Detail publikace

Segmentation of Head and Neck Organs at Risk Using CNN with Batch Dice Loss

KODYM, O. ŠPANĚL, M. HEROUT, A.

Originální název

Segmentation of Head and Neck Organs at Risk Using CNN with Batch Dice Loss

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

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. 

Klíčová slova

Convolutional Neural Networks, Computed Tomography, Multi-label Segmentation, Head and Neck Radiotherapy

Autoři

KODYM, O.; ŠPANĚL, M.; HEROUT, A.

Vydáno

20. 7. 2018

Nakladatel

Springer International Publishing

Místo

Stuttgart

ISBN

978-3-030-12938-5

Kniha

Pattern Recognition, 40th German Conference, GCPR 2018 Proceedings

Edice

LNCS, volume 11269

ISSN

0302-9743

Periodikum

Lecture Notes in Computer Science

Ročník

2018

Číslo

11269

Stát

Spolková republika Německo

Strany od

105

Strany do

114

Strany počet

9

BibTex

@inproceedings{BUT155013,
  author="Oldřich {Kodym} and Michal {Španěl} and Adam {Herout}",
  title="Segmentation of Head and Neck Organs at Risk Using CNN with Batch Dice Loss",
  booktitle="Pattern Recognition, 40th German Conference, GCPR 2018 Proceedings",
  year="2018",
  series="LNCS, volume 11269",
  journal="Lecture Notes in Computer Science",
  volume="2018",
  number="11269",
  pages="105--114",
  publisher="Springer International Publishing",
  address="Stuttgart",
  doi="10.1007/978-3-030-12939-2\{_}8",
  isbn="978-3-030-12938-5",
  issn="0302-9743"
}