Multi-modal classification of polyp malignancy using CNN features with balanced class augmentation

R. Fonollá; F. van der Sommen; R.M. Schreuder; E.J. Schoon; P.H.N. de With

doi:10.1109/ISBI.2019.8759320

Multi-modal classification of polyp malignancy using CNN features with balanced class augmentation

R. Fonollá, F. van der Sommen, R.M. Schreuder, E.J. Schoon, P.H.N. de With

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

14 Citations (SciVal)

Abstract

Colorectal polyps are an indicator of colorectal cancer (CRC). Classification of polyps during colonoscopy is still a challenge for which many medical experts have come up with visual models albeit with limited success. In this paper, a classification approach is proposed to differentiate between polyp malignancy, using features extracted from the Global Average Pooling (GAP) layer of a Convolutional Neural Network (CNNs). Two recent endoscopic modalities are used to improve the algorithm prediction: Blue Laser Imaging (BLI) and Linked Color Imaging (LCI). Furthermore, a new strategy of per-class data augmentation is adopted to tackle an unbalanced class distribution and to improve the decision of the classifiers. As a result, we increase the performance compared to state-of-the-art methods (0.97 vs 0.90 AUC). Our method for automatic polyp malignancy classification facilitates future advances towards patient safety and may avoid time-consuming and costly histopathological assessment.

Original language	English
Title of host publication	ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging
Place of Publication	Piscataway
Publisher	Institute of Electrical and Electronics Engineers
Pages	74-78
Number of pages	5
ISBN (Electronic)	978-1-5386-3641-1
DOIs	https://doi.org/10.1109/ISBI.2019.8759320
Publication status	Published - 1 Apr 2019
Event	16th IEEE International Symposium on Biomedical Imaging (ISBI 2019) - Venice, Italy Duration: 8 Apr 2019 → 11 Apr 2019 Conference number: 16

Conference

Conference	16th IEEE International Symposium on Biomedical Imaging (ISBI 2019)
Abbreviated title	ISBI 2019
Country/Territory	Italy
City	Venice
Period	8/04/19 → 11/04/19

Keywords

colorectal cancer
deep learning
svm
colonoscopy
BLI
CNN
Blue laser imaging
Linked color imaging
SVM
LCI
Polyp classification
Data augmentation
Bli

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/ISBI.2019.8759320

Cite this

Fonollá, R., Sommen, F. V. D., Schreuder, R. M., Schoon, E. J., & de With, P. H. N. (2019). Multi-modal classification of polyp malignancy using CNN features with balanced class augmentation. In ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging (pp. 74-78). [8759320] Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ISBI.2019.8759320

@inproceedings{0fbf4aad6b5748d88b310752fe9c9fee,

title = "Multi-modal classification of polyp malignancy using CNN features with balanced class augmentation",

abstract = "Colorectal polyps are an indicator of colorectal cancer (CRC). Classification of polyps during colonoscopy is still a challenge for which many medical experts have come up with visual models albeit with limited success. In this paper, a classification approach is proposed to differentiate between polyp malignancy, using features extracted from the Global Average Pooling (GAP) layer of a Convolutional Neural Network (CNNs). Two recent endoscopic modalities are used to improve the algorithm prediction: Blue Laser Imaging (BLI) and Linked Color Imaging (LCI). Furthermore, a new strategy of per-class data augmentation is adopted to tackle an unbalanced class distribution and to improve the decision of the classifiers. As a result, we increase the performance compared to state-of-the-art methods (0.97 vs 0.90 AUC). Our method for automatic polyp malignancy classification facilitates future advances towards patient safety and may avoid time-consuming and costly histopathological assessment.",

keywords = "Polyp classification, Blue Laser Imaging, BLI, Linked Color Imaging, LCI, CNN, Data Augmentation, SVM, colorectal cancer, deep learning, svm, colonoscopy, BLI, CNN, Blue laser imaging, Linked color imaging, SVM, LCI, Polyp classification, Data augmentation, Bli",

author = "R. Fonoll{\'a} and Sommen, {F. van der} and R.M. Schreuder and E.J. Schoon and {de With}, P.H.N.",

year = "2019",

month = apr,

day = "1",

doi = "10.1109/ISBI.2019.8759320",

language = "English",

pages = "74--78",

booktitle = "ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

note = "16th IEEE International Symposium on Biomedical Imaging (ISBI 2019), ISBI 2019 ; Conference date: 08-04-2019 Through 11-04-2019",

