Cookies on this website

We use cookies to ensure that we give you the best experience on our website. If you click 'Accept all cookies' we'll assume that you are happy to receive all cookies and you won't see this message again. If you click 'Reject all non-essential cookies' only necessary cookies providing core functionality such as security, network management, and accessibility will be enabled. Click 'Find out more' for information on how to change your cookie settings.

The relationship between fetal cortical development and gestational age has been commonly studied, with cortical folding events found to be temporally consistent across the healthy population. In order to utilise this relationship in clinical practice, manual fissure grading charts have been proposed to compare fissure appearance or measurements to the known fetal gestational age. However, these techniques are found to be extremely user-dependent, time-consuming and error-prone. In this study, we propose a deep learning-based automated method to assess the development of three fissures: the Sylvian fissure (SF), Parieto-occipital fissure (POF) and Calcarine sulcus (CLC), by predicting fetal gestational age based on their respective morphology. This fissure-specific age prediction can then be compared to the true gestational age to determine if regional cortical development is healthy, delayed, or advanced. Our best-performing CNN estimated the gestational age with an error of 3.4, 5.0, 4.9 and 4.1 days, for the SF, POF, CLC and whole-brain, respectively, outperforming previously reported ultrasound whole-brain age prediction techniques.

Original publication




Conference paper

Publication Date



12959 LNCS


242 - 252