Efficient nuclei segmentation based on spectral graph partitioning

Gwo-Giun Lee, Shi Yu Hung, Tai Ping Wang, Chun Fu Richard Chen, Chi Kuang Sun, Yi Hua Liao

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

Abstract

Biomedical image processing that offers computer-aided diagnosis is much more popular due to the availability of high quality and large quantity of medical data. Our well-developed biomedical image computing system, which automatically extracts and segments the nucleus and cytoplasm of cell in medical images, is no doubt following this idea. Nonetheless, even though previous system provide good algorithmic performance, its throughput is limited by high computation load and data dependency. Therefore, we deploy spectral graph partitioning to improve computation speed of the most complex module, maker-controlled watershed transform for nuclei detection. By modeling our problem as a graph and embedding architectural costs as the attributes in vertices and edges, we equally distribute workload among processors and reduce overhead in data transfer rate. We deploy the proposed approach on Intel Core i7-930 CPU with four cores and eight threads and test 153 medical images; as a consequence, we achieve less data transfer and better load balance as compared to conventional workload distribution through clustering and other graph partitioning methods.

Original languageEnglish
Title of host publicationISCAS 2016 - IEEE International Symposium on Circuits and Systems
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2723-2726
Number of pages4
ISBN (Electronic)9781479953400
DOIs
Publication statusPublished - 2016 Jul 29
Event2016 IEEE International Symposium on Circuits and Systems, ISCAS 2016 - Montreal, Canada
Duration: 2016 May 222016 May 25

Publication series

NameProceedings - IEEE International Symposium on Circuits and Systems
Volume2016-July
ISSN (Print)0271-4310

Other

Other2016 IEEE International Symposium on Circuits and Systems, ISCAS 2016
CountryCanada
CityMontreal
Period16-05-2216-05-25

Fingerprint

Medical image processing
Data transfer rates
Computer aided diagnosis
Data transfer
Watersheds
Program processors
Throughput
Availability
Costs

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

Cite this

Lee, G-G., Hung, S. Y., Wang, T. P., Chen, C. F. R., Sun, C. K., & Liao, Y. H. (2016). Efficient nuclei segmentation based on spectral graph partitioning. In ISCAS 2016 - IEEE International Symposium on Circuits and Systems (pp. 2723-2726). [7539155] (Proceedings - IEEE International Symposium on Circuits and Systems; Vol. 2016-July). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISCAS.2016.7539155
Lee, Gwo-Giun ; Hung, Shi Yu ; Wang, Tai Ping ; Chen, Chun Fu Richard ; Sun, Chi Kuang ; Liao, Yi Hua. / Efficient nuclei segmentation based on spectral graph partitioning. ISCAS 2016 - IEEE International Symposium on Circuits and Systems. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 2723-2726 (Proceedings - IEEE International Symposium on Circuits and Systems).
@inproceedings{53ee09ae7b2348aa88f61c89f07677da,
title = "Efficient nuclei segmentation based on spectral graph partitioning",
abstract = "Biomedical image processing that offers computer-aided diagnosis is much more popular due to the availability of high quality and large quantity of medical data. Our well-developed biomedical image computing system, which automatically extracts and segments the nucleus and cytoplasm of cell in medical images, is no doubt following this idea. Nonetheless, even though previous system provide good algorithmic performance, its throughput is limited by high computation load and data dependency. Therefore, we deploy spectral graph partitioning to improve computation speed of the most complex module, maker-controlled watershed transform for nuclei detection. By modeling our problem as a graph and embedding architectural costs as the attributes in vertices and edges, we equally distribute workload among processors and reduce overhead in data transfer rate. We deploy the proposed approach on Intel Core i7-930 CPU with four cores and eight threads and test 153 medical images; as a consequence, we achieve less data transfer and better load balance as compared to conventional workload distribution through clustering and other graph partitioning methods.",
author = "Gwo-Giun Lee and Hung, {Shi Yu} and Wang, {Tai Ping} and Chen, {Chun Fu Richard} and Sun, {Chi Kuang} and Liao, {Yi Hua}",
year = "2016",
month = "7",
day = "29",
doi = "10.1109/ISCAS.2016.7539155",
language = "English",
series = "Proceedings - IEEE International Symposium on Circuits and Systems",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "2723--2726",
booktitle = "ISCAS 2016 - IEEE International Symposium on Circuits and Systems",
address = "United States",

