Fully-automated alignment of 3D fetal brain ultrasound to a canonical reference space using multi-task learning.

Journal article

Methods for aligning 3D fetal neurosonography images must be robust to (i) intensity variations, (ii) anatomical and age-specific differences within the fetal population, and (iii) the variations in fetal posi- tion. To this end, we propose a multi-task fully convolutional neural network (FCN) architecture to ad- dress the problem of 3D fetal brain localization, structural segmentation, and alignment to a referential coordinate system. Instead of treating these tasks as independent problems, we optimize the network by simultaneously learning features shared within the input data pertaining to the correlated tasks, and later branching out into task-specific output streams. Brain alignment is achieved by defining a parametric co- ordinate system based on skull boundaries, location of the eye sockets, and head pose, as predicted from intracranial structures. This information is used to estimate an affine transformation to align a volumet- ric image to the skull-based coordinate system. Co-alignment of 140 fetal ultrasound volumes (age range: 26.0 ±4.4 weeks) was achieved with high brain overlap and low eye localization error, regardless of ges- tational age or head size. The automatically co-aligned volumes show good structural correspondence between fetal anatomies.

Authors: Namburete, AIL; Xie, W; Yaqub, M; Zisserman, A; Noble, JA

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Elsevier
• Journal: Medical Image Analysis
• Volume: 46
• Pages: 1-14
• Publication date: 2018-02-01
• Acceptance date: 2018-02-19
• DOI: 10.1016/j.media.2018.02.006
• EISSN: 1361-8423
• ISSN: 1361-8415
• Pmid: 29499436
• Language: English
• Keywords: Fully convolutional neural networks; Fetal brain; Ultrasound; Multi-task learning; Alignment