End-to-end First Trimester Fetal Ultrasound Video Automated CRL and NT Segmentation

Robail Yasrab; Zeyu Fu; Lior Drukker; Lok Hin Lee; He Zhao; Aris T Papageorghiou; Alison J Noble

doi:10.1109/ISBI52829.2022.9761400

End-to-end First Trimester Fetal Ultrasound Video Automated CRL and NT Segmentation

Proc IEEE Int Symp Biomed Imaging. 2022 Apr 28:2022:9761400. doi: 10.1109/ISBI52829.2022.9761400.

Authors

Robail Yasrab¹, Zeyu Fu¹, Lior Drukker^{2

3}, Lok Hin Lee¹, He Zhao¹, Aris T Papageorghiou², Alison J Noble¹

Affiliations

¹ Institute of Biomedical Engineering, University of Oxford, Oxford, UK.
² Nuffield Department of Women's & Reproductive Health, University of Oxford, Oxford, UK.
³ Rabin Medical Center, Sackler Faculty of Medicine, Tel-Aviv University, Israel.

Abstract

This study presents a novel approach to automatic detection and segmentation of the Crown Rump Length (CRL) and Nuchal Translucency (NT), two essential measurements in the first trimester US scan. The proposed method automatically localises a standard plane within a video clip as defined by the UK Fetal Abnormality Screening Programme. A Nested Hourglass (NHG) based network performs semantic pixel-wise segmentation to extract NT and CRL structures. Our results show that the NHG network is faster (19.52% < GFlops than FCN32) and offers high pixel agreement (mean-IoU=80.74) with expert manual annotations.

Keywords: First trimester; crown rump length (CRL); nuchal translucency (NT); ultrasound; video segmentation.

Grants and funding

694581/ERC_/European Research Council/International