Imperial College London


Faculty of MedicineDepartment of Surgery & Cancer




+44 (0)20 3313 3759eric.aboagye




Mrs Maureen Francis +44 (0)20 7594 2793




GN1Commonwealth BuildingHammersmith Campus






BibTex format

author = {Valindria, V and Lavdas, I and Cerrolaza, J and Aboagye, EO and Rockall, A and Rueckert, D and Glocker, B},
doi = {10.1007/978-3-030-00919-9_40},
pages = {346--354},
publisher = {Springer Verlag},
title = {Small organ segmentation in whole-body MRI using a two-stage FCN and weighting schemes},
url = {},
year = {2018}

RIS format (EndNote, RefMan)

AB - Accurate and robust segmentation of small organs in whole-body MRI is difficult due to anatomical variation and class imbalance. Recent deep network based approaches have demonstrated promising performance on abdominal multi-organ segmentations. However, the performance on small organs is still suboptimal as these occupy only small regions of the whole-body volumes with unclear boundaries and variable shapes. A coarse-to-fine, hierarchical strategy is a common approach to alleviate this problem, however, this might miss useful contextual information. We propose a two-stage approach with weighting schemes based on auto-context and spatial atlas priors. Our experiments show that the proposed approach can boost the segmentation accuracy of multiple small organs in whole-body MRI scans.
AU - Valindria,V
AU - Lavdas,I
AU - Cerrolaza,J
AU - Aboagye,EO
AU - Rockall,A
AU - Rueckert,D
AU - Glocker,B
DO - 10.1007/978-3-030-00919-9_40
EP - 354
PB - Springer Verlag
PY - 2018///
SN - 0302-9743
SP - 346
TI - Small organ segmentation in whole-body MRI using a two-stage FCN and weighting schemes
UR -
UR -
ER -