AmnioML: Amniotic Fluid Segmentation and Volume Prediction with Uncertainty Quantification

Authors

  • Daniel Csillag IMPA
  • Lucas Monteiro Paes Harvard University
  • Thiago Ramos IMPA
  • João Vitor Romano IMPA
  • Rodrigo Schuller IMPA
  • Roberto B. Seixas IMPA
  • Roberto I. Oliveira IMPA
  • Paulo Orenstein IMPA

DOI:

https://doi.org/10.1609/aaai.v37i13.26837

Keywords:

Amniotic Fluid, Fetal MRI, Conformal Prediction, Neural Networks, Volume Estimation, Medical Segmentation

Abstract

Accurately predicting the volume of amniotic fluid is fundamental to assessing pregnancy risks, though the task usually requires many hours of laborious work by medical experts. In this paper, we present AmnioML, a machine learning solution that leverages deep learning and conformal prediction to output fast and accurate volume estimates and segmentation masks from fetal MRIs with Dice coefficient over 0.9. Also, we make available a novel, curated dataset for fetal MRIs with 853 exams and benchmark the performance of many recent deep learning architectures. In addition, we introduce a conformal prediction tool that yields narrow predictive intervals with theoretically guaranteed coverage, thus aiding doctors in detecting pregnancy risks and saving lives. A successful case study of AmnioML deployed in a medical setting is also reported. Real-world clinical benefits include up to 20x segmentation time reduction, with most segmentations deemed by doctors as not needing any further manual refinement. Furthermore, AmnioML's volume predictions were found to be highly accurate in practice, with mean absolute error below 56mL and tight predictive intervals, showcasing its impact in reducing pregnancy complications.

Downloads

Published

2023-09-06

How to Cite

Csillag, D., Monteiro Paes, L., Ramos, T., Romano, J. V., Schuller, R., Seixas, R. B., Oliveira, R. I., & Orenstein, P. (2023). AmnioML: Amniotic Fluid Segmentation and Volume Prediction with Uncertainty Quantification. Proceedings of the AAAI Conference on Artificial Intelligence, 37(13), 15494-15502. https://doi.org/10.1609/aaai.v37i13.26837

Issue

Section

IAAI Technical Track on deployed Highly Innovative Applications of AI