Pan Yimu, Mehta Manas, Goldstein Jeffery A, Ngonzi Joseph, Bebell Lisa M, Roberts Drucilla J, Carreon Chrystalle Katte, Gallagher Kelly, Walker Rachel E, Gernand Alison D, Wang James Z
Data Sciences and Artificial Intelligence Section, College of Information Sciences and Technology, The Pennsylvania State University, University Park, PA, USA.
Department of Pathology, Feinberg School of Medicine, Northwestern University, Chicago, IL, USA.
Patterns (N Y). 2024 Nov 19;5(12):101097. doi: 10.1016/j.patter.2024.101097. eCollection 2024 Dec 13.
The placenta is vital to maternal and child health but often overlooked in pregnancy studies. Addressing the need for a more accessible and cost-effective method of placental assessment, our study introduces a computational tool designed for the analysis of placental photographs. Leveraging images and pathology reports collected from sites in the United States and Uganda over a 12-year period, we developed a cross-modal contrastive learning algorithm consisting of pre-alignment, distillation, and retrieval modules. Moreover, the proposed robustness evaluation protocol enables statistical assessment of performance improvements, provides deeper insight into the impact of different features on predictions, and offers practical guidance for its application in a variety of settings. Through extensive experimentation, our tool demonstrates an average area under the receiver operating characteristic curve score of over 82% in both internal and external validations, which underscores the potential of our tool to enhance clinical care across diverse environments.
胎盘对母婴健康至关重要，但在妊娠研究中常常被忽视。为了满足对更便捷且经济高效的胎盘评估方法的需求，我们的研究引入了一种用于分析胎盘照片的计算工具。利用在美国和乌干达的多个地点在12年期间收集的图像和病理报告，我们开发了一种跨模态对比学习算法，该算法由预对齐、蒸馏和检索模块组成。此外，所提出的稳健性评估协议能够对性能改进进行统计评估，更深入地洞察不同特征对预测的影响，并为其在各种环境中的应用提供实用指导。通过广泛的实验，我们的工具在内部和外部验证中均显示出受试者工作特征曲线下面积得分平均超过82%，这突出了我们的工具在不同环境中加强临床护理的潜力。
