Calibrated Bayesian neural networks to estimate gestational age and its uncertainty on fetal brain ultrasound images

Conference item

We present an original automated framework for estimating gestational age (GA) from fetal ultrasound head biometry plane images. A novelty of our approach is the use of a Bayesian Neural Network (BNN), which quantifies uncertainty of the estimated GA. Knowledge of estimated uncertainty is useful in clinical decision-making, and is especially important in ultrasound image analysis where image appearance and quality can naturally vary a lot. A further novelty of our approach is that the neural ...

Expand abstract

Authors: Lee, LH; Bradburn, E; Papageorghiou, AT; Noble, JA

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Springer Publisher's website
• Host title: Medical Ultrasound, and Preterm, Perinatal and Paediatric Image Analysis
• Series: Lecture Notes in Computer Science
• Series number: 12437
• Pages: 13-22
• Publication date: 2020-10-01
• Acceptance date: 2020-07-28
• Event title: ASMUS: International Workshop on Advances in Simplifying Medical Ultrasound 2020
• Event location: Lima, Peru
• Event website: https://sites.google.com/view/asmus2020
• Event start date: 2020-10-04
• Event end date: 2020-10-04
• DOI: 10.1007/978-3-030-60334-2_2
• EISSN: 1611-3349
• ISSN: 0302-9743
• EISBN: 9783030603342
• ISBN: 9783030603335
• Language: English
• Keywords: FFR; gestational age estimation; Bayesian neural networks; uncertainty in regression; fetal ultrasound