Conference paper

KODYM Oldřich, ŠPANĚL Michal and HEROUT Adam. Segmentation of Head and Neck Organs at Risk Using CNN with Batch Dice Loss. In: Pattern Recognition, 40th German Conference, GCPR 2018 Proceedings. Stuttgart: Springer International Publishing, 2018, pp. 1-9. ISBN 978-3-030-12939-2. ISSN 0302-9743.
Publication language:english
Original title:Segmentation of Head and Neck Organs at Risk Using CNN with Batch Dice Loss
Title (cs):Segmentace orgánů hlavy a krku s využitím CNN s batch Dice loss
Pages:1-9
Proceedings:Pattern Recognition, 40th German Conference, GCPR 2018 Proceedings
Conference:German Conference on Pattern Recognition
Series:LNCS, volume 11269
Place:Stuttgart, DE
Year:2018
ISBN:978-3-030-12939-2
Journal:Lecture Notes in Computer Science, Vol. 2018, No. 11269, DE
ISSN:0302-9743
DOI:10.1007/978-3-030-12939-2
Publisher:Springer International Publishing
Keywords
Convolutional Neural Networks, Computed Tomography, Multi-label Segmentation, Head and Neck Radiotherapy
Annotation
This paper deals with segmentation of organs at risk (OAR) in head and neck area in CT images which is a crucial step for reliable intensity modulated radiotherapy treatment. We introduce a convolution neural network with encoder-decoder architecture and a new loss function, the batch soft Dice loss function, used to train the network. The resulting model produces segmentations of every OAR in the public MICCAI 2015 Head And Neck Auto-Segmentation Challenge dataset. Despite the heavy class imbalance in the data, we improve accuracy of current state-of-the-art methods by 0.33 mm in terms of average surface distance and by 0.11 in terms of Dice overlap coefficient on average. 
BibTeX:
@INPROCEEDINGS{
   author = {Old{\v{r}}ich Kodym and Michal {\v{S}}pan{\v{e}}l
	and Adam Herout},
   title = {Segmentation of Head and Neck Organs at Risk Using
	CNN with Batch Dice Loss},
   pages = {1--9},
   booktitle = {Pattern Recognition, 40th German Conference, GCPR 2018
	Proceedings},
   series = {LNCS, volume 11269},
   journal = {Lecture Notes in Computer Science},
   volume = {2018},
   number = {11269},
   year = {2018},
   location = {Stuttgart, DE},
   publisher = {Springer International Publishing},
   ISBN = {978-3-030-12939-2},
   ISSN = {0302-9743},
   doi = {10.1007/978-3-030-12939-2},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php?id=11677}
}

Your IPv4 address: 3.88.156.58
Switch to https