Multi-scale Contrastive Learning for Gastroenteroscopy Classification

Dan Li; Xuechen Li; Zhibin Peng; Wenting Chen; Linlin Shen; Guangyao Wu

doi:10.1109/CBMS58004.2023.00331

Multi-scale Contrastive Learning for Gastroenteroscopy Classification

Dan Li
, Xuechen Li
, Zhibin Peng
, Wenting Chen
, Linlin Shen
, Guangyao Wu

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

Abstract

In gastroenteroscopy image analysis, numerous CADs demonstrate that deep learning aids doctors' diagnosis. The shapes and sizes of the lesions are varied. And in the clinic, the dataset appears to be data imbalanced. However, existing methods directly classify by texture and ignore lesions with various shapes and sizes. To address the issue above, we propose a deep neural network, which consists of multi-scale feature extraction, contrastive feature learning and a multi-scale feature fusion module. We train the contrastive feature learning module and multi-scale feature fusion module simultaneously to alleviate the issue of data distribution differences. Thus, the proposed network can better identify various categories. Extensive experiments on the Hyper Kvasir dataset show that the proposed Hybrid-M2CL outperforms the benchmark proposed by the dataset with 5.0% Macro Precision, 3.3% Macro Recall, 3.4% Macro F1-score, 3.3% Micro Precision, 3.6% MCC. In addition, it outperforms the SOTA by 1.1% Macro F1-score, 2.6% MCC, and 2.0% B-ACC.

Original language	English
Title of host publication	Proceedings - 2023 IEEE 36th International Symposium on Computer-Based Medical Systems, CBMS 2023
Editors	Rosa Sicilia, Bridget Kane, Joao Rafael Almeida, Myra Spiliopoulou, Jose Alberto Benitez Andrades, Giuseppe Placidi, Alejandro Rodriguez Gonzalez
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	852-858
Number of pages	7
ISBN (Electronic)	9798350312249
DOIs	https://doi.org/10.1109/CBMS58004.2023.00331
Publication status	Published - 2023
Externally published	Yes
Event	36th IEEE International Symposium on Computer-Based Medical Systems, CBMS 2023 - L�Aquila, Italy Duration: 22 Jun 2023 → 24 Jun 2023

Publication series

Name	Proceedings - IEEE Symposium on Computer-Based Medical Systems
Volume	2023-June
ISSN (Print)	1063-7125

Conference

Conference	36th IEEE International Symposium on Computer-Based Medical Systems, CBMS 2023
Country/Territory	Italy
City	L�Aquila
Period	22/06/23 → 24/06/23

UN SDGs

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

SDG 3 Good Health and Well-being

Free Keywords

contrastive learning
gastroenterology classification
multi-scale
supervised learning

ASJC Scopus subject areas

Radiology Nuclear Medicine and imaging
Computer Science Applications

Access to Document

10.1109/CBMS58004.2023.00331

Cite this

Li, D., Li, X., Peng, Z., Chen, W., Shen, L., & Wu, G. (2023). Multi-scale Contrastive Learning for Gastroenteroscopy Classification. In R. Sicilia, B. Kane, J. R. Almeida, M. Spiliopoulou, J. A. B. Andrades, G. Placidi, & A. R. Gonzalez (Eds.), Proceedings - 2023 IEEE 36th International Symposium on Computer-Based Medical Systems, CBMS 2023 (pp. 852-858). (Proceedings - IEEE Symposium on Computer-Based Medical Systems; Vol. 2023-June). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CBMS58004.2023.00331

Li, Dan ; Li, Xuechen ; Peng, Zhibin et al. / Multi-scale Contrastive Learning for Gastroenteroscopy Classification. Proceedings - 2023 IEEE 36th International Symposium on Computer-Based Medical Systems, CBMS 2023. editor / Rosa Sicilia ; Bridget Kane ; Joao Rafael Almeida ; Myra Spiliopoulou ; Jose Alberto Benitez Andrades ; Giuseppe Placidi ; Alejandro Rodriguez Gonzalez. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 852-858 (Proceedings - IEEE Symposium on Computer-Based Medical Systems).

