Predicting abnormal fetal growth using deep learning.

Authors

Mikołaj KW,Christensen AN,Taksøe-Vester CA,Feragen A,Petersen OB,Lin M,Nielsen M,Svendsen MBS,Tolsgaard MG

Affiliations (9)

  • Department of Applied Mathematics and Computer Science, Technical University of Denmark, Kongens Lyngby, Denmark.
  • Copenhagen Academy for Medical Education and Simulation (CAMES), Copenhagen, Denmark.
  • Center for Fetal Medicine, Copenhagen University Hospital Rigshospitalet, Copenhagen, Denmark.
  • Department of Clinical Medicine, University of Copenhagen, Copenhagen, Denmark.
  • Department of Computer Science, University of Copenhagen, Copenhagen, Denmark.
  • Department of Health Technology, Technical University of Denmark, Kongens Lyngby, Denmark.
  • Copenhagen Academy for Medical Education and Simulation (CAMES), Copenhagen, Denmark. [email protected].
  • Center for Fetal Medicine, Copenhagen University Hospital Rigshospitalet, Copenhagen, Denmark. [email protected].
  • Department of Clinical Medicine, University of Copenhagen, Copenhagen, Denmark. [email protected].

Abstract

Ultrasound assessment of fetal size and growth is the mainstay of monitoring fetal well-being during pregnancy, as being small for gestational age (SGA) or large for gestational age (LGA) poses significant risks for both the fetus and the mother. This study aimed to enhance the prediction accuracy of abnormal fetal growth. We developed a deep learning model, trained on a dataset of 433,096 ultrasound images derived from 94,538 examinations conducted on 65,752 patients. The deep learning model performed significantly better in detecting both SGA (58% vs 70%) and LGA compared with the current clinical standard, the Hadlock formula (41% vs 55%), p < 0.001. Additionally, the model estimates were significantly less biased across all demographic and technical variables compared to the Hadlock formula. Incorporating key anatomical features such as cortical structures, liver texture, and skin thickness was likely to be responsible for the improved prediction accuracy observed.

Topics

Journal Article

Ready to Sharpen Your Edge?

Join hundreds of your peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.