Image Features for Automated Colorectal Polyp Classification Based on Clinical Prediction Models

M.C.A. van Grinsven; Thom Scheeve; Ramon-Michel Schreuder; Fons van der Sommen; Erik J. Schoon; Peter de With

doi:10.1109/ICIP.2019.8803822

Image Features for Automated Colorectal Polyp Classification Based on Clinical Prediction Models

M.C.A. van Grinsven, Thom Scheeve, Ramon-Michel Schreuder, Fons van der Sommen, Erik J. Schoon, Peter de With

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

3 Citations (Scopus)

Abstract

Accurate endoscopic differentiation on resection of colorectal polyps (CRPs) (resect-discard or diagnose-leave strategies) increases cost-efficiency and reduces patient risk. We aim to develop a classification algorithm for automated differentiation of CRPs, by following the validated clinical Work-group serrAted polypS and Polyposis (WASP) classification scheme. Quantitative image features are investigated for each individual WASP criterion and classification is performed by conventional SVM. The technical WASP model results in areas under the curve of 0.87-0.95 and accuracies of 78-89%. Predicting polyp histology using model-based learning out-performs medical experts (accuracy, 87-93% vs 86 87%). Direct classification predicts more premalignant polyps-as being benign, compared to the automated WASP scheme. These errors do not occur when including ROC characteristics to the WASP model. The proposed WASP model is the first automated system, competing with medical expert classification.

Original language	English
Title of host publication	2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings
Place of Publication	Piscataway
Publisher	Institute of Electrical and Electronics Engineers
Pages	210-214
Number of pages	5
ISBN (Electronic)	978-1-5386-6249-6
ISBN (Print)	978-1-5386-6250-2
DOIs	https://doi.org/10.1109/ICIP.2019.8803822
Publication status	Published - 26 Aug 2019
Event	26th IEEE International Conference on Image Processing, ICIP 2019 - Taipei, Taiwan Duration: 22 Sept 2019 → 25 Sept 2019

Conference

Conference	26th IEEE International Conference on Image Processing, ICIP 2019
Country/Territory	Taiwan
City	Taipei
Period	22/09/19 → 25/09/19

Bibliographical note

Publisher Copyright:
© 2019 IEEE.

Keywords

Colorectal polyps
Quantitative features
Coputer-aided diagnosis
SVM
Gastroenterology
quantitative features
gastroenterology
computer-aided diagnosis

Access to Document

10.1109/ICIP.2019.8803822

Cite this

van Grinsven, M. C. A., Scheeve, T., Schreuder, R.-M., van der Sommen, F., Schoon, E. J., & de With, P. (2019). Image Features for Automated Colorectal Polyp Classification Based on Clinical Prediction Models. In 2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings (pp. 210-214). Article 8803822 Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ICIP.2019.8803822

@inproceedings{f98037c7d8af48cc8638069493ed91af,

title = "Image Features for Automated Colorectal Polyp Classification Based on Clinical Prediction Models",

abstract = "Accurate endoscopic differentiation on resection of colorectal polyps (CRPs) (resect-discard or diagnose-leave strategies) increases cost-efficiency and reduces patient risk. We aim to develop a classification algorithm for automated differentiation of CRPs, by following the validated clinical Work-group serrAted polypS and Polyposis (WASP) classification scheme. Quantitative image features are investigated for each individual WASP criterion and classification is performed by conventional SVM. The technical WASP model results in areas under the curve of 0.87-0.95 and accuracies of 78-89%. Predicting polyp histology using model-based learning out-performs medical experts (accuracy, 87-93% vs 86 87%). Direct classification predicts more premalignant polyps-as being benign, compared to the automated WASP scheme. These errors do not occur when including ROC characteristics to the WASP model. The proposed WASP model is the first automated system, competing with medical expert classification.",

keywords = "Colorectal polyps, Quantitative features, Coputer-aided diagnosis, SVM, Gastroenterology, quantitative features, gastroenterology, computer-aided diagnosis",

author = "{van Grinsven}, M.C.A. and Thom Scheeve and Ramon-Michel Schreuder and {van der Sommen}, Fons and Schoon, {Erik J.} and {de With}, Peter",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 26th IEEE International Conference on Image Processing, ICIP 2019 ; Conference date: 22-09-2019 Through 25-09-2019",