}

Lee, G-G, Hung, SY, Wang, TP, Chen, CFR, Sun, CK & Liao, YH 2016, Efficient nuclei segmentation based on spectral graph partitioning. in ISCAS 2016 - IEEE International Symposium on Circuits and Systems., 7539155, Proceedings - IEEE International Symposium on Circuits and Systems, vol. 2016-July, Institute of Electrical and Electronics Engineers Inc., pp. 2723-2726, 2016 IEEE International Symposium on Circuits and Systems, ISCAS 2016, Montreal, Canada, 16-05-22. https://doi.org/10.1109/ISCAS.2016.7539155

Efficient nuclei segmentation based on spectral graph partitioning. / Lee, Gwo-Giun; Hung, Shi Yu; Wang, Tai Ping; Chen, Chun Fu Richard; Sun, Chi Kuang; Liao, Yi Hua.

ISCAS 2016 - IEEE International Symposium on Circuits and Systems. Institute of Electrical and Electronics Engineers Inc., 2016. p. 2723-2726 7539155 (Proceedings - IEEE International Symposium on Circuits and Systems; Vol. 2016-July).

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

TY - GEN

T1 - Efficient nuclei segmentation based on spectral graph partitioning

AU - Lee, Gwo-Giun

AU - Hung, Shi Yu

AU - Wang, Tai Ping

AU - Chen, Chun Fu Richard

AU - Sun, Chi Kuang

AU - Liao, Yi Hua

PY - 2016/7/29

Y1 - 2016/7/29

N2 - Biomedical image processing that offers computer-aided diagnosis is much more popular due to the availability of high quality and large quantity of medical data. Our well-developed biomedical image computing system, which automatically extracts and segments the nucleus and cytoplasm of cell in medical images, is no doubt following this idea. Nonetheless, even though previous system provide good algorithmic performance, its throughput is limited by high computation load and data dependency. Therefore, we deploy spectral graph partitioning to improve computation speed of the most complex module, maker-controlled watershed transform for nuclei detection. By modeling our problem as a graph and embedding architectural costs as the attributes in vertices and edges, we equally distribute workload among processors and reduce overhead in data transfer rate. We deploy the proposed approach on Intel Core i7-930 CPU with four cores and eight threads and test 153 medical images; as a consequence, we achieve less data transfer and better load balance as compared to conventional workload distribution through clustering and other graph partitioning methods.

AB - Biomedical image processing that offers computer-aided diagnosis is much more popular due to the availability of high quality and large quantity of medical data. Our well-developed biomedical image computing system, which automatically extracts and segments the nucleus and cytoplasm of cell in medical images, is no doubt following this idea. Nonetheless, even though previous system provide good algorithmic performance, its throughput is limited by high computation load and data dependency. Therefore, we deploy spectral graph partitioning to improve computation speed of the most complex module, maker-controlled watershed transform for nuclei detection. By modeling our problem as a graph and embedding architectural costs as the attributes in vertices and edges, we equally distribute workload among processors and reduce overhead in data transfer rate. We deploy the proposed approach on Intel Core i7-930 CPU with four cores and eight threads and test 153 medical images; as a consequence, we achieve less data transfer and better load balance as compared to conventional workload distribution through clustering and other graph partitioning methods.

UR - http://www.scopus.com/inward/record.url?scp=84983420742&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84983420742&partnerID=8YFLogxK

U2 - 10.1109/ISCAS.2016.7539155

DO - 10.1109/ISCAS.2016.7539155

M3 - Conference contribution

T3 - Proceedings - IEEE International Symposium on Circuits and Systems

SP - 2723

EP - 2726

BT - ISCAS 2016 - IEEE International Symposium on Circuits and Systems

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Lee G-G, Hung SY, Wang TP, Chen CFR, Sun CK, Liao YH. Efficient nuclei segmentation based on spectral graph partitioning. In ISCAS 2016 - IEEE International Symposium on Circuits and Systems. Institute of Electrical and Electronics Engineers Inc. 2016. p. 2723-2726. 7539155. (Proceedings - IEEE International Symposium on Circuits and Systems). https://doi.org/10.1109/ISCAS.2016.7539155