Bladder cancer segmentation on multispectral images

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

1 Downloads (Pure)

Abstract

Nonmuscle Invasive Bladder Cancer (NMIBC) has high incidence, and close follow-up with cystoscopy is necessary due to its high recurrence rate after initial treatment, estimated to be as high as 75%. Because of the high recurrence rate, it is vital that the detection of bladder cancer is improved. Computer automated detection algorithms have shown to be exceptionally effective in achieving this goal. This paper presents the first automated segmentation algorithm for bladder cancer in endoscopic images. The second purpose of this study is to determine which modality is best suited for computer-aided segmentation of bladder cancer. Gabor and color features are extracted from 20 patients in four different modalities with a block-based strategy. Three different classifiers are used to classify the blocks and post-processing is applied to obtain a segmented region. The best classification results were obtained by using a support vector machine and the Spectrum B modality. Additionally, color features were found to be effective for obtaining segmentations comparable to experts.

Original languageEnglish
Title of host publicationProceedings of the 12th International Conference on Distributed Smart Cameras, ICDSC 2018
Place of PublicationNew York
PublisherAssociation for Computing Machinery, Inc
Number of pages4
ISBN (Electronic)978-1-4503-6511-6
DOIs
Publication statusPublished - 3 Sep 2018
Event12th International Conference on Distributed Smart Cameras, ICDSC 2018 - Eindhoven, Netherlands
Duration: 3 Sep 20184 Sep 2018

Conference

Conference12th International Conference on Distributed Smart Cameras, ICDSC 2018
CountryNetherlands
CityEindhoven
Period3/09/184/09/18

Fingerprint

Color
Support vector machines
Classifiers
Processing

Keywords

  • Bladder cancer
  • Computer-aided diagnosis
  • Features
  • Radiomics
  • Segmentation

Cite this

van der Putten, J., van der Sommen, F., Zinger, S., de Bruin, D. M., Kamphuis, G., & de With, P. H. N. (2018). Bladder cancer segmentation on multispectral images. In Proceedings of the 12th International Conference on Distributed Smart Cameras, ICDSC 2018 [a13] New York: Association for Computing Machinery, Inc. https://doi.org/10.1145/3243394.3243702
van der Putten, Joost ; van der Sommen, Fons ; Zinger, Svitlana ; de Bruin, Daniel M. ; Kamphuis, Guido ; de With, Peter H.N. / Bladder cancer segmentation on multispectral images. Proceedings of the 12th International Conference on Distributed Smart Cameras, ICDSC 2018. New York : Association for Computing Machinery, Inc, 2018.
@inproceedings{52ff1fd5694b4299b05145fc6000c53d,
title = "Bladder cancer segmentation on multispectral images",
abstract = "Nonmuscle Invasive Bladder Cancer (NMIBC) has high incidence, and close follow-up with cystoscopy is necessary due to its high recurrence rate after initial treatment, estimated to be as high as 75{\%}. Because of the high recurrence rate, it is vital that the detection of bladder cancer is improved. Computer automated detection algorithms have shown to be exceptionally effective in achieving this goal. This paper presents the first automated segmentation algorithm for bladder cancer in endoscopic images. The second purpose of this study is to determine which modality is best suited for computer-aided segmentation of bladder cancer. Gabor and color features are extracted from 20 patients in four different modalities with a block-based strategy. Three different classifiers are used to classify the blocks and post-processing is applied to obtain a segmented region. The best classification results were obtained by using a support vector machine and the Spectrum B modality. Additionally, color features were found to be effective for obtaining segmentations comparable to experts.",
keywords = "Bladder cancer, Computer-aided diagnosis, Features, Radiomics, Segmentation",
author = "{van der Putten}, Joost and {van der Sommen}, Fons and Svitlana Zinger and {de Bruin}, {Daniel M.} and Guido Kamphuis and {de With}, {Peter H.N.}",
year = "2018",
month = "9",
day = "3",
doi = "10.1145/3243394.3243702",
language = "English",
booktitle = "Proceedings of the 12th International Conference on Distributed Smart Cameras, ICDSC 2018",
publisher = "Association for Computing Machinery, Inc",
address = "United States",

