Cross-modal contrastive learning for unified placenta analysis using photographs
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.
Authors
- Rachel E. Walker (ORCID: https://orcid.org/0000-0002-8845-858X)
- Lisa M. Bebell (ORCID: https://orcid.org/0000-0003-0077-6522)
- Alison D. Gernand (ORCID: https://orcid.org/0000-0002-5661-7785)
- Chrystalle Katte Carreon (ORCID: https://orcid.org/0000-0003-2152-7998)
- Drucilla J. Roberts (ORCID: https://orcid.org/0000-0002-9104-6674)
- Yimu Pan
- Manas Mehta (ORCID: https://orcid.org/0009-0000-5077-2998)
- Kelly Gallagher (ORCID: https://orcid.org/0000-0002-3291-3512)
- Joseph Ngonzi (ORCID: https://orcid.org/0000-0001-5253-9516)
- Jeffrey A. Goldstein (ORCID: https://orcid.org/0000-0002-4086-057X)
- James Z. Wang (ORCID: https://orcid.org/0000-0003-4379-4173)
Institutions
- Northwestern University (US)
- Boston Children's Hospital (US)
- Pennsylvania State University (US)
- Harvard University (US)
- Mbarara University of Science and Technology (UG)
- Massachusetts General Hospital (US)
- Center for Global Health (US)
Publication Details
- Journal
- Patterns
- Published
- 2024-11-19
- DOI
- https://doi.org/10.1016/j.patter.2024.101097
- Citations
- 4
- Primary Topic
- Grief, Bereavement, and Mental Health
- Type
- article
- Field-Weighted Citation Impact
- 2.56
Funders
- National Science Foundation
- American Society of Tropical Medicine and Hygiene
- Northwestern University
- National Institutes of Health
- National Institute of Child Health and Human Development
- Office of Advanced Cyberinfrastructure