Comparison of objective functions in CNN-based prostate magnetic resonance image segmentation

Juhyeok Mun, Won Dong Jang, Deuk Jae Sung, Chang-Su Kim

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

We investigate the impacts of objective functions on the performance of deep-learning-based prostate magnetic resonance image segmentation. To this end, we first develop a baseline convolutional neural network (BCNN) for the prostate image segmentation, which consists of encoding, bridge, decoding, and classification modules. In the BCNN, we use 3D convolutional layers to consider volumetric information. Also, we adopt the residual feature forwarding and intermediate feature propagation techniques to make the BCNN reliably trainable for various objective functions. We compare six objective functions: Hamming distance, Euclidean distance, Jaccard index, dice coefficient, cosine similarity, and cross entropy. Experimental results on the PROMISE12 dataset demonstrate that the cosine similarity provides the best segmentation performance, whereas the cross entropy performs the worst.

Original languageEnglish
Title of host publication2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings
PublisherIEEE Computer Society
Pages3859-3863
Number of pages5
Volume2017-September
ISBN (Electronic)9781509021758
DOIs
Publication statusPublished - 2018 Feb 20
Event24th IEEE International Conference on Image Processing, ICIP 2017 - Beijing, China
Duration: 2017 Sep 172017 Sep 20

Other

Other24th IEEE International Conference on Image Processing, ICIP 2017
CountryChina
CityBeijing
Period17/9/1717/9/20

Fingerprint

Magnetic resonance
Image segmentation
Neural networks
Entropy
Hamming distance
Decoding

Keywords

  • 3D convolutional neural networks
  • Medical image segmentation
  • Objective functions
  • Prostate segmentation

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Mun, J., Jang, W. D., Sung, D. J., & Kim, C-S. (2018). Comparison of objective functions in CNN-based prostate magnetic resonance image segmentation. In 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings (Vol. 2017-September, pp. 3859-3863). IEEE Computer Society. https://doi.org/10.1109/ICIP.2017.8297005

Comparison of objective functions in CNN-based prostate magnetic resonance image segmentation. / Mun, Juhyeok; Jang, Won Dong; Sung, Deuk Jae; Kim, Chang-Su.

2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings. Vol. 2017-September IEEE Computer Society, 2018. p. 3859-3863.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Mun, J, Jang, WD, Sung, DJ & Kim, C-S 2018, Comparison of objective functions in CNN-based prostate magnetic resonance image segmentation. in 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings. vol. 2017-September, IEEE Computer Society, pp. 3859-3863, 24th IEEE International Conference on Image Processing, ICIP 2017, Beijing, China, 17/9/17. https://doi.org/10.1109/ICIP.2017.8297005
Mun J, Jang WD, Sung DJ, Kim C-S. Comparison of objective functions in CNN-based prostate magnetic resonance image segmentation. In 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings. Vol. 2017-September. IEEE Computer Society. 2018. p. 3859-3863 https://doi.org/10.1109/ICIP.2017.8297005
Mun, Juhyeok ; Jang, Won Dong ; Sung, Deuk Jae ; Kim, Chang-Su. / Comparison of objective functions in CNN-based prostate magnetic resonance image segmentation. 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings. Vol. 2017-September IEEE Computer Society, 2018. pp. 3859-3863
@inproceedings{ab01b70a97a641ffb0d56f127fe4eac4,
title = "Comparison of objective functions in CNN-based prostate magnetic resonance image segmentation",
abstract = "We investigate the impacts of objective functions on the performance of deep-learning-based prostate magnetic resonance image segmentation. To this end, we first develop a baseline convolutional neural network (BCNN) for the prostate image segmentation, which consists of encoding, bridge, decoding, and classification modules. In the BCNN, we use 3D convolutional layers to consider volumetric information. Also, we adopt the residual feature forwarding and intermediate feature propagation techniques to make the BCNN reliably trainable for various objective functions. We compare six objective functions: Hamming distance, Euclidean distance, Jaccard index, dice coefficient, cosine similarity, and cross entropy. Experimental results on the PROMISE12 dataset demonstrate that the cosine similarity provides the best segmentation performance, whereas the cross entropy performs the worst.",
keywords = "3D convolutional neural networks, Medical image segmentation, Objective functions, Prostate segmentation",
author = "Juhyeok Mun and Jang, {Won Dong} and Sung, {Deuk Jae} and Chang-Su Kim",
year = "2018",
month = "2",
day = "20",
doi = "10.1109/ICIP.2017.8297005",
language = "English",
volume = "2017-September",
pages = "3859--3863",
booktitle = "2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Comparison of objective functions in CNN-based prostate magnetic resonance image segmentation

AU - Mun, Juhyeok

AU - Jang, Won Dong

AU - Sung, Deuk Jae

AU - Kim, Chang-Su

PY - 2018/2/20

Y1 - 2018/2/20

N2 - We investigate the impacts of objective functions on the performance of deep-learning-based prostate magnetic resonance image segmentation. To this end, we first develop a baseline convolutional neural network (BCNN) for the prostate image segmentation, which consists of encoding, bridge, decoding, and classification modules. In the BCNN, we use 3D convolutional layers to consider volumetric information. Also, we adopt the residual feature forwarding and intermediate feature propagation techniques to make the BCNN reliably trainable for various objective functions. We compare six objective functions: Hamming distance, Euclidean distance, Jaccard index, dice coefficient, cosine similarity, and cross entropy. Experimental results on the PROMISE12 dataset demonstrate that the cosine similarity provides the best segmentation performance, whereas the cross entropy performs the worst.

AB - We investigate the impacts of objective functions on the performance of deep-learning-based prostate magnetic resonance image segmentation. To this end, we first develop a baseline convolutional neural network (BCNN) for the prostate image segmentation, which consists of encoding, bridge, decoding, and classification modules. In the BCNN, we use 3D convolutional layers to consider volumetric information. Also, we adopt the residual feature forwarding and intermediate feature propagation techniques to make the BCNN reliably trainable for various objective functions. We compare six objective functions: Hamming distance, Euclidean distance, Jaccard index, dice coefficient, cosine similarity, and cross entropy. Experimental results on the PROMISE12 dataset demonstrate that the cosine similarity provides the best segmentation performance, whereas the cross entropy performs the worst.

KW - 3D convolutional neural networks

KW - Medical image segmentation

KW - Objective functions

KW - Prostate segmentation

UR - http://www.scopus.com/inward/record.url?scp=85045344961&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85045344961&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2017.8297005

DO - 10.1109/ICIP.2017.8297005

M3 - Conference contribution

AN - SCOPUS:85045344961

VL - 2017-September

SP - 3859

EP - 3863

BT - 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings

PB - IEEE Computer Society

ER -