year = "2019",

month = aug,

day = "26",

doi = "10.1109/ICIP.2019.8803822",

language = "English",

isbn = "978-1-5386-6250-2",

pages = "210--214",

booktitle = "2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

}

van Grinsven, MCA, Scheeve, T, Schreuder, R-M, van der Sommen, F, Schoon, EJ & de With, P 2019, Image Features for Automated Colorectal Polyp Classification Based on Clinical Prediction Models. in 2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings., 8803822, Institute of Electrical and Electronics Engineers, Piscataway, pp. 210-214, 26th IEEE International Conference on Image Processing, ICIP 2019, Taipei, Taiwan, 22/09/19. https://doi.org/10.1109/ICIP.2019.8803822

Image Features for Automated Colorectal Polyp Classification Based on Clinical Prediction Models. / van Grinsven, M.C.A.; Scheeve, Thom; Schreuder, Ramon-Michel et al.
2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings. Piscataway: Institute of Electrical and Electronics Engineers, 2019. p. 210-214 8803822.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Image Features for Automated Colorectal Polyp Classification Based on Clinical Prediction Models

AU - van Grinsven, M.C.A.

AU - Scheeve, Thom

AU - Schreuder, Ramon-Michel

AU - van der Sommen, Fons

AU - Schoon, Erik J.

AU - de With, Peter

PY - 2019/8/26

Y1 - 2019/8/26

N2 - Accurate endoscopic differentiation on resection of colorectal polyps (CRPs) (resect-discard or diagnose-leave strategies) increases cost-efficiency and reduces patient risk. We aim to develop a classification algorithm for automated differentiation of CRPs, by following the validated clinical Work-group serrAted polypS and Polyposis (WASP) classification scheme. Quantitative image features are investigated for each individual WASP criterion and classification is performed by conventional SVM. The technical WASP model results in areas under the curve of 0.87-0.95 and accuracies of 78-89%. Predicting polyp histology using model-based learning out-performs medical experts (accuracy, 87-93% vs 86 87%). Direct classification predicts more premalignant polyps-as being benign, compared to the automated WASP scheme. These errors do not occur when including ROC characteristics to the WASP model. The proposed WASP model is the first automated system, competing with medical expert classification.

AB - Accurate endoscopic differentiation on resection of colorectal polyps (CRPs) (resect-discard or diagnose-leave strategies) increases cost-efficiency and reduces patient risk. We aim to develop a classification algorithm for automated differentiation of CRPs, by following the validated clinical Work-group serrAted polypS and Polyposis (WASP) classification scheme. Quantitative image features are investigated for each individual WASP criterion and classification is performed by conventional SVM. The technical WASP model results in areas under the curve of 0.87-0.95 and accuracies of 78-89%. Predicting polyp histology using model-based learning out-performs medical experts (accuracy, 87-93% vs 86 87%). Direct classification predicts more premalignant polyps-as being benign, compared to the automated WASP scheme. These errors do not occur when including ROC characteristics to the WASP model. The proposed WASP model is the first automated system, competing with medical expert classification.

KW - Colorectal polyps

KW - Quantitative features

KW - Coputer-aided diagnosis

KW - SVM

KW - Gastroenterology

KW - quantitative features

KW - gastroenterology

KW - computer-aided diagnosis

UR - http://www.scopus.com/inward/record.url?scp=85076820010&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2019.8803822

DO - 10.1109/ICIP.2019.8803822

M3 - Conference contribution

AN - SCOPUS:85076820010

SN - 978-1-5386-6250-2

SP - 210

EP - 214

BT - 2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings

PB - Institute of Electrical and Electronics Engineers

CY - Piscataway

T2 - 26th IEEE International Conference on Image Processing, ICIP 2019

Y2 - 22 September 2019 through 25 September 2019

ER -

van Grinsven MCA, Scheeve T, Schreuder RM, van der Sommen F, Schoon EJ, de With P. Image Features for Automated Colorectal Polyp Classification Based on Clinical Prediction Models. In 2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings. Piscataway: Institute of Electrical and Electronics Engineers. 2019. p. 210-214. 8803822 doi: 10.1109/ICIP.2019.8803822

Image Features for Automated Colorectal Polyp Classification Based on Clinical Prediction Models

Abstract

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint