率/灵敏度/特异性值分别为 0.996/0.993/1.000、0.992/0.986/1.000、0.985/1.000/0.979、0.996/0.888/1.000 和 1.000/1.000/1.000，用于眨眼、张嘴、无表情、皱眉类别和打哈欠。
AI 分类器具有客观分类胎儿面部表情的潜力。AI 可以使用超声技术推进胎儿大脑发育研究。