@inproceedings{10f2d5d5fbe94f5ea3734ddc0d77b5d0,

title = "Multi-scale Contrastive Learning for Gastroenteroscopy Classification",

abstract = "In gastroenteroscopy image analysis, numerous CADs demonstrate that deep learning aids doctors' diagnosis. The shapes and sizes of the lesions are varied. And in the clinic, the dataset appears to be data imbalanced. However, existing methods directly classify by texture and ignore lesions with various shapes and sizes. To address the issue above, we propose a deep neural network, which consists of multi-scale feature extraction, contrastive feature learning and a multi-scale feature fusion module. We train the contrastive feature learning module and multi-scale feature fusion module simultaneously to alleviate the issue of data distribution differences. Thus, the proposed network can better identify various categories. Extensive experiments on the Hyper Kvasir dataset show that the proposed Hybrid-M2CL outperforms the benchmark proposed by the dataset with 5.0\% Macro Precision, 3.3\% Macro Recall, 3.4\% Macro F1-score, 3.3\% Micro Precision, 3.6\% MCC. In addition, it outperforms the SOTA by 1.1\% Macro F1-score, 2.6\% MCC, and 2.0\% B-ACC.",

keywords = "contrastive learning, gastroenterology classification, multi-scale, supervised learning",

author = "Dan Li and Xuechen Li and Zhibin Peng and Wenting Chen and Linlin Shen and Guangyao Wu",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 36th IEEE International Symposium on Computer-Based Medical Systems, CBMS 2023 ; Conference date: 22-06-2023 Through 24-06-2023",

year = "2023",

doi = "10.1109/CBMS58004.2023.00331",

language = "English",

series = "Proceedings - IEEE Symposium on Computer-Based Medical Systems",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "852--858",

editor = "Rosa Sicilia and Bridget Kane and Almeida, \{Joao Rafael\} and Myra Spiliopoulou and Andrades, \{Jose Alberto Benitez\} and Giuseppe Placidi and Gonzalez, \{Alejandro Rodriguez\}",

booktitle = "Proceedings - 2023 IEEE 36th International Symposium on Computer-Based Medical Systems, CBMS 2023",

address = "United States",

}

Li, D, Li, X, Peng, Z, Chen, W, Shen, L & Wu, G 2023, Multi-scale Contrastive Learning for Gastroenteroscopy Classification. in R Sicilia, B Kane, JR Almeida, M Spiliopoulou, JAB Andrades, G Placidi & AR Gonzalez (eds), Proceedings - 2023 IEEE 36th International Symposium on Computer-Based Medical Systems, CBMS 2023. Proceedings - IEEE Symposium on Computer-Based Medical Systems, vol. 2023-June, Institute of Electrical and Electronics Engineers Inc., pp. 852-858, 36th IEEE International Symposium on Computer-Based Medical Systems, CBMS 2023, L�Aquila, Italy, 22/06/23. https://doi.org/10.1109/CBMS58004.2023.00331

Multi-scale Contrastive Learning for Gastroenteroscopy Classification. / Li, Dan; Li, Xuechen; Peng, Zhibin et al.
Proceedings - 2023 IEEE 36th International Symposium on Computer-Based Medical Systems, CBMS 2023. ed. / Rosa Sicilia; Bridget Kane; Joao Rafael Almeida; Myra Spiliopoulou; Jose Alberto Benitez Andrades; Giuseppe Placidi; Alejandro Rodriguez Gonzalez. Institute of Electrical and Electronics Engineers Inc., 2023. p. 852-858 (Proceedings - IEEE Symposium on Computer-Based Medical Systems; Vol. 2023-June).