}

Fonollá, R , Sommen, FVD, Schreuder, RM, Schoon, EJ & de With, PHN 2019, Multi-modal classification of polyp malignancy using CNN features with balanced class augmentation. in ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging., 8759320, Institute of Electrical and Electronics Engineers, Piscataway , pp. 74-78, 16th IEEE International Symposium on Biomedical Imaging (ISBI 2019), Venice, Italy, 8/04/19. https://doi.org/10.1109/ISBI.2019.8759320

Multi-modal classification of polyp malignancy using CNN features with balanced class augmentation. / Fonollá, R.; Sommen, F. van der; Schreuder, R.M. et al.

ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging. Piscataway : Institute of Electrical and Electronics Engineers, 2019. p. 74-78 8759320.

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

TY - GEN

T1 - Multi-modal classification of polyp malignancy using CNN features with balanced class augmentation

AU - Fonollá, R.

AU - Sommen, F. van der

AU - Schreuder, R.M.

AU - Schoon, E.J.

AU - de With, P.H.N.

N1 - Conference code: 16

PY - 2019/4/1

Y1 - 2019/4/1

N2 - Colorectal polyps are an indicator of colorectal cancer (CRC). Classification of polyps during colonoscopy is still a challenge for which many medical experts have come up with visual models albeit with limited success. In this paper, a classification approach is proposed to differentiate between polyp malignancy, using features extracted from the Global Average Pooling (GAP) layer of a Convolutional Neural Network (CNNs). Two recent endoscopic modalities are used to improve the algorithm prediction: Blue Laser Imaging (BLI) and Linked Color Imaging (LCI). Furthermore, a new strategy of per-class data augmentation is adopted to tackle an unbalanced class distribution and to improve the decision of the classifiers. As a result, we increase the performance compared to state-of-the-art methods (0.97 vs 0.90 AUC). Our method for automatic polyp malignancy classification facilitates future advances towards patient safety and may avoid time-consuming and costly histopathological assessment.

AB - Colorectal polyps are an indicator of colorectal cancer (CRC). Classification of polyps during colonoscopy is still a challenge for which many medical experts have come up with visual models albeit with limited success. In this paper, a classification approach is proposed to differentiate between polyp malignancy, using features extracted from the Global Average Pooling (GAP) layer of a Convolutional Neural Network (CNNs). Two recent endoscopic modalities are used to improve the algorithm prediction: Blue Laser Imaging (BLI) and Linked Color Imaging (LCI). Furthermore, a new strategy of per-class data augmentation is adopted to tackle an unbalanced class distribution and to improve the decision of the classifiers. As a result, we increase the performance compared to state-of-the-art methods (0.97 vs 0.90 AUC). Our method for automatic polyp malignancy classification facilitates future advances towards patient safety and may avoid time-consuming and costly histopathological assessment.

KW - Polyp classification

KW - Blue Laser Imaging

KW - BLI

KW - Linked Color Imaging

KW - LCI

KW - CNN

KW - Data Augmentation

KW - SVM

KW - colorectal cancer

KW - deep learning

KW - svm

KW - colonoscopy

KW - BLI

KW - CNN

KW - Blue laser imaging

KW - Linked color imaging

KW - SVM

KW - LCI

KW - Polyp classification

KW - Data augmentation

KW - Bli

UR - http://www.scopus.com/inward/record.url?scp=85073913836&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2019.8759320

DO - 10.1109/ISBI.2019.8759320

M3 - Conference contribution

SP - 74

EP - 78

BT - ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging

PB - Institute of Electrical and Electronics Engineers

CY - Piscataway

T2 - 16th IEEE International Symposium on Biomedical Imaging (ISBI 2019)

Y2 - 8 April 2019 through 11 April 2019

ER -

Multi-modal classification of polyp malignancy using CNN features with balanced class augmentation

Abstract

Conference

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this