Citation

BibTex format

@inproceedings{Galazis:2022:10.1007/978-3-030-93722-5_29,
author = {Galazis, C and Wu, H and Li, Z and Petri, C and Bharath, AA and Varela, M},
doi = {10.1007/978-3-030-93722-5_29},
pages = {268--276},
publisher = {Springer International Publishing},
title = {Tempera: spatial transformer feature pyramid network for cardiac MRI segmentation},
url = {http://dx.doi.org/10.1007/978-3-030-93722-5_29},
year = {2022}
}

RIS format (EndNote, RefMan)

TY  - CPAPER
AB - Assessing the structure and function of the right ventricle (RV) is important in the diagnosis of several cardiac pathologies. However, it remains more challenging to segment the RV than the left ventricle (LV). In this paper, we focus on segmenting the RV in both short (SA) and long-axis (LA) cardiac MR images simultaneously. For this task, we propose a new multi-input/output architecture, hybrid 2D/3D geometric spatial TransformEr Multi-Pass fEature pyRAmid (Tempera). Our feature pyramid extends current designs by allowing not only a multi-scale feature output but multi-scale SA and LA input images as well. Tempera transfers learned features between SA and LA images via layer weight sharing and incorporates a geometric target transformer to map the predicted SA segmentation to LA space. Our model achieves an average Dice score of 0.836 and 0.798 for the SA and LA, respectively, and 26.31 mm and 31.19 mm Hausdorff distances. This opens up the potential for the incorporation of RV segmentation models into clinical workflows.
AU - Galazis,C
AU - Wu,H
AU - Li,Z
AU - Petri,C
AU - Bharath,AA
AU - Varela,M
DO - 10.1007/978-3-030-93722-5_29
EP - 276
PB - Springer International Publishing
PY - 2022///
SN - 0302-9743
SP - 268
TI - Tempera: spatial transformer feature pyramid network for cardiac MRI segmentation
UR - http://dx.doi.org/10.1007/978-3-030-93722-5_29
UR - https://link.springer.com/chapter/10.1007/978-3-030-93722-5_29
UR - http://hdl.handle.net/10044/1/104870
ER -