TY - JOUR
T1 - BabyNet++
T2 - Fetal birth weight prediction using biometry multimodal data acquired less than 24 hours before delivery
AU - Płotka, Szymon
AU - Grzeszczyk, Michal K.
AU - Brawura-Biskupski-Samaha, Robert
AU - Gutaj, Paweł
AU - Lipa, Michał
AU - Trzciński, Tomasz
AU - Išgum, Ivana
AU - Sánchez, Clara I.
AU - Sitek, Arkadiusz
N1 - Funding Information: This work is supported by the European Union's Horizon 2020 research and innovation programme under grant agreement no. 857533 (Sano) and the International Research Agendas programme of the Foundation for Polish Science, Poland, co-financed by the European Union under the European Regional Development Fund. This work is supported in part by National Institutes of Health (NIH), United States grant number HL159183. We would like to thank all pregnant women who participated in this study. Special thanks to Beata Rebizant, MD PhD, Katarzyna Kosińska-Kaczyńska, MD PhD, and Małgorzata Siergiej, MD PhD for acquiring the data. We would like to thank Piotr Nowakowski for his assistance with proofreading the manuscript. We would like to thank NVIDIA Corporation for the in-kind donation of DGX Clara hardware. Funding Information: This work is supported by the European Union’s Horizon 2020 research and innovation programme under grant agreement no. 857533 (Sano) and the International Research Agendas programme of the Foundation for Polish Science, Poland , co-financed by the European Union under the European Regional Development Fund . This work is supported in part by National Institutes of Health (NIH), United States grant number HL159183 . We would like to thank all pregnant women who participated in this study. Special thanks to Beata Rebizant, MD PhD, Katarzyna Kosińska-Kaczyńska, MD PhD, and Małgorzata Siergiej, MD PhD for acquiring the data. We would like to thank Piotr Nowakowski for his assistance with proofreading the manuscript. We would like to thank NVIDIA Corporation for the in-kind donation of DGX Clara hardware. Publisher Copyright: © 2023 The Author(s)
PY - 2023/12/1
Y1 - 2023/12/1
N2 - Accurate prediction of fetal weight at birth is essential for effective perinatal care, particularly in the context of antenatal management, which involves determining the timing and mode of delivery. The current standard of care involves performing a prenatal ultrasound 24 hours prior to delivery. However, this task presents challenges as it requires acquiring high-quality images, which becomes difficult during advanced pregnancy due to the lack of amniotic fluid. In this paper, we present a novel method that automatically predicts fetal birth weight by using fetal ultrasound video scans and clinical data. Our proposed method is based on a Transformer-based approach that combines a Residual Transformer Module with a Dynamic Affine Feature Map Transform. This method leverages tabular clinical data to evaluate 2D+t spatio-temporal features in fetal ultrasound video scans. Development and evaluation were carried out on a clinical set comprising 582 2D fetal ultrasound videos and clinical records of pregnancies from 194 patients performed less than 24 hours before delivery. Our results show that our method outperforms several state-of-the-art automatic methods and estimates fetal birth weight with an accuracy comparable to human experts. Hence, automatic measurements obtained by our method can reduce the risk of errors inherent in manual measurements. Observer studies suggest that our approach may be used as an aid for less experienced clinicians to predict fetal birth weight before delivery, optimizing perinatal care regardless of the available expertise.
AB - Accurate prediction of fetal weight at birth is essential for effective perinatal care, particularly in the context of antenatal management, which involves determining the timing and mode of delivery. The current standard of care involves performing a prenatal ultrasound 24 hours prior to delivery. However, this task presents challenges as it requires acquiring high-quality images, which becomes difficult during advanced pregnancy due to the lack of amniotic fluid. In this paper, we present a novel method that automatically predicts fetal birth weight by using fetal ultrasound video scans and clinical data. Our proposed method is based on a Transformer-based approach that combines a Residual Transformer Module with a Dynamic Affine Feature Map Transform. This method leverages tabular clinical data to evaluate 2D+t spatio-temporal features in fetal ultrasound video scans. Development and evaluation were carried out on a clinical set comprising 582 2D fetal ultrasound videos and clinical records of pregnancies from 194 patients performed less than 24 hours before delivery. Our results show that our method outperforms several state-of-the-art automatic methods and estimates fetal birth weight with an accuracy comparable to human experts. Hence, automatic measurements obtained by our method can reduce the risk of errors inherent in manual measurements. Observer studies suggest that our approach may be used as an aid for less experienced clinicians to predict fetal birth weight before delivery, optimizing perinatal care regardless of the available expertise.
KW - Birth weight prediction
KW - Deep learning
KW - Fetal ultrasound
KW - Multimodal data
KW - Transformers
UR - http://www.scopus.com/inward/record.url?scp=85175825676&partnerID=8YFLogxK
U2 - https://doi.org/10.1016/j.compbiomed.2023.107602
DO - https://doi.org/10.1016/j.compbiomed.2023.107602
M3 - Article
C2 - 37925906
SN - 0010-4825
VL - 167
JO - Computers in Biology and Medicine
JF - Computers in Biology and Medicine
M1 - 107602
ER -