Predicting abnormal fetal growth using deep learning
Kamil Mikolaj, Anders Nymark Christensen, Caroline Taksøe‐Vester, Aasa Feragen, Olav Bjørn Petersen, Manxi Lin, Mads Nielsen, Morten Bo Søndergaard Svendsen, Martin G. Tolsgaard
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.