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

TY - GEN

T1 - Multi-scale Contrastive Learning for Gastroenteroscopy Classification

AU - Li, Dan

AU - Li, Xuechen

AU - Peng, Zhibin

AU - Chen, Wenting

AU - Shen, Linlin

AU - Wu, Guangyao

PY - 2023

Y1 - 2023

N2 - In gastroenteroscopy image analysis, numerous CADs demonstrate that deep learning aids doctors' diagnosis. The shapes and sizes of the lesions are varied. And in the clinic, the dataset appears to be data imbalanced. However, existing methods directly classify by texture and ignore lesions with various shapes and sizes. To address the issue above, we propose a deep neural network, which consists of multi-scale feature extraction, contrastive feature learning and a multi-scale feature fusion module. We train the contrastive feature learning module and multi-scale feature fusion module simultaneously to alleviate the issue of data distribution differences. Thus, the proposed network can better identify various categories. Extensive experiments on the Hyper Kvasir dataset show that the proposed Hybrid-M2CL outperforms the benchmark proposed by the dataset with 5.0% Macro Precision, 3.3% Macro Recall, 3.4% Macro F1-score, 3.3% Micro Precision, 3.6% MCC. In addition, it outperforms the SOTA by 1.1% Macro F1-score, 2.6% MCC, and 2.0% B-ACC.

AB - In gastroenteroscopy image analysis, numerous CADs demonstrate that deep learning aids doctors' diagnosis. The shapes and sizes of the lesions are varied. And in the clinic, the dataset appears to be data imbalanced. However, existing methods directly classify by texture and ignore lesions with various shapes and sizes. To address the issue above, we propose a deep neural network, which consists of multi-scale feature extraction, contrastive feature learning and a multi-scale feature fusion module. We train the contrastive feature learning module and multi-scale feature fusion module simultaneously to alleviate the issue of data distribution differences. Thus, the proposed network can better identify various categories. Extensive experiments on the Hyper Kvasir dataset show that the proposed Hybrid-M2CL outperforms the benchmark proposed by the dataset with 5.0% Macro Precision, 3.3% Macro Recall, 3.4% Macro F1-score, 3.3% Micro Precision, 3.6% MCC. In addition, it outperforms the SOTA by 1.1% Macro F1-score, 2.6% MCC, and 2.0% B-ACC.

KW - contrastive learning

KW - gastroenterology classification

KW - multi-scale

KW - supervised learning

UR - https://www.scopus.com/pages/publications/85166470240

U2 - 10.1109/CBMS58004.2023.00331

DO - 10.1109/CBMS58004.2023.00331

M3 - Conference contribution

AN - SCOPUS:85166470240

T3 - Proceedings - IEEE Symposium on Computer-Based Medical Systems

SP - 852

EP - 858

BT - Proceedings - 2023 IEEE 36th International Symposium on Computer-Based Medical Systems, CBMS 2023

A2 - Sicilia, Rosa

A2 - Kane, Bridget

A2 - Almeida, Joao Rafael

A2 - Spiliopoulou, Myra

A2 - Andrades, Jose Alberto Benitez

A2 - Placidi, Giuseppe

A2 - Gonzalez, Alejandro Rodriguez

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 36th IEEE International Symposium on Computer-Based Medical Systems, CBMS 2023

Y2 - 22 June 2023 through 24 June 2023

ER -

Li D, Li X, Peng Z, Chen W, Shen L, Wu G. Multi-scale Contrastive Learning for Gastroenteroscopy Classification. In Sicilia R, Kane B, Almeida JR, Spiliopoulou M, Andrades JAB, Placidi G, Gonzalez AR, editors, Proceedings - 2023 IEEE 36th International Symposium on Computer-Based Medical Systems, CBMS 2023. Institute of Electrical and Electronics Engineers Inc. 2023. p. 852-858. (Proceedings - IEEE Symposium on Computer-Based Medical Systems). doi: 10.1109/CBMS58004.2023.00331

Multi-scale Contrastive Learning for Gastroenteroscopy Classification

Abstract

Publication series

Conference

UN SDGs

Free Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this