}

van der Putten, J, van der Sommen, F, Zinger, S, de Bruin, DM, Kamphuis, G & de With, PHN 2018, Bladder cancer segmentation on multispectral images. in Proceedings of the 12th International Conference on Distributed Smart Cameras, ICDSC 2018., a13, Association for Computing Machinery, Inc, New York, 12th International Conference on Distributed Smart Cameras, ICDSC 2018, Eindhoven, Netherlands, 3/09/18. https://doi.org/10.1145/3243394.3243702

Bladder cancer segmentation on multispectral images. / van der Putten, Joost; van der Sommen, Fons; Zinger, Svitlana; de Bruin, Daniel M.; Kamphuis, Guido; de With, Peter H.N.

Proceedings of the 12th International Conference on Distributed Smart Cameras, ICDSC 2018. New York : Association for Computing Machinery, Inc, 2018. a13.

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Bladder cancer segmentation on multispectral images

AU - van der Putten, Joost

AU - van der Sommen, Fons

AU - Zinger, Svitlana

AU - de Bruin, Daniel M.

AU - Kamphuis, Guido

AU - de With, Peter H.N.

PY - 2018/9/3

Y1 - 2018/9/3

N2 - Nonmuscle Invasive Bladder Cancer (NMIBC) has high incidence, and close follow-up with cystoscopy is necessary due to its high recurrence rate after initial treatment, estimated to be as high as 75%. Because of the high recurrence rate, it is vital that the detection of bladder cancer is improved. Computer automated detection algorithms have shown to be exceptionally effective in achieving this goal. This paper presents the first automated segmentation algorithm for bladder cancer in endoscopic images. The second purpose of this study is to determine which modality is best suited for computer-aided segmentation of bladder cancer. Gabor and color features are extracted from 20 patients in four different modalities with a block-based strategy. Three different classifiers are used to classify the blocks and post-processing is applied to obtain a segmented region. The best classification results were obtained by using a support vector machine and the Spectrum B modality. Additionally, color features were found to be effective for obtaining segmentations comparable to experts.

AB - Nonmuscle Invasive Bladder Cancer (NMIBC) has high incidence, and close follow-up with cystoscopy is necessary due to its high recurrence rate after initial treatment, estimated to be as high as 75%. Because of the high recurrence rate, it is vital that the detection of bladder cancer is improved. Computer automated detection algorithms have shown to be exceptionally effective in achieving this goal. This paper presents the first automated segmentation algorithm for bladder cancer in endoscopic images. The second purpose of this study is to determine which modality is best suited for computer-aided segmentation of bladder cancer. Gabor and color features are extracted from 20 patients in four different modalities with a block-based strategy. Three different classifiers are used to classify the blocks and post-processing is applied to obtain a segmented region. The best classification results were obtained by using a support vector machine and the Spectrum B modality. Additionally, color features were found to be effective for obtaining segmentations comparable to experts.

KW - Bladder cancer

KW - Computer-aided diagnosis

KW - Features

KW - Radiomics

KW - Segmentation

UR - http://www.scopus.com/inward/record.url?scp=85056621694&partnerID=8YFLogxK

U2 - 10.1145/3243394.3243702

DO - 10.1145/3243394.3243702

M3 - Conference contribution

AN - SCOPUS:85056621694

BT - Proceedings of the 12th International Conference on Distributed Smart Cameras, ICDSC 2018

PB - Association for Computing Machinery, Inc

CY - New York

ER -

van der Putten J, van der Sommen F, Zinger S, de Bruin DM, Kamphuis G, de With PHN. Bladder cancer segmentation on multispectral images. In Proceedings of the 12th International Conference on Distributed Smart Cameras, ICDSC 2018. New York: Association for Computing Machinery, Inc. 2018. a13 https://doi.org/10.1145/3243394.3243702