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

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

doi:10.1109/ICIP.2017.8297005

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 proceeding › Conference contribution

19 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 language	English
Title of host publication	2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings
Publisher	IEEE Computer Society
Pages	3859-3863
Number of pages	5
ISBN (Electronic)	9781509021758
DOIs	https://doi.org/10.1109/ICIP.2017.8297005
Publication status	Published - 2017 Jul 2
Event	24th IEEE International Conference on Image Processing, ICIP 2017 - Beijing, China Duration: 2017 Sept 17 → 2017 Sept 20

Publication series

Name	Proceedings - International Conference on Image Processing, ICIP
Volume	2017-September
ISSN (Print)	1522-4880

Other

Other	24th IEEE International Conference on Image Processing, ICIP 2017
Country/Territory	China
City	Beijing
Period	17/9/17 → 17/9/20

Bibliographical note

Funding Information:
This work was supported partly by the National Research Foundation of Korea(NRF) grant funded by the Korea government(MSIP)(No. NRF-2015R1A2A1A10055037), and partly by the Agency for Defense Development (ADD) and Defense Acquisition Program Administration (DAPA) of Korea (UC160016FD).

Publisher Copyright:
© 2017 IEEE.

Keywords

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

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition
Signal Processing

Access to Document

10.1109/ICIP.2017.8297005

Cite this

Mun, J., Jang, W. D., Sung, D. J., & Kim, C-S. (2017). Comparison of objective functions in CNN-based prostate magnetic resonance image segmentation. In 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings (pp. 3859-3863). (Proceedings - International Conference on Image Processing, ICIP; Vol. 2017-September). 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 et al.
2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings. IEEE Computer Society, 2017. p. 3859-3863 (Proceedings - International Conference on Image Processing, ICIP; Vol. 2017-September).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Mun, J, Jang, WD, Sung, DJ & Kim, C-S 2017, Comparison of objective functions in CNN-based prostate magnetic resonance image segmentation. in 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings. Proceedings - International Conference on Image Processing, ICIP, 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

@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",

note = "Funding Information: This work was supported partly by the National Research Foundation of Korea(NRF) grant funded by the Korea government(MSIP)(No. NRF-2015R1A2A1A10055037), and partly by the Agency for Defense Development (ADD) and Defense Acquisition Program Administration (DAPA) of Korea (UC160016FD). Publisher Copyright: {\textcopyright} 2017 IEEE.; 24th IEEE International Conference on Image Processing, ICIP 2017 ; Conference date: 17-09-2017 Through 20-09-2017",

year = "2017",

month = jul,

day = "2",

doi = "10.1109/ICIP.2017.8297005",

language = "English",

series = "Proceedings - International Conference on Image Processing, ICIP",

publisher = "IEEE Computer Society",

pages = "3859--3863",

booktitle = "2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings",

}

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

N1 - Funding Information: This work was supported partly by the National Research Foundation of Korea(NRF) grant funded by the Korea government(MSIP)(No. NRF-2015R1A2A1A10055037), and partly by the Agency for Defense Development (ADD) and Defense Acquisition Program Administration (DAPA) of Korea (UC160016FD). Publisher Copyright: © 2017 IEEE.

PY - 2017/7/2

Y1 - 2017/7/2

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

U2 - 10.1109/ICIP.2017.8297005

DO - 10.1109/ICIP.2017.8297005

M3 - Conference contribution

AN - SCOPUS:85045344961

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 3859

EP - 3863

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

PB - IEEE Computer Society

T2 - 24th IEEE International Conference on Image Processing, ICIP 2017

Y2 - 17 September 2017 through 20 September 2017

ER -

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

Abstract

Publication series

Other

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this