City Research Online

Recurrent Neural Networks for Aortic Image Sequence Segmentation with Sparse Annotations

Bai, W., Suzuki, H., Qin, C., Tarroni, G. ORCID: 0000-0002-0341-6138, Oktay, O., Matthews, P. M. and Rueckert, D. (2018). Recurrent Neural Networks for Aortic Image Sequence Segmentation with Sparse Annotations. In: Medical Image Computing and Computer Assisted Intervention – MICCAI 2018. Lecture Notes in Computer Science, 11073. (pp. 586-594). Cham: Springer. ISBN 978-3-030-00936-6

Abstract

Segmentation of image sequences is an important task in medical image analysis, which enables clinicians to assess the anatomy and function of moving organs. However, direct application of a segmentation algorithm to each time frame of a sequence may ignore the temporal continuity inherent in the sequence. In this work, we propose an image sequence segmentation algorithm by combining a fully convolutional network with a recurrent neural network, which incorporates both spatial and temporal information into the segmentation task. A key challenge in training this network is that the available manual annotations are temporally sparse, which forbids end-to-end training. We address this challenge by performing non-rigid label propagation on the annotations and introducing an exponentially weighted loss function for training. Experiments on aortic MR image sequences demonstrate that the proposed method significantly improves both accuracy and temporal smoothness of segmentation, compared to a baseline method that utilises spatial information only. It achieves an average Dice metric of 0.960 for the ascending aorta and 0.953 for the descending aorta.

Publication Type: Conference or Workshop Item (Paper)
Additional Information: The final authenticated version is available online at https://doi.org/10.1007/978-3-030-00937-3_67.
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Departments: School of Mathematics, Computer Science & Engineering > Computer Science
URI: https://openaccess.city.ac.uk/id/eprint/23149
[img]
Preview
Text - Accepted Version
Download (848kB) | Preview

Export

Downloads

Downloads per month over past year

View more statistics

Actions (login required)

Admin Login Admin Login