PuSH - Publikationsserver des Helmholtz Zentrums München

Zimmer, V.A.* ; Gomez, A.* ; Skelton, E.* ; Wright, R.* ; Wheeler, G.* ; Deng, S.* ; Ghavami, N.* ; Lloyd, K.* ; Matthew, J.* ; Kainz, B.* ; Rueckert, D.* ; Hajnal, J.V.* ; Schnabel, J.A.

Placenta segmentation in ultrasound imaging: Addressing sources of uncertainty and limited field-of-view.

Med. Image Anal. 83:102639 (2022)
Verlagsversion DOI
Open Access Gold (Paid Option)
Creative Commons Lizenzvertrag
Automatic segmentation of the placenta in fetal ultrasound (US) is challenging due to the (i) high diversity of placenta appearance, (ii) the restricted quality in US resulting in highly variable reference annotations, and (iii) the limited field-of-view of US prohibiting whole placenta assessment at late gestation. In this work, we address these three challenges with a multi-task learning approach that combines the classification of placental location (e.g., anterior, posterior) and semantic placenta segmentation in a single convolutional neural network. Through the classification task the model can learn from larger and more diverse datasets while improving the accuracy of the segmentation task in particular in limited training set conditions. With this approach we investigate the variability in annotations from multiple raters and show that our automatic segmentations (Dice of 0.86 for anterior and 0.83 for posterior placentas) achieve human-level performance as compared to intra- and inter-observer variability. Lastly, our approach can deliver whole placenta segmentation using a multi-view US acquisition pipeline consisting of three stages: multi-probe image acquisition, image fusion and image segmentation. This results in high quality segmentation of larger structures such as the placenta in US with reduced image artifacts which are beyond the field-of-view of single probes.
Altmetric
Weitere Metriken?
Zusatzinfos bearbeiten [➜Einloggen]
Publikationstyp Artikel: Journalartikel
Dokumenttyp Wissenschaftlicher Artikel
Schlagwörter Multi-task Learning ; Multi-view Imaging ; Ultrasound Placenta Segmentation ; Uncertainty/variability
ISSN (print) / ISBN 1361-8415
e-ISSN 1361-8415
Quellenangaben Band: 83, Heft: , Seiten: , Artikelnummer: 102639 Supplement: ,
Verlag Elsevier
Begutachtungsstatus Peer reviewed
Institut(e) Institute for Machine Learning in Biomed Imaging (IML)
Förderungen Centre For Medical Engineering, King’s College London
Guy's and St Thomas' NHS Foundation Trust
King's College London
National Institute for Health and Care Research
NIHR Biomedical Research Centre, Royal Marsden NHS Foundation Trust/Institute of Cancer Research
Wellcome Trust
King’s College London