TY - JOUR
T1 - Cross-modal contrastive learning for unified placenta analysis using photographs
AU - Pan, Yimu
AU - Mehta, Manas
AU - Goldstein, Jeffery A.
AU - Ngonzi, Joseph
AU - Bebell, Lisa M.
AU - Roberts, Drucilla J.
AU - Carreon, Chrystalle Katte
AU - Gallagher, Kelly
AU - Walker, Rachel E.
AU - Gernand, Alison D.
AU - Wang, James
N1 - Publisher Copyright:
© 2024 The Author(s)
PY - 2024/12/13
Y1 - 2024/12/13
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85211422768&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85211422768&partnerID=8YFLogxK
U2 - 10.1016/j.patter.2024.101097
DO - 10.1016/j.patter.2024.101097
M3 - Article
AN - SCOPUS:85211422768
SN - 2666-3899
VL - 5
JO - Patterns
JF - Patterns
IS - 12
M1 - 101097
ER -